Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,14 @@ models/checkpoints/memo/misc/face_analysis/misc/face_analysis/models/face_landma
 models/checkpoints/memo/misc/face_analysis/models/face_landmarker_v2_with_blendshapes.task filter=lfs diff=lfs merge=lfs -text
 models/diffusers/models--ZhengPeng7--BiRefNet/blobs/77277264c0e8c74149d3ff2fade4fd8176965b7108f3c5fc3b8c9c811edb4519 filter=lfs diff=lfs merge=lfs -text
 models/diffusers/models--huanngzh--mv-adapter/blobs/260e486d507247db30601d22de317e3f9c07f75a29912d43ed5c3a4aab4db4c9 filter=lfs diff=lfs merge=lfs -text
+models/BiRefNet/RMBG-2.0/collage5.png filter=lfs diff=lfs merge=lfs -text
+models/BiRefNet/RMBG-2.0/t4.png filter=lfs diff=lfs merge=lfs -text
+models/FILM/L1/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+models/FILM/Style/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+models/FILM/VGG/saved_model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+models/Janus-Pro/Janus-Pro-7B/janus_pro_teaser2.png filter=lfs diff=lfs merge=lfs -text
+models/OmniGen/OmniGen-v1/demo_cases.png filter=lfs diff=lfs merge=lfs -text
+models/blip/models--Salesforce--blip-image-captioning-base/blobs/d6638651a5526cc2ede56f2b5104d6851b0755816d220e5e046870430180c767 filter=lfs diff=lfs merge=lfs -text
+models/blip/models--Salesforce--blip-vqa-base/blobs/33786eed34def0c95fa948128cb4386be9b9219aa2c2e25f1c9c744692121bb7 filter=lfs diff=lfs merge=lfs -text
+models/clip_interrogator/models--timm--vit_large_patch14_clip_224.openai/blobs/9ce2e8a8ebfff3793d7d375ad6d3c35cb9aebf3de7ace0fc7308accab7cd207e filter=lfs diff=lfs merge=lfs -text
+models/x-portrait/model_state-415001.th filter=lfs diff=lfs merge=lfs -text

models/BiRefNet/RMBG-2.0/.gitattributes

@@ -0,0 +1,40 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model_not_working.not_safetensors filter=lfs diff=lfs merge=lfs -text
+t4.png filter=lfs diff=lfs merge=lfs -text
+collage.png filter=lfs diff=lfs merge=lfs -text
+collage3.png filter=lfs diff=lfs merge=lfs -text
+collage5.png filter=lfs diff=lfs merge=lfs -text

models/BiRefNet/RMBG-2.0/BiRefNet_config.py

@@ -0,0 +1,11 @@
+from transformers import PretrainedConfig
+
+class BiRefNetConfig(PretrainedConfig):
+    model_type = "SegformerForSemanticSegmentation"
+    def __init__(
+        self,
+        bb_pretrained=False,
+        **kwargs
+    ):
+        self.bb_pretrained = bb_pretrained
+        super().__init__(**kwargs)

models/BiRefNet/RMBG-2.0/birefnet.py

@@ -0,0 +1,2244 @@
+### config.py
+
+import os
+import math
+
+
+class Config():
+    def __init__(self) -> None:
+        # PATH settings
+        self.sys_home_dir = os.path.expanduser('~')    # Make up your file system as: SYS_HOME_DIR/codes/dis/BiRefNet, SYS_HOME_DIR/datasets/dis/xx, SYS_HOME_DIR/weights/xx
+
+        # TASK settings
+        self.task = ['DIS5K', 'COD', 'HRSOD', 'DIS5K+HRSOD+HRS10K', 'P3M-10k'][0]
+        self.training_set = {
+            'DIS5K': ['DIS-TR', 'DIS-TR+DIS-TE1+DIS-TE2+DIS-TE3+DIS-TE4'][0],
+            'COD': 'TR-COD10K+TR-CAMO',
+            'HRSOD': ['TR-DUTS', 'TR-HRSOD', 'TR-UHRSD', 'TR-DUTS+TR-HRSOD', 'TR-DUTS+TR-UHRSD', 'TR-HRSOD+TR-UHRSD', 'TR-DUTS+TR-HRSOD+TR-UHRSD'][5],
+            'DIS5K+HRSOD+HRS10K': 'DIS-TE1+DIS-TE2+DIS-TE3+DIS-TE4+DIS-TR+TE-HRS10K+TE-HRSOD+TE-UHRSD+TR-HRS10K+TR-HRSOD+TR-UHRSD',     # leave DIS-VD for evaluation.
+            'P3M-10k': 'TR-P3M-10k',
+        }[self.task]
+        self.prompt4loc = ['dense', 'sparse'][0]
+
+        # Faster-Training settings
+        self.load_all = True
+        self.compile = True     # 1. Trigger CPU memory leak in some extend, which is an inherent problem of PyTorch.
+                                #   Machines with > 70GB CPU memory can run the whole training on DIS5K with default setting.
+                                # 2. Higher PyTorch version may fix it: https://github.com/pytorch/pytorch/issues/119607.
+                                # 3. But compile in Pytorch > 2.0.1 seems to bring no acceleration for training.
+        self.precisionHigh = True
+
+        # MODEL settings
+        self.ms_supervision = True
+        self.out_ref = self.ms_supervision and True
+        self.dec_ipt = True
+        self.dec_ipt_split = True
+        self.cxt_num = [0, 3][1]    # multi-scale skip connections from encoder
+        self.mul_scl_ipt = ['', 'add', 'cat'][2]
+        self.dec_att = ['', 'ASPP', 'ASPPDeformable'][2]
+        self.squeeze_block = ['', 'BasicDecBlk_x1', 'ResBlk_x4', 'ASPP_x3', 'ASPPDeformable_x3'][1]
+        self.dec_blk = ['BasicDecBlk', 'ResBlk', 'HierarAttDecBlk'][0]
+
+        # TRAINING settings
+        self.batch_size = 4
+        self.IoU_finetune_last_epochs = [
+            0,
+            {
+                'DIS5K': -50,
+                'COD': -20,
+                'HRSOD': -20,
+                'DIS5K+HRSOD+HRS10K': -20,
+                'P3M-10k': -20,
+            }[self.task]
+        ][1]    # choose 0 to skip
+        self.lr = (1e-4 if 'DIS5K' in self.task else 1e-5) * math.sqrt(self.batch_size / 4)     # DIS needs high lr to converge faster. Adapt the lr linearly
+        self.size = 1024
+        self.num_workers = max(4, self.batch_size)          # will be decrease to min(it, batch_size) at the initialization of the data_loader
+
+        # Backbone settings
+        self.bb = [
+            'vgg16', 'vgg16bn', 'resnet50',         # 0, 1, 2
+            'swin_v1_t', 'swin_v1_s',               # 3, 4
+            'swin_v1_b', 'swin_v1_l',               # 5-bs9, 6-bs4
+            'pvt_v2_b0', 'pvt_v2_b1',               # 7, 8
+            'pvt_v2_b2', 'pvt_v2_b5',               # 9-bs10, 10-bs5
+        ][6]
+        self.lateral_channels_in_collection = {
+            'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
+            'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
+            'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
+            'swin_v1_t': [768, 384, 192, 96], 'swin_v1_s': [768, 384, 192, 96],
+            'pvt_v2_b0': [256, 160, 64, 32], 'pvt_v2_b1': [512, 320, 128, 64],
+        }[self.bb]
+        if self.mul_scl_ipt == 'cat':
+            self.lateral_channels_in_collection = [channel * 2 for channel in self.lateral_channels_in_collection]
+        self.cxt = self.lateral_channels_in_collection[1:][::-1][-self.cxt_num:] if self.cxt_num else []
+
+        # MODEL settings - inactive
+        self.lat_blk = ['BasicLatBlk'][0]
+        self.dec_channels_inter = ['fixed', 'adap'][0]
+        self.refine = ['', 'itself', 'RefUNet', 'Refiner', 'RefinerPVTInChannels4'][0]
+        self.progressive_ref = self.refine and True
+        self.ender = self.progressive_ref and False
+        self.scale = self.progressive_ref and 2
+        self.auxiliary_classification = False       # Only for DIS5K, where class labels are saved in `dataset.py`.
+        self.refine_iteration = 1
+        self.freeze_bb = False
+        self.model = [
+            'BiRefNet',
+        ][0]
+        if self.dec_blk == 'HierarAttDecBlk':
+            self.batch_size = 2 ** [0, 1, 2, 3, 4][2]
+
+        # TRAINING settings - inactive
+        self.preproc_methods = ['flip', 'enhance', 'rotate', 'pepper', 'crop'][:4]
+        self.optimizer = ['Adam', 'AdamW'][1]
+        self.lr_decay_epochs = [1e5]    # Set to negative N to decay the lr in the last N-th epoch.
+        self.lr_decay_rate = 0.5
+        # Loss
+        self.lambdas_pix_last = {
+            # not 0 means opening this loss
+            # original rate -- 1 : 30 : 1.5 : 0.2, bce x 30
+            'bce': 30 * 1,          # high performance
+            'iou': 0.5 * 1,         # 0 / 255
+            'iou_patch': 0.5 * 0,   # 0 / 255, win_size = (64, 64)
+            'mse': 150 * 0,         # can smooth the saliency map
+            'triplet': 3 * 0,
+            'reg': 100 * 0,
+            'ssim': 10 * 1,          # help contours,
+            'cnt': 5 * 0,          # help contours
+            'structure': 5 * 0,    # structure loss from codes of MVANet. A little improvement on DIS-TE[1,2,3], a bit more decrease on DIS-TE4.
+        }
+        self.lambdas_cls = {
+            'ce': 5.0
+        }
+        # Adv
+        self.lambda_adv_g = 10. * 0        # turn to 0 to avoid adv training
+        self.lambda_adv_d = 3. * (self.lambda_adv_g > 0)
+
+        # PATH settings - inactive
+        self.data_root_dir = os.path.join(self.sys_home_dir, 'datasets/dis')
+        self.weights_root_dir = os.path.join(self.sys_home_dir, 'weights')
+        self.weights = {
+            'pvt_v2_b2': os.path.join(self.weights_root_dir, 'pvt_v2_b2.pth'),
+            'pvt_v2_b5': os.path.join(self.weights_root_dir, ['pvt_v2_b5.pth', 'pvt_v2_b5_22k.pth'][0]),
+            'swin_v1_b': os.path.join(self.weights_root_dir, ['swin_base_patch4_window12_384_22kto1k.pth', 'swin_base_patch4_window12_384_22k.pth'][0]),
+            'swin_v1_l': os.path.join(self.weights_root_dir, ['swin_large_patch4_window12_384_22kto1k.pth', 'swin_large_patch4_window12_384_22k.pth'][0]),
+            'swin_v1_t': os.path.join(self.weights_root_dir, ['swin_tiny_patch4_window7_224_22kto1k_finetune.pth'][0]),
+            'swin_v1_s': os.path.join(self.weights_root_dir, ['swin_small_patch4_window7_224_22kto1k_finetune.pth'][0]),
+            'pvt_v2_b0': os.path.join(self.weights_root_dir, ['pvt_v2_b0.pth'][0]),
+            'pvt_v2_b1': os.path.join(self.weights_root_dir, ['pvt_v2_b1.pth'][0]),
+        }
+
+        # Callbacks - inactive
+        self.verbose_eval = True
+        self.only_S_MAE = False
+        self.use_fp16 = False   # Bugs. It may cause nan in training.
+        self.SDPA_enabled = False    # Bugs. Slower and errors occur in multi-GPUs
+
+        # others
+        self.device = [0, 'cpu'][0]     # .to(0) == .to('cuda:0')
+
+        self.batch_size_valid = 1
+        self.rand_seed = 7
+        # run_sh_file = [f for f in os.listdir('.') if 'train.sh' == f] + [os.path.join('..', f) for f in os.listdir('..') if 'train.sh' == f]
+        # with open(run_sh_file[0], 'r') as f:
+        #     lines = f.readlines()
+        #     self.save_last = int([l.strip() for l in lines if '"{}")'.format(self.task) in l and 'val_last=' in l][0].split('val_last=')[-1].split()[0])
+        #     self.save_step = int([l.strip() for l in lines if '"{}")'.format(self.task) in l and 'step=' in l][0].split('step=')[-1].split()[0])
+        # self.val_step = [0, self.save_step][0]
+
+    def print_task(self) -> None:
+        # Return task for choosing settings in shell scripts.
+        print(self.task)
+
+
+
+### models/backbones/pvt_v2.py
+
+import torch
+import torch.nn as nn
+from functools import partial
+
+from timm.models.layers import DropPath, to_2tuple, trunc_normal_
+from timm.models.registry import register_model
+
+import math
+
+# from config import Config
+
+# config = Config()
+
+class Mlp(nn.Module):
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.dwconv = DWConv(hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+        elif isinstance(m, nn.Conv2d):
+            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+            fan_out //= m.groups
+            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
+            if m.bias is not None:
+                m.bias.data.zero_()
+
+    def forward(self, x, H, W):
+        x = self.fc1(x)
+        x = self.dwconv(x, H, W)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Attention(nn.Module):
+    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):
+        super().__init__()
+        assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}."
+
+        self.dim = dim
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5
+
+        self.q = nn.Linear(dim, dim, bias=qkv_bias)
+        self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
+        self.attn_drop_prob = attn_drop
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+        self.sr_ratio = sr_ratio
+        if sr_ratio > 1:
+            self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
+            self.norm = nn.LayerNorm(dim)
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+        elif isinstance(m, nn.Conv2d):
+            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+            fan_out //= m.groups
+            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
+            if m.bias is not None:
+                m.bias.data.zero_()
+
+    def forward(self, x, H, W):
+        B, N, C = x.shape
+        q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
+
+        if self.sr_ratio > 1:
+            x_ = x.permute(0, 2, 1).reshape(B, C, H, W)
+            x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)
+            x_ = self.norm(x_)
+            kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        else:
+            kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        k, v = kv[0], kv[1]
+
+        if config.SDPA_enabled:
+            x = torch.nn.functional.scaled_dot_product_attention(
+                q, k, v,
+                attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
+            ).transpose(1, 2).reshape(B, N, C)
+        else:
+            attn = (q @ k.transpose(-2, -1)) * self.scale
+            attn = attn.softmax(dim=-1)
+            attn = self.attn_drop(attn)
+
+            x = (attn @ v).transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+
+        return x
+
+
+class Block(nn.Module):
+
+    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
+                 drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):
+        super().__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(
+            dim,
+            num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
+            attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)
+        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+        elif isinstance(m, nn.Conv2d):
+            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+            fan_out //= m.groups
+            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
+            if m.bias is not None:
+                m.bias.data.zero_()
+
+    def forward(self, x, H, W):
+        x = x + self.drop_path(self.attn(self.norm1(x), H, W))
+        x = x + self.drop_path(self.mlp(self.norm2(x), H, W))
+
+        return x
+
+
+class OverlapPatchEmbed(nn.Module):
+    """ Image to Patch Embedding
+    """
+
+    def __init__(self, img_size=224, patch_size=7, stride=4, in_channels=3, embed_dim=768):
+        super().__init__()
+        img_size = to_2tuple(img_size)
+        patch_size = to_2tuple(patch_size)
+
+        self.img_size = img_size
+        self.patch_size = patch_size
+        self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]
+        self.num_patches = self.H * self.W
+        self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=stride,
+                              padding=(patch_size[0] // 2, patch_size[1] // 2))
+        self.norm = nn.LayerNorm(embed_dim)
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+        elif isinstance(m, nn.Conv2d):
+            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+            fan_out //= m.groups
+            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
+            if m.bias is not None:
+                m.bias.data.zero_()
+
+    def forward(self, x):
+        x = self.proj(x)
+        _, _, H, W = x.shape
+        x = x.flatten(2).transpose(1, 2)
+        x = self.norm(x)
+
+        return x, H, W
+
+
+class PyramidVisionTransformerImpr(nn.Module):
+    def __init__(self, img_size=224, patch_size=16, in_channels=3, num_classes=1000, embed_dims=[64, 128, 256, 512],
+                 num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0.,
+                 attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,
+                 depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1]):
+        super().__init__()
+        self.num_classes = num_classes
+        self.depths = depths
+
+        # patch_embed
+        self.patch_embed1 = OverlapPatchEmbed(img_size=img_size, patch_size=7, stride=4, in_channels=in_channels,
+                                              embed_dim=embed_dims[0])
+        self.patch_embed2 = OverlapPatchEmbed(img_size=img_size // 4, patch_size=3, stride=2, in_channels=embed_dims[0],
+                                              embed_dim=embed_dims[1])
+        self.patch_embed3 = OverlapPatchEmbed(img_size=img_size // 8, patch_size=3, stride=2, in_channels=embed_dims[1],
+                                              embed_dim=embed_dims[2])
+        self.patch_embed4 = OverlapPatchEmbed(img_size=img_size // 16, patch_size=3, stride=2, in_channels=embed_dims[2],
+                                              embed_dim=embed_dims[3])
+
+        # transformer encoder
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule
+        cur = 0
+        self.block1 = nn.ModuleList([Block(
+            dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=mlp_ratios[0], qkv_bias=qkv_bias, qk_scale=qk_scale,
+            drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
+            sr_ratio=sr_ratios[0])
+            for i in range(depths[0])])
+        self.norm1 = norm_layer(embed_dims[0])
+
+        cur += depths[0]
+        self.block2 = nn.ModuleList([Block(
+            dim=embed_dims[1], num_heads=num_heads[1], mlp_ratio=mlp_ratios[1], qkv_bias=qkv_bias, qk_scale=qk_scale,
+            drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
+            sr_ratio=sr_ratios[1])
+            for i in range(depths[1])])
+        self.norm2 = norm_layer(embed_dims[1])
+
+        cur += depths[1]
+        self.block3 = nn.ModuleList([Block(
+            dim=embed_dims[2], num_heads=num_heads[2], mlp_ratio=mlp_ratios[2], qkv_bias=qkv_bias, qk_scale=qk_scale,
+            drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
+            sr_ratio=sr_ratios[2])
+            for i in range(depths[2])])
+        self.norm3 = norm_layer(embed_dims[2])
+
+        cur += depths[2]
+        self.block4 = nn.ModuleList([Block(
+            dim=embed_dims[3], num_heads=num_heads[3], mlp_ratio=mlp_ratios[3], qkv_bias=qkv_bias, qk_scale=qk_scale,
+            drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,
+            sr_ratio=sr_ratios[3])
+            for i in range(depths[3])])
+        self.norm4 = norm_layer(embed_dims[3])
+
+        # classification head
+        # self.head = nn.Linear(embed_dims[3], num_classes) if num_classes > 0 else nn.Identity()
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+        elif isinstance(m, nn.Conv2d):
+            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
+            fan_out //= m.groups
+            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
+            if m.bias is not None:
+                m.bias.data.zero_()
+
+    def init_weights(self, pretrained=None):
+        if isinstance(pretrained, str):
+            logger = 1
+            #load_checkpoint(self, pretrained, map_location='cpu', strict=False, logger=logger)
+
+    def reset_drop_path(self, drop_path_rate):
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(self.depths))]
+        cur = 0
+        for i in range(self.depths[0]):
+            self.block1[i].drop_path.drop_prob = dpr[cur + i]
+
+        cur += self.depths[0]
+        for i in range(self.depths[1]):
+            self.block2[i].drop_path.drop_prob = dpr[cur + i]
+
+        cur += self.depths[1]
+        for i in range(self.depths[2]):
+            self.block3[i].drop_path.drop_prob = dpr[cur + i]
+
+        cur += self.depths[2]
+        for i in range(self.depths[3]):
+            self.block4[i].drop_path.drop_prob = dpr[cur + i]
+
+    def freeze_patch_emb(self):
+        self.patch_embed1.requires_grad = False
+
+    @torch.jit.ignore
+    def no_weight_decay(self):
+        return {'pos_embed1', 'pos_embed2', 'pos_embed3', 'pos_embed4', 'cls_token'}  # has pos_embed may be better
+
+    def get_classifier(self):
+        return self.head
+
+    def reset_classifier(self, num_classes, global_pool=''):
+        self.num_classes = num_classes
+        self.head = nn.Linear(self.embed_dim, num_classes) if num_classes > 0 else nn.Identity()
+
+    def forward_features(self, x):
+        B = x.shape[0]
+        outs = []
+
+        # stage 1
+        x, H, W = self.patch_embed1(x)
+        for i, blk in enumerate(self.block1):
+            x = blk(x, H, W)
+        x = self.norm1(x)
+        x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+        outs.append(x)
+
+        # stage 2
+        x, H, W = self.patch_embed2(x)
+        for i, blk in enumerate(self.block2):
+            x = blk(x, H, W)
+        x = self.norm2(x)
+        x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+        outs.append(x)
+
+        # stage 3
+        x, H, W = self.patch_embed3(x)
+        for i, blk in enumerate(self.block3):
+            x = blk(x, H, W)
+        x = self.norm3(x)
+        x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+        outs.append(x)
+
+        # stage 4
+        x, H, W = self.patch_embed4(x)
+        for i, blk in enumerate(self.block4):
+            x = blk(x, H, W)
+        x = self.norm4(x)
+        x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()
+        outs.append(x)
+
+        return outs
+
+        # return x.mean(dim=1)
+
+    def forward(self, x):
+        x = self.forward_features(x)
+        # x = self.head(x)
+
+        return x
+
+
+class DWConv(nn.Module):
+    def __init__(self, dim=768):
+        super(DWConv, self).__init__()
+        self.dwconv = nn.Conv2d(dim, dim, 3, 1, 1, bias=True, groups=dim)
+
+    def forward(self, x, H, W):
+        B, N, C = x.shape
+        x = x.transpose(1, 2).view(B, C, H, W).contiguous()
+        x = self.dwconv(x)
+        x = x.flatten(2).transpose(1, 2)
+
+        return x
+
+
+def _conv_filter(state_dict, patch_size=16):
+    """ convert patch embedding weight from manual patchify + linear proj to conv"""
+    out_dict = {}
+    for k, v in state_dict.items():
+        if 'patch_embed.proj.weight' in k:
+            v = v.reshape((v.shape[0], 3, patch_size, patch_size))
+        out_dict[k] = v
+
+    return out_dict
+
+
+## @register_model
+class pvt_v2_b0(PyramidVisionTransformerImpr):
+    def __init__(self, **kwargs):
+        super(pvt_v2_b0, self).__init__(
+            patch_size=4, embed_dims=[32, 64, 160, 256], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1)
+
+
+
+## @register_model
+class pvt_v2_b1(PyramidVisionTransformerImpr):
+    def __init__(self, **kwargs):
+        super(pvt_v2_b1, self).__init__(
+            patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[2, 2, 2, 2], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1)
+
+## @register_model
+class pvt_v2_b2(PyramidVisionTransformerImpr):
+    def __init__(self, in_channels=3, **kwargs):
+        super(pvt_v2_b2, self).__init__(
+            patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1, in_channels=in_channels)
+
+## @register_model
+class pvt_v2_b3(PyramidVisionTransformerImpr):
+    def __init__(self, **kwargs):
+        super(pvt_v2_b3, self).__init__(
+            patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 18, 3], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1)
+
+## @register_model
+class pvt_v2_b4(PyramidVisionTransformerImpr):
+    def __init__(self, **kwargs):
+        super(pvt_v2_b4, self).__init__(
+            patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 8, 27, 3], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1)
+
+
+## @register_model
+class pvt_v2_b5(PyramidVisionTransformerImpr):
+    def __init__(self, **kwargs):
+        super(pvt_v2_b5, self).__init__(
+            patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[4, 4, 4, 4],
+            qkv_bias=True, norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 6, 40, 3], sr_ratios=[8, 4, 2, 1],
+            drop_rate=0.0, drop_path_rate=0.1)
+
+
+
+### models/backbones/swin_v1.py
+
+# --------------------------------------------------------
+# Swin Transformer
+# Copyright (c) 2021 Microsoft
+# Licensed under The MIT License [see LICENSE for details]
+# Written by Ze Liu, Yutong Lin, Yixuan Wei
+# --------------------------------------------------------
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.checkpoint as checkpoint
+import numpy as np
+from timm.models.layers import DropPath, to_2tuple, trunc_normal_
+
+# from config import Config
+
+
+# config = Config()
+
+class Mlp(nn.Module):
+    """ Multilayer perceptron."""
+
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+def window_partition(x, window_size):
+    """
+    Args:
+        x: (B, H, W, C)
+        window_size (int): window size
+
+    Returns:
+        windows: (num_windows*B, window_size, window_size, C)
+    """
+    B, H, W, C = x.shape
+    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
+    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
+    return windows
+
+
+def window_reverse(windows, window_size, H, W):
+    """
+    Args:
+        windows: (num_windows*B, window_size, window_size, C)
+        window_size (int): Window size
+        H (int): Height of image
+        W (int): Width of image
+
+    Returns:
+        x: (B, H, W, C)
+    """
+    B = int(windows.shape[0] / (H * W / window_size / window_size))
+    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
+    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
+    return x
+
+
+class WindowAttention(nn.Module):
+    """ Window based multi-head self attention (W-MSA) module with relative position bias.
+    It supports both of shifted and non-shifted window.
+
+    Args:
+        dim (int): Number of input channels.
+        window_size (tuple[int]): The height and width of the window.
+        num_heads (int): Number of attention heads.
+        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
+        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
+        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
+        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
+    """
+
+    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
+
+        super().__init__()
+        self.dim = dim
+        self.window_size = window_size  # Wh, Ww
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5
+
+        # define a parameter table of relative position bias
+        self.relative_position_bias_table = nn.Parameter(
+            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH
+
+        # get pair-wise relative position index for each token inside the window
+        coords_h = torch.arange(self.window_size[0])
+        coords_w = torch.arange(self.window_size[1])
+        coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing='ij'))  # 2, Wh, Ww
+        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
+        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
+        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
+        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
+        relative_coords[:, :, 1] += self.window_size[1] - 1
+        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
+        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
+        self.register_buffer("relative_position_index", relative_position_index)
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop_prob = attn_drop
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+        trunc_normal_(self.relative_position_bias_table, std=.02)
+        self.softmax = nn.Softmax(dim=-1)
+
+    def forward(self, x, mask=None):
+        """ Forward function.
+
+        Args:
+            x: input features with shape of (num_windows*B, N, C)
+            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
+        """
+        B_, N, C = x.shape
+        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
+
+        q = q * self.scale
+
+        if config.SDPA_enabled:
+            x = torch.nn.functional.scaled_dot_product_attention(
+                q, k, v,
+                attn_mask=None, dropout_p=self.attn_drop_prob, is_causal=False
+            ).transpose(1, 2).reshape(B_, N, C)
+        else:
+            attn = (q @ k.transpose(-2, -1))
+
+            relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
+                self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
+            relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
+            attn = attn + relative_position_bias.unsqueeze(0)
+
+            if mask is not None:
+                nW = mask.shape[0]
+                attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
+                attn = attn.view(-1, self.num_heads, N, N)
+                attn = self.softmax(attn)
+            else:
+                attn = self.softmax(attn)
+
+            attn = self.attn_drop(attn)
+
+            x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+
+class SwinTransformerBlock(nn.Module):
+    """ Swin Transformer Block.
+
+    Args:
+        dim (int): Number of input channels.
+        num_heads (int): Number of attention heads.
+        window_size (int): Window size.
+        shift_size (int): Shift size for SW-MSA.
+        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
+        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
+        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
+        drop (float, optional): Dropout rate. Default: 0.0
+        attn_drop (float, optional): Attention dropout rate. Default: 0.0
+        drop_path (float, optional): Stochastic depth rate. Default: 0.0
+        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
+        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
+    """
+
+    def __init__(self, dim, num_heads, window_size=7, shift_size=0,
+                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
+                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
+        super().__init__()
+        self.dim = dim
+        self.num_heads = num_heads
+        self.window_size = window_size
+        self.shift_size = shift_size
+        self.mlp_ratio = mlp_ratio
+        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
+
+        self.norm1 = norm_layer(dim)
+        self.attn = WindowAttention(
+            dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
+            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
+
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+        self.H = None
+        self.W = None
+
+    def forward(self, x, mask_matrix):
+        """ Forward function.
+
+        Args:
+            x: Input feature, tensor size (B, H*W, C).
+            H, W: Spatial resolution of the input feature.
+            mask_matrix: Attention mask for cyclic shift.
+        """
+        B, L, C = x.shape
+        H, W = self.H, self.W
+        assert L == H * W, "input feature has wrong size"
+
+        shortcut = x
+        x = self.norm1(x)
+        x = x.view(B, H, W, C)
+
+        # pad feature maps to multiples of window size
+        pad_l = pad_t = 0
+        pad_r = (self.window_size - W % self.window_size) % self.window_size
+        pad_b = (self.window_size - H % self.window_size) % self.window_size
+        x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
+        _, Hp, Wp, _ = x.shape
+
+        # cyclic shift
+        if self.shift_size > 0:
+            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
+            attn_mask = mask_matrix
+        else:
+            shifted_x = x
+            attn_mask = None
+
+        # partition windows
+        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
+        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C
+
+        # W-MSA/SW-MSA
+        attn_windows = self.attn(x_windows, mask=attn_mask)  # nW*B, window_size*window_size, C
+
+        # merge windows
+        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
+        shifted_x = window_reverse(attn_windows, self.window_size, Hp, Wp)  # B H' W' C
+
+        # reverse cyclic shift
+        if self.shift_size > 0:
+            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
+        else:
+            x = shifted_x
+
+        if pad_r > 0 or pad_b > 0:
+            x = x[:, :H, :W, :].contiguous()
+
+        x = x.view(B, H * W, C)
+
+        # FFN
+        x = shortcut + self.drop_path(x)
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+
+        return x
+
+
+class PatchMerging(nn.Module):
+    """ Patch Merging Layer
+
+    Args:
+        dim (int): Number of input channels.
+        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
+    """
+    def __init__(self, dim, norm_layer=nn.LayerNorm):
+        super().__init__()
+        self.dim = dim
+        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
+        self.norm = norm_layer(4 * dim)
+
+    def forward(self, x, H, W):
+        """ Forward function.
+
+        Args:
+            x: Input feature, tensor size (B, H*W, C).
+            H, W: Spatial resolution of the input feature.
+        """
+        B, L, C = x.shape
+        assert L == H * W, "input feature has wrong size"
+
+        x = x.view(B, H, W, C)
+
+        # padding
+        pad_input = (H % 2 == 1) or (W % 2 == 1)
+        if pad_input:
+            x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))
+
+        x0 = x[:, 0::2, 0::2, :]  # B H/2 W/2 C
+        x1 = x[:, 1::2, 0::2, :]  # B H/2 W/2 C
+        x2 = x[:, 0::2, 1::2, :]  # B H/2 W/2 C
+        x3 = x[:, 1::2, 1::2, :]  # B H/2 W/2 C
+        x = torch.cat([x0, x1, x2, x3], -1)  # B H/2 W/2 4*C
+        x = x.view(B, -1, 4 * C)  # B H/2*W/2 4*C
+
+        x = self.norm(x)
+        x = self.reduction(x)
+
+        return x
+
+
+class BasicLayer(nn.Module):
+    """ A basic Swin Transformer layer for one stage.
+
+    Args:
+        dim (int): Number of feature channels
+        depth (int): Depths of this stage.
+        num_heads (int): Number of attention head.
+        window_size (int): Local window size. Default: 7.
+        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
+        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
+        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
+        drop (float, optional): Dropout rate. Default: 0.0
+        attn_drop (float, optional): Attention dropout rate. Default: 0.0
+        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
+        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
+        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
+        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
+    """
+
+    def __init__(self,
+                 dim,
+                 depth,
+                 num_heads,
+                 window_size=7,
+                 mlp_ratio=4.,
+                 qkv_bias=True,
+                 qk_scale=None,
+                 drop=0.,
+                 attn_drop=0.,
+                 drop_path=0.,
+                 norm_layer=nn.LayerNorm,
+                 downsample=None,
+                 use_checkpoint=False):
+        super().__init__()
+        self.window_size = window_size
+        self.shift_size = window_size // 2
+        self.depth = depth
+        self.use_checkpoint = use_checkpoint
+
+        # build blocks
+        self.blocks = nn.ModuleList([
+            SwinTransformerBlock(
+                dim=dim,
+                num_heads=num_heads,
+                window_size=window_size,
+                shift_size=0 if (i % 2 == 0) else window_size // 2,
+                mlp_ratio=mlp_ratio,
+                qkv_bias=qkv_bias,
+                qk_scale=qk_scale,
+                drop=drop,
+                attn_drop=attn_drop,
+                drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
+                norm_layer=norm_layer)
+            for i in range(depth)])
+
+        # patch merging layer
+        if downsample is not None:
+            self.downsample = downsample(dim=dim, norm_layer=norm_layer)
+        else:
+            self.downsample = None
+
+    def forward(self, x, H, W):
+        """ Forward function.
+
+        Args:
+            x: Input feature, tensor size (B, H*W, C).
+            H, W: Spatial resolution of the input feature.
+        """
+
+        # calculate attention mask for SW-MSA
+        Hp = int(np.ceil(H / self.window_size)) * self.window_size
+        Wp = int(np.ceil(W / self.window_size)) * self.window_size
+        img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device)  # 1 Hp Wp 1
+        h_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        w_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        cnt = 0
+        for h in h_slices:
+            for w in w_slices:
+                img_mask[:, h, w, :] = cnt
+                cnt += 1
+
+        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
+        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
+        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
+        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
+
+        for blk in self.blocks:
+            blk.H, blk.W = H, W
+            if self.use_checkpoint:
+                x = checkpoint.checkpoint(blk, x, attn_mask)
+            else:
+                x = blk(x, attn_mask)
+        if self.downsample is not None:
+            x_down = self.downsample(x, H, W)
+            Wh, Ww = (H + 1) // 2, (W + 1) // 2
+            return x, H, W, x_down, Wh, Ww
+        else:
+            return x, H, W, x, H, W
+
+
+class PatchEmbed(nn.Module):
+    """ Image to Patch Embedding
+
+    Args:
+        patch_size (int): Patch token size. Default: 4.
+        in_channels (int): Number of input image channels. Default: 3.
+        embed_dim (int): Number of linear projection output channels. Default: 96.
+        norm_layer (nn.Module, optional): Normalization layer. Default: None
+    """
+
+    def __init__(self, patch_size=4, in_channels=3, embed_dim=96, norm_layer=None):
+        super().__init__()
+        patch_size = to_2tuple(patch_size)
+        self.patch_size = patch_size
+
+        self.in_channels = in_channels
+        self.embed_dim = embed_dim
+
+        self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=patch_size)
+        if norm_layer is not None:
+            self.norm = norm_layer(embed_dim)
+        else:
+            self.norm = None
+
+    def forward(self, x):
+        """Forward function."""
+        # padding
+        _, _, H, W = x.size()
+        if W % self.patch_size[1] != 0:
+            x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
+        if H % self.patch_size[0] != 0:
+            x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))
+
+        x = self.proj(x)  # B C Wh Ww
+        if self.norm is not None:
+            Wh, Ww = x.size(2), x.size(3)
+            x = x.flatten(2).transpose(1, 2)
+            x = self.norm(x)
+            x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)
+
+        return x
+
+
+class SwinTransformer(nn.Module):
+    """ Swin Transformer backbone.
+        A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows`  -
+          https://arxiv.org/pdf/2103.14030
+
+    Args:
+        pretrain_img_size (int): Input image size for training the pretrained model,
+            used in absolute postion embedding. Default 224.
+        patch_size (int | tuple(int)): Patch size. Default: 4.
+        in_channels (int): Number of input image channels. Default: 3.
+        embed_dim (int): Number of linear projection output channels. Default: 96.
+        depths (tuple[int]): Depths of each Swin Transformer stage.
+        num_heads (tuple[int]): Number of attention head of each stage.
+        window_size (int): Window size. Default: 7.
+        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
+        qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
+        qk_scale (float): Override default qk scale of head_dim ** -0.5 if set.
+        drop_rate (float): Dropout rate.
+        attn_drop_rate (float): Attention dropout rate. Default: 0.
+        drop_path_rate (float): Stochastic depth rate. Default: 0.2.
+        norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
+        ape (bool): If True, add absolute position embedding to the patch embedding. Default: False.
+        patch_norm (bool): If True, add normalization after patch embedding. Default: True.
+        out_indices (Sequence[int]): Output from which stages.
+        frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
+            -1 means not freezing any parameters.
+        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
+    """
+
+    def __init__(self,
+                 pretrain_img_size=224,
+                 patch_size=4,
+                 in_channels=3,
+                 embed_dim=96,
+                 depths=[2, 2, 6, 2],
+                 num_heads=[3, 6, 12, 24],
+                 window_size=7,
+                 mlp_ratio=4.,
+                 qkv_bias=True,
+                 qk_scale=None,
+                 drop_rate=0.,
+                 attn_drop_rate=0.,
+                 drop_path_rate=0.2,
+                 norm_layer=nn.LayerNorm,
+                 ape=False,
+                 patch_norm=True,
+                 out_indices=(0, 1, 2, 3),
+                 frozen_stages=-1,
+                 use_checkpoint=False):
+        super().__init__()
+
+        self.pretrain_img_size = pretrain_img_size
+        self.num_layers = len(depths)
+        self.embed_dim = embed_dim
+        self.ape = ape
+        self.patch_norm = patch_norm
+        self.out_indices = out_indices
+        self.frozen_stages = frozen_stages
+
+        # split image into non-overlapping patches
+        self.patch_embed = PatchEmbed(
+            patch_size=patch_size, in_channels=in_channels, embed_dim=embed_dim,
+            norm_layer=norm_layer if self.patch_norm else None)
+
+        # absolute position embedding
+        if self.ape:
+            pretrain_img_size = to_2tuple(pretrain_img_size)
+            patch_size = to_2tuple(patch_size)
+            patches_resolution = [pretrain_img_size[0] // patch_size[0], pretrain_img_size[1] // patch_size[1]]
+
+            self.absolute_pos_embed = nn.Parameter(torch.zeros(1, embed_dim, patches_resolution[0], patches_resolution[1]))
+            trunc_normal_(self.absolute_pos_embed, std=.02)
+
+        self.pos_drop = nn.Dropout(p=drop_rate)
+
+        # stochastic depth
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule
+
+        # build layers
+        self.layers = nn.ModuleList()
+        for i_layer in range(self.num_layers):
+            layer = BasicLayer(
+                dim=int(embed_dim * 2 ** i_layer),
+                depth=depths[i_layer],
+                num_heads=num_heads[i_layer],
+                window_size=window_size,
+                mlp_ratio=mlp_ratio,
+                qkv_bias=qkv_bias,
+                qk_scale=qk_scale,
+                drop=drop_rate,
+                attn_drop=attn_drop_rate,
+                drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
+                norm_layer=norm_layer,
+                downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
+                use_checkpoint=use_checkpoint)
+            self.layers.append(layer)
+
+        num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
+        self.num_features = num_features
+
+        # add a norm layer for each output
+        for i_layer in out_indices:
+            layer = norm_layer(num_features[i_layer])
+            layer_name = f'norm{i_layer}'
+            self.add_module(layer_name, layer)
+
+        self._freeze_stages()
+
+    def _freeze_stages(self):
+        if self.frozen_stages >= 0:
+            self.patch_embed.eval()
+            for param in self.patch_embed.parameters():
+                param.requires_grad = False
+
+        if self.frozen_stages >= 1 and self.ape:
+            self.absolute_pos_embed.requires_grad = False
+
+        if self.frozen_stages >= 2:
+            self.pos_drop.eval()
+            for i in range(0, self.frozen_stages - 1):
+                m = self.layers[i]
+                m.eval()
+                for param in m.parameters():
+                    param.requires_grad = False
+
+
+    def forward(self, x):
+        """Forward function."""
+        x = self.patch_embed(x)
+
+        Wh, Ww = x.size(2), x.size(3)
+        if self.ape:
+            # interpolate the position embedding to the corresponding size
+            absolute_pos_embed = F.interpolate(self.absolute_pos_embed, size=(Wh, Ww), mode='bicubic')
+            x = (x + absolute_pos_embed) # B Wh*Ww C
+            
+        outs = []#x.contiguous()]
+        x = x.flatten(2).transpose(1, 2)
+        x = self.pos_drop(x)
+        for i in range(self.num_layers):
+            layer = self.layers[i]
+            x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)
+
+            if i in self.out_indices:
+                norm_layer = getattr(self, f'norm{i}')
+                x_out = norm_layer(x_out)
+
+                out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
+                outs.append(out)
+
+        return tuple(outs)
+
+    def train(self, mode=True):
+        """Convert the model into training mode while keep layers freezed."""
+        super(SwinTransformer, self).train(mode)
+        self._freeze_stages()
+
+def swin_v1_t():
+    model = SwinTransformer(embed_dim=96, depths=[2, 2, 6, 2], num_heads=[3, 6, 12, 24], window_size=7)
+    return model
+
+def swin_v1_s():
+    model = SwinTransformer(embed_dim=96, depths=[2, 2, 18, 2], num_heads=[3, 6, 12, 24], window_size=7)
+    return model
+
+def swin_v1_b():
+    model = SwinTransformer(embed_dim=128, depths=[2, 2, 18, 2], num_heads=[4, 8, 16, 32], window_size=12)
+    return model
+
+def swin_v1_l():
+    model = SwinTransformer(embed_dim=192, depths=[2, 2, 18, 2], num_heads=[6, 12, 24, 48], window_size=12)
+    return model
+
+
+
+### models/modules/deform_conv.py
+
+import torch
+import torch.nn as nn
+from torchvision.ops import deform_conv2d
+
+
+class DeformableConv2d(nn.Module):
+    def __init__(self,
+                 in_channels,
+                 out_channels,
+                 kernel_size=3,
+                 stride=1,
+                 padding=1,
+                 bias=False):
+
+        super(DeformableConv2d, self).__init__()
+        
+        assert type(kernel_size) == tuple or type(kernel_size) == int
+
+        kernel_size = kernel_size if type(kernel_size) == tuple else (kernel_size, kernel_size)
+        self.stride = stride if type(stride) == tuple else (stride, stride)
+        self.padding = padding
+        
+        self.offset_conv = nn.Conv2d(in_channels,
+                                     2 * kernel_size[0] * kernel_size[1],
+                                     kernel_size=kernel_size,
+                                     stride=stride,
+                                     padding=self.padding,
+                                     bias=True)
+
+        nn.init.constant_(self.offset_conv.weight, 0.)
+        nn.init.constant_(self.offset_conv.bias, 0.)
+        
+        self.modulator_conv = nn.Conv2d(in_channels,
+                                     1 * kernel_size[0] * kernel_size[1],
+                                     kernel_size=kernel_size,
+                                     stride=stride,
+                                     padding=self.padding,
+                                     bias=True)
+
+        nn.init.constant_(self.modulator_conv.weight, 0.)
+        nn.init.constant_(self.modulator_conv.bias, 0.)
+
+        self.regular_conv = nn.Conv2d(in_channels,
+                                      out_channels=out_channels,
+                                      kernel_size=kernel_size,
+                                      stride=stride,
+                                      padding=self.padding,
+                                      bias=bias)
+
+    def forward(self, x):
+        #h, w = x.shape[2:]
+        #max_offset = max(h, w)/4.
+
+        offset = self.offset_conv(x)#.clamp(-max_offset, max_offset)
+        modulator = 2. * torch.sigmoid(self.modulator_conv(x))
+        
+        x = deform_conv2d(
+            input=x,
+            offset=offset,
+            weight=self.regular_conv.weight,
+            bias=self.regular_conv.bias,
+            padding=self.padding,
+            mask=modulator,
+            stride=self.stride,
+        )
+        return x
+
+
+
+
+### utils.py
+
+import torch.nn as nn
+
+
+def build_act_layer(act_layer):
+    if act_layer == 'ReLU':
+        return nn.ReLU(inplace=True)
+    elif act_layer == 'SiLU':
+        return nn.SiLU(inplace=True)
+    elif act_layer == 'GELU':
+        return nn.GELU()
+
+    raise NotImplementedError(f'build_act_layer does not support {act_layer}')
+
+
+def build_norm_layer(dim,
+                     norm_layer,
+                     in_format='channels_last',
+                     out_format='channels_last',
+                     eps=1e-6):
+    layers = []
+    if norm_layer == 'BN':
+        if in_format == 'channels_last':
+            layers.append(to_channels_first())
+        layers.append(nn.BatchNorm2d(dim))
+        if out_format == 'channels_last':
+            layers.append(to_channels_last())
+    elif norm_layer == 'LN':
+        if in_format == 'channels_first':
+            layers.append(to_channels_last())
+        layers.append(nn.LayerNorm(dim, eps=eps))
+        if out_format == 'channels_first':
+            layers.append(to_channels_first())
+    else:
+        raise NotImplementedError(
+            f'build_norm_layer does not support {norm_layer}')
+    return nn.Sequential(*layers)
+
+
+class to_channels_first(nn.Module):
+
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x):
+        return x.permute(0, 3, 1, 2)
+
+
+class to_channels_last(nn.Module):
+
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x):
+        return x.permute(0, 2, 3, 1)
+
+
+
+### dataset.py
+
+_class_labels_TR_sorted = (
+    'Airplane, Ant, Antenna, Archery, Axe, BabyCarriage, Bag, BalanceBeam, Balcony, Balloon, Basket, BasketballHoop, Beatle, Bed, Bee, Bench, Bicycle, '
+    'BicycleFrame, BicycleStand, Boat, Bonsai, BoomLift, Bridge, BunkBed, Butterfly, Button, Cable, CableLift, Cage, Camcorder, Cannon, Canoe, Car, '
+    'CarParkDropArm, Carriage, Cart, Caterpillar, CeilingLamp, Centipede, Chair, Clip, Clock, Clothes, CoatHanger, Comb, ConcretePumpTruck, Crack, Crane, '
+    'Cup, DentalChair, Desk, DeskChair, Diagram, DishRack, DoorHandle, Dragonfish, Dragonfly, Drum, Earphone, Easel, ElectricIron, Excavator, Eyeglasses, '
+    'Fan, Fence, Fencing, FerrisWheel, FireExtinguisher, Fishing, Flag, FloorLamp, Forklift, GasStation, Gate, Gear, Goal, Golf, GymEquipment, Hammock, '
+    'Handcart, Handcraft, Handrail, HangGlider, Harp, Harvester, Headset, Helicopter, Helmet, Hook, HorizontalBar, Hydrovalve, IroningTable, Jewelry, Key, '
+    'KidsPlayground, Kitchenware, Kite, Knife, Ladder, LaundryRack, Lightning, Lobster, Locust, Machine, MachineGun, MagazineRack, Mantis, Medal, MemorialArchway, '
+    'Microphone, Missile, MobileHolder, Monitor, Mosquito, Motorcycle, MovingTrolley, Mower, MusicPlayer, MusicStand, ObservationTower, Octopus, OilWell, '
+    'OlympicLogo, OperatingTable, OutdoorFitnessEquipment, Parachute, Pavilion, Piano, Pipe, PlowHarrow, PoleVault, Punchbag, Rack, Racket, Rifle, Ring, Robot, '
+    'RockClimbing, Rope, Sailboat, Satellite, Scaffold, Scale, Scissor, Scooter, Sculpture, Seadragon, Seahorse, Seal, SewingMachine, Ship, Shoe, ShoppingCart, '
+    'ShoppingTrolley, Shower, Shrimp, Signboard, Skateboarding, Skeleton, Skiing, Spade, SpeedBoat, Spider, Spoon, Stair, Stand, Stationary, SteeringWheel, '
+    'Stethoscope, Stool, Stove, StreetLamp, SweetStand, Swing, Sword, TV, Table, TableChair, TableLamp, TableTennis, Tank, Tapeline, Teapot, Telescope, Tent, '
+    'TobaccoPipe, Toy, Tractor, TrafficLight, TrafficSign, Trampoline, TransmissionTower, Tree, Tricycle, TrimmerCover, Tripod, Trombone, Truck, Trumpet, Tuba, '
+    'UAV, Umbrella, UnevenBars, UtilityPole, VacuumCleaner, Violin, Wakesurfing, Watch, WaterTower, WateringPot, Well, WellLid, Wheel, Wheelchair, WindTurbine, Windmill, WineGlass, WireWhisk, Yacht'
+)
+class_labels_TR_sorted = _class_labels_TR_sorted.split(', ')
+
+
+### models/backbones/build_backbones.py
+
+import torch
+import torch.nn as nn
+from collections import OrderedDict
+from torchvision.models import vgg16, vgg16_bn, VGG16_Weights, VGG16_BN_Weights, resnet50, ResNet50_Weights
+# from models.pvt_v2 import pvt_v2_b0, pvt_v2_b1, pvt_v2_b2, pvt_v2_b5
+# from models.swin_v1 import swin_v1_t, swin_v1_s, swin_v1_b, swin_v1_l
+# from config import Config
+
+
+config = Config()
+
+def build_backbone(bb_name, pretrained=True, params_settings=''):
+    if bb_name == 'vgg16':
+        bb_net = list(vgg16(pretrained=VGG16_Weights.DEFAULT if pretrained else None).children())[0]
+        bb = nn.Sequential(OrderedDict({'conv1': bb_net[:4], 'conv2': bb_net[4:9], 'conv3': bb_net[9:16], 'conv4': bb_net[16:23]}))
+    elif bb_name == 'vgg16bn':
+        bb_net = list(vgg16_bn(pretrained=VGG16_BN_Weights.DEFAULT if pretrained else None).children())[0]
+        bb = nn.Sequential(OrderedDict({'conv1': bb_net[:6], 'conv2': bb_net[6:13], 'conv3': bb_net[13:23], 'conv4': bb_net[23:33]}))
+    elif bb_name == 'resnet50':
+        bb_net = list(resnet50(pretrained=ResNet50_Weights.DEFAULT if pretrained else None).children())
+        bb = nn.Sequential(OrderedDict({'conv1': nn.Sequential(*bb_net[0:3]), 'conv2': bb_net[4], 'conv3': bb_net[5], 'conv4': bb_net[6]}))
+    else:
+        bb = eval('{}({})'.format(bb_name, params_settings))
+        if pretrained:
+            bb = load_weights(bb, bb_name)
+    return bb
+
+def load_weights(model, model_name):
+    save_model = torch.load(config.weights[model_name], map_location='cpu')
+    model_dict = model.state_dict()
+    state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model.items() if k in model_dict.keys()}
+    # to ignore the weights with mismatched size when I modify the backbone itself.
+    if not state_dict:
+        save_model_keys = list(save_model.keys())
+        sub_item = save_model_keys[0] if len(save_model_keys) == 1 else None
+        state_dict = {k: v if v.size() == model_dict[k].size() else model_dict[k] for k, v in save_model[sub_item].items() if k in model_dict.keys()}
+        if not state_dict or not sub_item:
+            print('Weights are not successully loaded. Check the state dict of weights file.')
+            return None
+        else:
+            print('Found correct weights in the "{}" item of loaded state_dict.'.format(sub_item))
+    model_dict.update(state_dict)
+    model.load_state_dict(model_dict)
+    return model
+
+
+
+### models/modules/decoder_blocks.py
+
+import torch
+import torch.nn as nn
+# from models.aspp import ASPP, ASPPDeformable
+# from config import Config
+
+
+# config = Config()
+
+
+class BasicDecBlk(nn.Module):
+    def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
+        super(BasicDecBlk, self).__init__()
+        inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
+        self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
+        self.relu_in = nn.ReLU(inplace=True)
+        if config.dec_att == 'ASPP':
+            self.dec_att = ASPP(in_channels=inter_channels)
+        elif config.dec_att == 'ASPPDeformable':
+            self.dec_att = ASPPDeformable(in_channels=inter_channels)
+        self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
+        self.bn_in = nn.BatchNorm2d(inter_channels) if config.batch_size > 1 else nn.Identity()
+        self.bn_out = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
+
+    def forward(self, x):
+        x = self.conv_in(x)
+        x = self.bn_in(x)
+        x = self.relu_in(x)
+        if hasattr(self, 'dec_att'):
+            x = self.dec_att(x)
+        x = self.conv_out(x)
+        x = self.bn_out(x)
+        return x
+
+
+class ResBlk(nn.Module):
+    def __init__(self, in_channels=64, out_channels=None, inter_channels=64):
+        super(ResBlk, self).__init__()
+        if out_channels is None:
+            out_channels = in_channels
+        inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
+
+        self.conv_in = nn.Conv2d(in_channels, inter_channels, 3, 1, padding=1)
+        self.bn_in = nn.BatchNorm2d(inter_channels) if config.batch_size > 1 else nn.Identity()
+        self.relu_in = nn.ReLU(inplace=True)
+
+        if config.dec_att == 'ASPP':
+            self.dec_att = ASPP(in_channels=inter_channels)
+        elif config.dec_att == 'ASPPDeformable':
+            self.dec_att = ASPPDeformable(in_channels=inter_channels)
+
+        self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, padding=1)
+        self.bn_out = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
+        
+        self.conv_resi = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
+
+    def forward(self, x):
+        _x = self.conv_resi(x)
+        x = self.conv_in(x)
+        x = self.bn_in(x)
+        x = self.relu_in(x)
+        if hasattr(self, 'dec_att'):
+            x = self.dec_att(x)
+        x = self.conv_out(x)
+        x = self.bn_out(x)
+        return x + _x
+
+
+
+### models/modules/lateral_blocks.py
+
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from functools import partial
+
+# from config import Config
+
+
+# config = Config()
+
+
+class BasicLatBlk(nn.Module):
+    def __init__(self, in_channels=64, out_channels=64, inter_channels=64):
+        super(BasicLatBlk, self).__init__()
+        inter_channels = in_channels // 4 if config.dec_channels_inter == 'adap' else 64
+        self.conv = nn.Conv2d(in_channels, out_channels, 1, 1, 0)
+
+    def forward(self, x):
+        x = self.conv(x)
+        return x
+
+
+
+### models/modules/aspp.py
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+# from models.deform_conv import DeformableConv2d
+# from config import Config
+
+
+# config = Config()
+
+
+class _ASPPModule(nn.Module):
+    def __init__(self, in_channels, planes, kernel_size, padding, dilation):
+        super(_ASPPModule, self).__init__()
+        self.atrous_conv = nn.Conv2d(in_channels, planes, kernel_size=kernel_size,
+                                            stride=1, padding=padding, dilation=dilation, bias=False)
+        self.bn = nn.BatchNorm2d(planes) if config.batch_size > 1 else nn.Identity()
+        self.relu = nn.ReLU(inplace=True)
+
+    def forward(self, x):
+        x = self.atrous_conv(x)
+        x = self.bn(x)
+
+        return self.relu(x)
+
+
+class ASPP(nn.Module):
+    def __init__(self, in_channels=64, out_channels=None, output_stride=16):
+        super(ASPP, self).__init__()
+        self.down_scale = 1
+        if out_channels is None:
+            out_channels = in_channels
+        self.in_channelster = 256 // self.down_scale
+        if output_stride == 16:
+            dilations = [1, 6, 12, 18]
+        elif output_stride == 8:
+            dilations = [1, 12, 24, 36]
+        else:
+            raise NotImplementedError
+
+        self.aspp1 = _ASPPModule(in_channels, self.in_channelster, 1, padding=0, dilation=dilations[0])
+        self.aspp2 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[1], dilation=dilations[1])
+        self.aspp3 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[2], dilation=dilations[2])
+        self.aspp4 = _ASPPModule(in_channels, self.in_channelster, 3, padding=dilations[3], dilation=dilations[3])
+
+        self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
+                                             nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
+                                             nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
+                                             nn.ReLU(inplace=True))
+        self.conv1 = nn.Conv2d(self.in_channelster * 5, out_channels, 1, bias=False)
+        self.bn1 = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
+        self.relu = nn.ReLU(inplace=True)
+        self.dropout = nn.Dropout(0.5)
+
+    def forward(self, x):
+        x1 = self.aspp1(x)
+        x2 = self.aspp2(x)
+        x3 = self.aspp3(x)
+        x4 = self.aspp4(x)
+        x5 = self.global_avg_pool(x)
+        x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
+        x = torch.cat((x1, x2, x3, x4, x5), dim=1)
+
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+
+        return self.dropout(x)
+
+
+##################### Deformable
+class _ASPPModuleDeformable(nn.Module):
+    def __init__(self, in_channels, planes, kernel_size, padding):
+        super(_ASPPModuleDeformable, self).__init__()
+        self.atrous_conv = DeformableConv2d(in_channels, planes, kernel_size=kernel_size,
+                                            stride=1, padding=padding, bias=False)
+        self.bn = nn.BatchNorm2d(planes) if config.batch_size > 1 else nn.Identity()
+        self.relu = nn.ReLU(inplace=True)
+
+    def forward(self, x):
+        x = self.atrous_conv(x)
+        x = self.bn(x)
+
+        return self.relu(x)
+
+
+class ASPPDeformable(nn.Module):
+    def __init__(self, in_channels, out_channels=None, parallel_block_sizes=[1, 3, 7]):
+        super(ASPPDeformable, self).__init__()
+        self.down_scale = 1
+        if out_channels is None:
+            out_channels = in_channels
+        self.in_channelster = 256 // self.down_scale
+
+        self.aspp1 = _ASPPModuleDeformable(in_channels, self.in_channelster, 1, padding=0)
+        self.aspp_deforms = nn.ModuleList([
+            _ASPPModuleDeformable(in_channels, self.in_channelster, conv_size, padding=int(conv_size//2)) for conv_size in parallel_block_sizes
+        ])
+
+        self.global_avg_pool = nn.Sequential(nn.AdaptiveAvgPool2d((1, 1)),
+                                             nn.Conv2d(in_channels, self.in_channelster, 1, stride=1, bias=False),
+                                             nn.BatchNorm2d(self.in_channelster) if config.batch_size > 1 else nn.Identity(),
+                                             nn.ReLU(inplace=True))
+        self.conv1 = nn.Conv2d(self.in_channelster * (2 + len(self.aspp_deforms)), out_channels, 1, bias=False)
+        self.bn1 = nn.BatchNorm2d(out_channels) if config.batch_size > 1 else nn.Identity()
+        self.relu = nn.ReLU(inplace=True)
+        self.dropout = nn.Dropout(0.5)
+
+    def forward(self, x):
+        x1 = self.aspp1(x)
+        x_aspp_deforms = [aspp_deform(x) for aspp_deform in self.aspp_deforms]
+        x5 = self.global_avg_pool(x)
+        x5 = F.interpolate(x5, size=x1.size()[2:], mode='bilinear', align_corners=True)
+        x = torch.cat((x1, *x_aspp_deforms, x5), dim=1)
+
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+
+        return self.dropout(x)
+
+
+
+### models/refinement/refiner.py
+
+import torch
+import torch.nn as nn
+from collections import OrderedDict
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torchvision.models import vgg16, vgg16_bn
+from torchvision.models import resnet50
+
+# from config import Config
+# from dataset import class_labels_TR_sorted
+# from models.build_backbone import build_backbone
+# from models.decoder_blocks import BasicDecBlk
+# from models.lateral_blocks import BasicLatBlk
+# from models.ing import *
+# from models.stem_layer import StemLayer
+
+
+class RefinerPVTInChannels4(nn.Module):
+    def __init__(self, in_channels=3+1):
+        super(RefinerPVTInChannels4, self).__init__()
+        self.config = Config()
+        self.epoch = 1
+        self.bb = build_backbone(self.config.bb, params_settings='in_channels=4')
+
+        lateral_channels_in_collection = {
+            'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
+            'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
+            'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
+        }
+        channels = lateral_channels_in_collection[self.config.bb]
+        self.squeeze_module = BasicDecBlk(channels[0], channels[0])
+
+        self.decoder = Decoder(channels)
+
+        if 0:
+            for key, value in self.named_parameters():
+                if 'bb.' in key:
+                    value.requires_grad = False
+
+    def forward(self, x):
+        if isinstance(x, list):
+            x = torch.cat(x, dim=1)
+        ########## Encoder ##########
+        if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
+            x1 = self.bb.conv1(x)
+            x2 = self.bb.conv2(x1)
+            x3 = self.bb.conv3(x2)
+            x4 = self.bb.conv4(x3)
+        else:
+            x1, x2, x3, x4 = self.bb(x)
+
+        x4 = self.squeeze_module(x4)
+
+        ########## Decoder ##########
+
+        features = [x, x1, x2, x3, x4]
+        scaled_preds = self.decoder(features)
+
+        return scaled_preds
+
+
+class Refiner(nn.Module):
+    def __init__(self, in_channels=3+1):
+        super(Refiner, self).__init__()
+        self.config = Config()
+        self.epoch = 1
+        self.stem_layer = StemLayer(in_channels=in_channels, inter_channels=48, out_channels=3, norm_layer='BN' if self.config.batch_size > 1 else 'LN')
+        self.bb = build_backbone(self.config.bb)
+
+        lateral_channels_in_collection = {
+            'vgg16': [512, 256, 128, 64], 'vgg16bn': [512, 256, 128, 64], 'resnet50': [1024, 512, 256, 64],
+            'pvt_v2_b2': [512, 320, 128, 64], 'pvt_v2_b5': [512, 320, 128, 64],
+            'swin_v1_b': [1024, 512, 256, 128], 'swin_v1_l': [1536, 768, 384, 192],
+        }
+        channels = lateral_channels_in_collection[self.config.bb]
+        self.squeeze_module = BasicDecBlk(channels[0], channels[0])
+
+        self.decoder = Decoder(channels)
+
+        if 0:
+            for key, value in self.named_parameters():
+                if 'bb.' in key:
+                    value.requires_grad = False
+
+    def forward(self, x):
+        if isinstance(x, list):
+            x = torch.cat(x, dim=1)
+        x = self.stem_layer(x)
+        ########## Encoder ##########
+        if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
+            x1 = self.bb.conv1(x)
+            x2 = self.bb.conv2(x1)
+            x3 = self.bb.conv3(x2)
+            x4 = self.bb.conv4(x3)
+        else:
+            x1, x2, x3, x4 = self.bb(x)
+
+        x4 = self.squeeze_module(x4)
+
+        ########## Decoder ##########
+
+        features = [x, x1, x2, x3, x4]
+        scaled_preds = self.decoder(features)
+
+        return scaled_preds
+
+
+class Decoder(nn.Module):
+    def __init__(self, channels):
+        super(Decoder, self).__init__()
+        self.config = Config()
+        DecoderBlock = eval('BasicDecBlk')
+        LateralBlock = eval('BasicLatBlk')
+
+        self.decoder_block4 = DecoderBlock(channels[0], channels[1])
+        self.decoder_block3 = DecoderBlock(channels[1], channels[2])
+        self.decoder_block2 = DecoderBlock(channels[2], channels[3])
+        self.decoder_block1 = DecoderBlock(channels[3], channels[3]//2)
+
+        self.lateral_block4 = LateralBlock(channels[1], channels[1])
+        self.lateral_block3 = LateralBlock(channels[2], channels[2])
+        self.lateral_block2 = LateralBlock(channels[3], channels[3])
+
+        if self.config.ms_supervision:
+            self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
+            self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
+            self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
+        self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2, 1, 1, 1, 0))
+
+    def forward(self, features):
+        x, x1, x2, x3, x4 = features
+        outs = []
+        p4 = self.decoder_block4(x4)
+        _p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
+        _p3 = _p4 + self.lateral_block4(x3)
+
+        p3 = self.decoder_block3(_p3)
+        _p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
+        _p2 = _p3 + self.lateral_block3(x2)
+
+        p2 = self.decoder_block2(_p2)
+        _p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
+        _p1 = _p2 + self.lateral_block2(x1)
+
+        _p1 = self.decoder_block1(_p1)
+        _p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
+        p1_out = self.conv_out1(_p1)
+
+        if self.config.ms_supervision:
+            outs.append(self.conv_ms_spvn_4(p4))
+            outs.append(self.conv_ms_spvn_3(p3))
+            outs.append(self.conv_ms_spvn_2(p2))
+        outs.append(p1_out)
+        return outs
+
+
+class RefUNet(nn.Module):
+    # Refinement
+    def __init__(self, in_channels=3+1):
+        super(RefUNet, self).__init__()
+        self.encoder_1 = nn.Sequential(
+            nn.Conv2d(in_channels, 64, 3, 1, 1),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.encoder_2 = nn.Sequential(
+            nn.MaxPool2d(2, 2, ceil_mode=True),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.encoder_3 = nn.Sequential(
+            nn.MaxPool2d(2, 2, ceil_mode=True),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.encoder_4 = nn.Sequential(
+            nn.MaxPool2d(2, 2, ceil_mode=True),
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.pool4 = nn.MaxPool2d(2, 2, ceil_mode=True)
+        #####
+        self.decoder_5 = nn.Sequential(
+            nn.Conv2d(64, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+        #####
+        self.decoder_4 = nn.Sequential(
+            nn.Conv2d(128, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.decoder_3 = nn.Sequential(
+            nn.Conv2d(128, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.decoder_2 = nn.Sequential(
+            nn.Conv2d(128, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.decoder_1 = nn.Sequential(
+            nn.Conv2d(128, 64, 3, 1, 1),
+            nn.BatchNorm2d(64),
+            nn.ReLU(inplace=True)
+        )
+
+        self.conv_d0 = nn.Conv2d(64, 1, 3, 1, 1)
+
+        self.upscore2 = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
+
+    def forward(self, x):
+        outs = []
+        if isinstance(x, list):
+            x = torch.cat(x, dim=1)
+        hx = x
+
+        hx1 = self.encoder_1(hx)
+        hx2 = self.encoder_2(hx1)
+        hx3 = self.encoder_3(hx2)
+        hx4 = self.encoder_4(hx3)
+
+        hx = self.decoder_5(self.pool4(hx4))
+        hx = torch.cat((self.upscore2(hx), hx4), 1)
+
+        d4 = self.decoder_4(hx)
+        hx = torch.cat((self.upscore2(d4), hx3), 1)
+
+        d3 = self.decoder_3(hx)
+        hx = torch.cat((self.upscore2(d3), hx2), 1)
+
+        d2 = self.decoder_2(hx)
+        hx = torch.cat((self.upscore2(d2), hx1), 1)
+
+        d1 = self.decoder_1(hx)
+
+        x = self.conv_d0(d1)
+        outs.append(x)
+        return outs
+
+
+
+### models/stem_layer.py
+
+import torch.nn as nn
+# from utils import build_act_layer, build_norm_layer
+
+
+class StemLayer(nn.Module):
+    r""" Stem layer of InternImage
+    Args:
+        in_channels (int): number of input channels
+        out_channels (int): number of output channels
+        act_layer (str): activation layer
+        norm_layer (str): normalization layer
+    """
+
+    def __init__(self,
+                 in_channels=3+1,
+                 inter_channels=48,
+                 out_channels=96,
+                 act_layer='GELU',
+                 norm_layer='BN'):
+        super().__init__()
+        self.conv1 = nn.Conv2d(in_channels,
+                               inter_channels,
+                               kernel_size=3,
+                               stride=1,
+                               padding=1)
+        self.norm1 = build_norm_layer(
+            inter_channels, norm_layer, 'channels_first', 'channels_first'
+        )
+        self.act = build_act_layer(act_layer)
+        self.conv2 = nn.Conv2d(inter_channels,
+                               out_channels,
+                               kernel_size=3,
+                               stride=1,
+                               padding=1)
+        self.norm2 = build_norm_layer(
+            out_channels, norm_layer, 'channels_first', 'channels_first'
+        )
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.norm1(x)
+        x = self.act(x)
+        x = self.conv2(x)
+        x = self.norm2(x)
+        return x
+
+
+### models/birefnet.py
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from kornia.filters import laplacian
+from transformers import PreTrainedModel
+
+# from config import Config
+# from dataset import class_labels_TR_sorted
+# from models.build_backbone import build_backbone
+# from models.decoder_blocks import BasicDecBlk, ResBlk, HierarAttDecBlk
+# from models.lateral_blocks import BasicLatBlk
+# from models.aspp import ASPP, ASPPDeformable
+# from models.ing import *
+# from models.refiner import Refiner, RefinerPVTInChannels4, RefUNet
+# from models.stem_layer import StemLayer
+from .BiRefNet_config import BiRefNetConfig
+
+
+class BiRefNet(
+    PreTrainedModel
+):
+    config_class = BiRefNetConfig
+    def __init__(self, bb_pretrained=True, config=BiRefNetConfig()):
+        super(BiRefNet, self).__init__(config)
+        bb_pretrained = config.bb_pretrained
+        self.config = Config()
+        self.epoch = 1
+        self.bb = build_backbone(self.config.bb, pretrained=bb_pretrained)
+
+        channels = self.config.lateral_channels_in_collection
+
+        if self.config.auxiliary_classification:
+            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
+            self.cls_head = nn.Sequential(
+                nn.Linear(channels[0], len(class_labels_TR_sorted))
+            )
+
+        if self.config.squeeze_block:
+            self.squeeze_module = nn.Sequential(*[
+                eval(self.config.squeeze_block.split('_x')[0])(channels[0]+sum(self.config.cxt), channels[0])
+                for _ in range(eval(self.config.squeeze_block.split('_x')[1]))
+            ])
+
+        self.decoder = Decoder(channels)
+
+        if self.config.ender:
+            self.dec_end = nn.Sequential(
+                nn.Conv2d(1, 16, 3, 1, 1),
+                nn.Conv2d(16, 1, 3, 1, 1),
+                nn.ReLU(inplace=True),
+            )
+
+        # refine patch-level segmentation
+        if self.config.refine:
+            if self.config.refine == 'itself':
+                self.stem_layer = StemLayer(in_channels=3+1, inter_channels=48, out_channels=3, norm_layer='BN' if self.config.batch_size > 1 else 'LN')
+            else:
+                self.refiner = eval('{}({})'.format(self.config.refine, 'in_channels=3+1'))
+
+        if self.config.freeze_bb:
+            # Freeze the backbone...
+            print(self.named_parameters())
+            for key, value in self.named_parameters():
+                if 'bb.' in key and 'refiner.' not in key:
+                    value.requires_grad = False
+
+    def forward_enc(self, x):
+        if self.config.bb in ['vgg16', 'vgg16bn', 'resnet50']:
+            x1 = self.bb.conv1(x); x2 = self.bb.conv2(x1); x3 = self.bb.conv3(x2); x4 = self.bb.conv4(x3)
+        else:
+            x1, x2, x3, x4 = self.bb(x)
+            if self.config.mul_scl_ipt == 'cat':
+                B, C, H, W = x.shape
+                x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
+                x1 = torch.cat([x1, F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)], dim=1)
+                x2 = torch.cat([x2, F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)], dim=1)
+                x3 = torch.cat([x3, F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)], dim=1)
+                x4 = torch.cat([x4, F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)], dim=1)
+            elif self.config.mul_scl_ipt == 'add':
+                B, C, H, W = x.shape
+                x1_, x2_, x3_, x4_ = self.bb(F.interpolate(x, size=(H//2, W//2), mode='bilinear', align_corners=True))
+                x1 = x1 + F.interpolate(x1_, size=x1.shape[2:], mode='bilinear', align_corners=True)
+                x2 = x2 + F.interpolate(x2_, size=x2.shape[2:], mode='bilinear', align_corners=True)
+                x3 = x3 + F.interpolate(x3_, size=x3.shape[2:], mode='bilinear', align_corners=True)
+                x4 = x4 + F.interpolate(x4_, size=x4.shape[2:], mode='bilinear', align_corners=True)
+        class_preds = self.cls_head(self.avgpool(x4).view(x4.shape[0], -1)) if self.training and self.config.auxiliary_classification else None
+        if self.config.cxt:
+            x4 = torch.cat(
+                (
+                    *[
+                        F.interpolate(x1, size=x4.shape[2:], mode='bilinear', align_corners=True),
+                        F.interpolate(x2, size=x4.shape[2:], mode='bilinear', align_corners=True),
+                        F.interpolate(x3, size=x4.shape[2:], mode='bilinear', align_corners=True),
+                    ][-len(self.config.cxt):],
+                    x4
+                ),
+                dim=1
+            )
+        return (x1, x2, x3, x4), class_preds
+
+    def forward_ori(self, x):
+        ########## Encoder ##########
+        (x1, x2, x3, x4), class_preds = self.forward_enc(x)
+        if self.config.squeeze_block:
+            x4 = self.squeeze_module(x4)
+        ########## Decoder ##########
+        features = [x, x1, x2, x3, x4]
+        if self.training and self.config.out_ref:
+            features.append(laplacian(torch.mean(x, dim=1).unsqueeze(1), kernel_size=5))
+        scaled_preds = self.decoder(features)
+        return scaled_preds, class_preds
+
+    def forward(self, x):
+        scaled_preds, class_preds = self.forward_ori(x)
+        class_preds_lst = [class_preds]
+        return [scaled_preds, class_preds_lst] if self.training else scaled_preds
+
+
+class Decoder(nn.Module):
+    def __init__(self, channels):
+        super(Decoder, self).__init__()
+        self.config = Config()
+        DecoderBlock = eval(self.config.dec_blk)
+        LateralBlock = eval(self.config.lat_blk)
+
+        if self.config.dec_ipt:
+            self.split = self.config.dec_ipt_split
+            N_dec_ipt = 64
+            DBlock = SimpleConvs
+            ic = 64
+            ipt_cha_opt = 1
+            self.ipt_blk5 = DBlock(2**10*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
+            self.ipt_blk4 = DBlock(2**8*3 if self.split else 3, [N_dec_ipt, channels[0]//8][ipt_cha_opt], inter_channels=ic)
+            self.ipt_blk3 = DBlock(2**6*3 if self.split else 3, [N_dec_ipt, channels[1]//8][ipt_cha_opt], inter_channels=ic)
+            self.ipt_blk2 = DBlock(2**4*3 if self.split else 3, [N_dec_ipt, channels[2]//8][ipt_cha_opt], inter_channels=ic)
+            self.ipt_blk1 = DBlock(2**0*3 if self.split else 3, [N_dec_ipt, channels[3]//8][ipt_cha_opt], inter_channels=ic)
+        else:
+            self.split = None
+
+        self.decoder_block4 = DecoderBlock(channels[0]+([N_dec_ipt, channels[0]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[1])
+        self.decoder_block3 = DecoderBlock(channels[1]+([N_dec_ipt, channels[0]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[2])
+        self.decoder_block2 = DecoderBlock(channels[2]+([N_dec_ipt, channels[1]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3])
+        self.decoder_block1 = DecoderBlock(channels[3]+([N_dec_ipt, channels[2]//8][ipt_cha_opt] if self.config.dec_ipt else 0), channels[3]//2)
+        self.conv_out1 = nn.Sequential(nn.Conv2d(channels[3]//2+([N_dec_ipt, channels[3]//8][ipt_cha_opt] if self.config.dec_ipt else 0), 1, 1, 1, 0))
+
+        self.lateral_block4 = LateralBlock(channels[1], channels[1])
+        self.lateral_block3 = LateralBlock(channels[2], channels[2])
+        self.lateral_block2 = LateralBlock(channels[3], channels[3])
+
+        if self.config.ms_supervision:
+            self.conv_ms_spvn_4 = nn.Conv2d(channels[1], 1, 1, 1, 0)
+            self.conv_ms_spvn_3 = nn.Conv2d(channels[2], 1, 1, 1, 0)
+            self.conv_ms_spvn_2 = nn.Conv2d(channels[3], 1, 1, 1, 0)
+
+            if self.config.out_ref:
+                _N = 16
+                self.gdt_convs_4 = nn.Sequential(nn.Conv2d(channels[1], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
+                self.gdt_convs_3 = nn.Sequential(nn.Conv2d(channels[2], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
+                self.gdt_convs_2 = nn.Sequential(nn.Conv2d(channels[3], _N, 3, 1, 1), nn.BatchNorm2d(_N) if self.config.batch_size > 1 else nn.Identity(), nn.ReLU(inplace=True))
+
+                self.gdt_convs_pred_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+                self.gdt_convs_pred_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+                self.gdt_convs_pred_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+                
+                self.gdt_convs_attn_4 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+                self.gdt_convs_attn_3 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+                self.gdt_convs_attn_2 = nn.Sequential(nn.Conv2d(_N, 1, 1, 1, 0))
+
+    def get_patches_batch(self, x, p):
+        _size_h, _size_w = p.shape[2:]
+        patches_batch = []
+        for idx in range(x.shape[0]):
+            columns_x = torch.split(x[idx], split_size_or_sections=_size_w, dim=-1)
+            patches_x = []
+            for column_x in columns_x:
+                patches_x += [p.unsqueeze(0) for p in torch.split(column_x, split_size_or_sections=_size_h, dim=-2)]
+            patch_sample = torch.cat(patches_x, dim=1)
+            patches_batch.append(patch_sample)
+        return torch.cat(patches_batch, dim=0)
+
+    def forward(self, features):
+        if self.training and self.config.out_ref:
+            outs_gdt_pred = []
+            outs_gdt_label = []
+            x, x1, x2, x3, x4, gdt_gt = features
+        else:
+            x, x1, x2, x3, x4 = features
+        outs = []
+
+        if self.config.dec_ipt:
+            patches_batch = self.get_patches_batch(x, x4) if self.split else x
+            x4 = torch.cat((x4, self.ipt_blk5(F.interpolate(patches_batch, size=x4.shape[2:], mode='bilinear', align_corners=True))), 1)
+        p4 = self.decoder_block4(x4)
+        m4 = self.conv_ms_spvn_4(p4) if self.config.ms_supervision else None
+        if self.config.out_ref:
+            p4_gdt = self.gdt_convs_4(p4)
+            if self.training:
+                # >> GT:
+                m4_dia = m4
+                gdt_label_main_4 = gdt_gt * F.interpolate(m4_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
+                outs_gdt_label.append(gdt_label_main_4)
+                # >> Pred:
+                gdt_pred_4 = self.gdt_convs_pred_4(p4_gdt)
+                outs_gdt_pred.append(gdt_pred_4)
+            gdt_attn_4 = self.gdt_convs_attn_4(p4_gdt).sigmoid()
+            # >> Finally:
+            p4 = p4 * gdt_attn_4
+        _p4 = F.interpolate(p4, size=x3.shape[2:], mode='bilinear', align_corners=True)
+        _p3 = _p4 + self.lateral_block4(x3)
+
+        if self.config.dec_ipt:
+            patches_batch = self.get_patches_batch(x, _p3) if self.split else x
+            _p3 = torch.cat((_p3, self.ipt_blk4(F.interpolate(patches_batch, size=x3.shape[2:], mode='bilinear', align_corners=True))), 1)
+        p3 = self.decoder_block3(_p3)
+        m3 = self.conv_ms_spvn_3(p3) if self.config.ms_supervision else None
+        if self.config.out_ref:
+            p3_gdt = self.gdt_convs_3(p3)
+            if self.training:
+                # >> GT:
+                # m3 --dilation--> m3_dia
+                # G_3^gt * m3_dia --> G_3^m, which is the label of gradient
+                m3_dia = m3
+                gdt_label_main_3 = gdt_gt * F.interpolate(m3_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
+                outs_gdt_label.append(gdt_label_main_3)
+                # >> Pred:
+                # p3 --conv--BN--> F_3^G, where F_3^G predicts the \hat{G_3} with xx
+                # F_3^G --sigmoid--> A_3^G
+                gdt_pred_3 = self.gdt_convs_pred_3(p3_gdt)
+                outs_gdt_pred.append(gdt_pred_3)
+            gdt_attn_3 = self.gdt_convs_attn_3(p3_gdt).sigmoid()
+            # >> Finally:
+            # p3 = p3 * A_3^G
+            p3 = p3 * gdt_attn_3
+        _p3 = F.interpolate(p3, size=x2.shape[2:], mode='bilinear', align_corners=True)
+        _p2 = _p3 + self.lateral_block3(x2)
+
+        if self.config.dec_ipt:
+            patches_batch = self.get_patches_batch(x, _p2) if self.split else x
+            _p2 = torch.cat((_p2, self.ipt_blk3(F.interpolate(patches_batch, size=x2.shape[2:], mode='bilinear', align_corners=True))), 1)
+        p2 = self.decoder_block2(_p2)
+        m2 = self.conv_ms_spvn_2(p2) if self.config.ms_supervision else None
+        if self.config.out_ref:
+            p2_gdt = self.gdt_convs_2(p2)
+            if self.training:
+                # >> GT:
+                m2_dia = m2
+                gdt_label_main_2 = gdt_gt * F.interpolate(m2_dia, size=gdt_gt.shape[2:], mode='bilinear', align_corners=True)
+                outs_gdt_label.append(gdt_label_main_2)
+                # >> Pred:
+                gdt_pred_2 = self.gdt_convs_pred_2(p2_gdt)
+                outs_gdt_pred.append(gdt_pred_2)
+            gdt_attn_2 = self.gdt_convs_attn_2(p2_gdt).sigmoid()
+            # >> Finally:
+            p2 = p2 * gdt_attn_2
+        _p2 = F.interpolate(p2, size=x1.shape[2:], mode='bilinear', align_corners=True)
+        _p1 = _p2 + self.lateral_block2(x1)
+
+        if self.config.dec_ipt:
+            patches_batch = self.get_patches_batch(x, _p1) if self.split else x
+            _p1 = torch.cat((_p1, self.ipt_blk2(F.interpolate(patches_batch, size=x1.shape[2:], mode='bilinear', align_corners=True))), 1)
+        _p1 = self.decoder_block1(_p1)
+        _p1 = F.interpolate(_p1, size=x.shape[2:], mode='bilinear', align_corners=True)
+
+        if self.config.dec_ipt:
+            patches_batch = self.get_patches_batch(x, _p1) if self.split else x
+            _p1 = torch.cat((_p1, self.ipt_blk1(F.interpolate(patches_batch, size=x.shape[2:], mode='bilinear', align_corners=True))), 1)
+        p1_out = self.conv_out1(_p1)
+
+        if self.config.ms_supervision:
+            outs.append(m4)
+            outs.append(m3)
+            outs.append(m2)
+        outs.append(p1_out)
+        return outs if not (self.config.out_ref and self.training) else ([outs_gdt_pred, outs_gdt_label], outs)
+
+
+class SimpleConvs(nn.Module):
+    def __init__(
+        self, in_channels: int, out_channels: int, inter_channels=64
+    ) -> None:
+        super().__init__()
+        self.conv1 = nn.Conv2d(in_channels, inter_channels, 3, 1, 1)
+        self.conv_out = nn.Conv2d(inter_channels, out_channels, 3, 1, 1)
+
+    def forward(self, x):
+        return self.conv_out(self.conv1(x))

models/BiRefNet/RMBG-2.0/config.json

@@ -0,0 +1,20 @@
+{
+  "_name_or_path": "ZhengPeng7/BiRefNet",
+  "architectures": [
+    "BiRefNet"
+  ],
+  "auto_map": {
+    "AutoConfig": "BiRefNet_config.BiRefNetConfig",
+    "AutoModelForImageSegmentation": "birefnet.BiRefNet"
+  },
+  "custom_pipelines": {
+    "image-segmentation": {
+      "pt": [
+        "AutoModelForImageSegmentation"
+      ],
+      "tf": [],
+      "type": "image"
+    }
+  },
+  "bb_pretrained": false
+}

models/BiRefNet/RMBG-2.0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566ed80c3d95f87ada6864d4cbe2290a1c5eb1c7bb0b123e984f60f76b02c3a7
+size 884878856

models/BiRefNet/RMBG-2.0/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b486f08200f513f460da46dd701db5fbb47d79b4be4b708a19444bcd4e79958
+size 1024331469

models/BiRefNet/RMBG-2.0/onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadc9222fbffa53a348efea52d97475350ecee463a4a46f452e6e6b7b8757d25
+size 355288046

models/BiRefNet/RMBG-2.0/onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc47db40d113090ba5d7a13d8fcfd9ee4eda510ce92613219b2fe19da4746f6
+size 513576499

models/BiRefNet/RMBG-2.0/onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ee7690d8c5e7fc45d7b4938ac2fe4eab63fdeddd537673cda2d4c6e74809af
+size 366087445

models/BiRefNet/RMBG-2.0/onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a813e0eab56c982b71254214f41fa860cc7b565a6f2aab55d1f99f41c646ece1
+size 367451512

models/BiRefNet/RMBG-2.0/onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfeb5f93220eb19f6747c217b62cf04342840c4e973f55bf64e9762919f446d
+size 233815293

models/BiRefNet/RMBG-2.0/onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcea23951a378f92634834888896cc1eec54655366ae6e949282646ce17c5420
+size 366087549

models/BiRefNet/RMBG-2.0/onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcea23951a378f92634834888896cc1eec54655366ae6e949282646ce17c5420
+size 366087549

models/BiRefNet/RMBG-2.0/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1024,
+    "width": 1024
+  }
+}

models/BiRefNet/RMBG-2.0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0986c2881028a2d0ef9b638ab06bc4cfe7c529760d451eaa7098ade2592015f2
+size 885079136

models/BiRefNet/pth/BiRefNet-general-epoch_244.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11341a6a1c12646627e8d28da025bfec8aad027929d377cbe8fd4759636cc77c
+size 885082437

models/CogVideo/CogVideoX-5b-1.5/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

models/CogVideo/CogVideoX-5b-1.5/transformer_I2V/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.31.0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 32,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "ofs_embed_dim": 512,
+  "out_channels": 16,
+  "patch_bias": false,
+  "patch_size": 2,
+  "patch_size_t": 2,
+  "sample_frames": 81,
+  "sample_height": 300,
+  "sample_width": 300,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": true
+}

models/CogVideo/CogVideoX-5b-1.5/transformer_I2V/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d392921dd79e0e7adbef45f2c88a21dfe9aeb8688a9dd6e757275b2e4c1bca
+size 4979532864

models/CogVideo/CogVideoX-5b-1.5/transformer_I2V/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052af05f6d91fcb5bc7cb85805c507fc3c476b2bc01a1b2475a384cff03a7854
+size 4948039832

models/CogVideo/CogVideoX-5b-1.5/transformer_I2V/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f3b8812a540aca85a15fb06909cfd36b7b1f3bc638042cf8f6899d38043787
+size 1215733728

models/CogVideo/CogVideoX-5b-1.5/vae/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "AutoencoderKLCogVideoX",
+  "_diffusers_version": "0.31.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_height": 480,
+  "sample_width": 720,
+  "scaling_factor": 0.7,
+  "shift_factor": null,
+  "temporal_compression_ratio": 4,
+  "up_block_types": [
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

models/CogVideo/CogVideoX-5b-1.5/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd47d57ad948ff80da0af0cb2e4dcdef65073aba59bccfd383ada9a7d1c02024
+size 431221142

models/CogVideo/CogVideoX-5b-I2V/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

models/CogVideo/CogVideoX-5b-I2V/LICENSE

@@ -0,0 +1,71 @@
+The CogVideoX License
+
+1. Definitions
+
+“Licensor” means the CogVideoX Model Team that distributes its Software.
+
+“Software” means the CogVideoX model parameters made available under this license.
+
+2. License Grant
+
+Under the terms and conditions of this license, the licensor hereby grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free copyright license. The intellectual property rights of the generated content belong to the user to the extent permitted by applicable local laws.
+This license allows you to freely use all open-source models in this repository for academic research. Users who wish to use the models for commercial purposes must register and obtain a basic commercial license in https://open.bigmodel.cn/mla/form .
+Users who have registered and obtained the basic commercial license can use the models for commercial activities for free, but must comply with all terms and conditions of this license. Additionally, the number of service users (visits) for your commercial activities must not exceed 1 million visits per month.
+If the number of service users (visits) for your commercial activities exceeds 1 million visits per month, you need to contact our business team to obtain more commercial licenses.
+The above copyright statement and this license statement should be included in all copies or significant portions of this software.
+
+3. Restriction
+
+You will not use, copy, modify, merge, publish, distribute, reproduce, or create derivative works of the Software, in whole or in part, for any military, or illegal purposes.
+
+You will not use the Software for any act that may undermine China's national security and national unity, harm the public interest of society, or infringe upon the rights and interests of human beings.
+
+4. Disclaimer
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+5. Limitation of Liability
+
+EXCEPT TO THE EXTENT PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER BASED IN TORT, NEGLIGENCE, CONTRACT, LIABILITY, OR OTHERWISE WILL ANY LICENSOR BE LIABLE TO YOU FOR ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES, OR ANY OTHER COMMERCIAL LOSSES, EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+6. Dispute Resolution
+
+This license shall be governed and construed in accordance with the laws of People’s Republic of China. Any dispute arising from or in connection with this License shall be submitted to Haidian District People's Court in Beijing.
+
+Note that the license is subject to update to a more comprehensive version.  For any questions related to the license and copyright, please contact us at [email protected].
+
+1. 定义
+
+“许可方”是指分发其软件的 CogVideoX 模型团队。
+
+“软件”是指根据本许可提供的 CogVideoX 模型参数。
+
+2. 许可授予
+
+根据本许可的条款和条件，许可方特此授予您非排他性、全球性、不可转让、不可再许可、可撤销、免版税的版权许可。生成内容的知识产权所属，可根据适用当地法律的规定，在法律允许的范围内由用户享有生成内容的知识产权或其他权利。
+本许可允许您免费使用本仓库中的所有开源模型进行学术研究。对于希望将模型用于商业目的的用户，需在 https://open.bigmodel.cn/mla/form 完成登记并获得基础商用授权。
+
+经过登记并获得基础商用授权的用户可以免费使用本模型进行商业活动，但必须遵守本许可的所有条款和条件。
+在本许可证下，您的商业活动的服务用户数量（访问量）不得超过100万人次访问 / 每月。如果超过，您需要与我们的商业团队联系以获得更多的商业许可。
+上述版权声明和本许可声明应包含在本软件的所有副本或重要部分中。
+
+3.限制
+
+您不得出于任何军事或非法目的使用、复制、修改、合并、发布、分发、复制或创建本软件的全部或部分衍生作品。
+
+您不得利用本软件从事任何危害国家安全和国家统一、危害社会公共利益、侵犯人身权益的行为。
+
+4.免责声明
+
+本软件“按原样”提供，不提供任何明示或暗示的保证，包括但不限于对适销性、特定用途的适用性和非侵权性的保证。
+在任何情况下，作者或版权持有人均不对任何索赔、损害或其他责任负责，无论是在合同诉讼、侵权行为还是其他方面，由软件或软件的使用或其他交易引起、由软件引起或与之相关 软件。
+
+5. 责任限制
+
+除适用��律禁止的范围外，在任何情况下且根据任何法律理论，无论是基于侵权行为、疏忽、合同、责任或其他原因，任何许可方均不对您承担任何直接、间接、特殊、偶然、示范性、 或间接损害，或任何其他商业损失，即使许可人已被告知此类损害的可能性。
+
+6.争议解决
+
+本许可受中华人民共和国法律管辖并按其解释。 因本许可引起的或与本许可有关的任何争议应提交北京市海淀区人民法院。
+
+请注意，许可证可能会更新到更全面的版本。 有关许可和版权的任何问题，请通过 [email protected] 与我们联系。

models/CogVideo/CogVideoX-5b-I2V/README.md

@@ -0,0 +1,280 @@
+---
+license: other
+license_link: https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/LICENSE
+language:
+  - en
+tags:
+  - cogvideox
+  - video-generation
+  - thudm
+  - image-to-video
+inference: false
+---
+
+# CogVideoX-5B-I2V
+
+<p style="text-align: center;">
+  <div align="center">
+  <img src=https://github.com/THUDM/CogVideo/raw/main/resources/logo.svg width="50%"/>
+  </div>
+  <p align="center">
+  <a href="https://huggingface.co/THUDM//CogVideoX-5b-I2V/blob/main/README.md">📄 Read in English</a> | 
+  <a href="https://huggingface.co/spaces/THUDM/CogVideoX-5B-Space">🤗 Huggingface Space</a> |
+  <a href="https://github.com/THUDM/CogVideo">🌐 Github </a> | 
+  <a href="https://arxiv.org/pdf/2408.06072">📜 arxiv </a>
+</p>
+<p align="center">
+📍 Visit <a href="https://chatglm.cn/video?fr=osm_cogvideox">Qingying</a> and <a href="https://open.bigmodel.cn/?utm_campaign=open&_channel_track_key=OWTVNma9">API Platform</a> for the commercial version of the video generation model
+</p>
+
+## Model Introduction
+
+CogVideoX is an open-source video generation model originating
+from [Qingying](https://chatglm.cn/video?fr=osm_cogvideo). The table below presents information related to the video
+generation models we offer in this version.
+
+<table  style="border-collapse: collapse; width: 100%;">
+  <tr>
+    <th style="text-align: center;">Model Name</th>
+    <th style="text-align: center;">CogVideoX-2B</th>
+    <th style="text-align: center;">CogVideoX-5B</th>
+    <th style="text-align: center;">CogVideoX-5B-I2V (This Repository)</th>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Model Description</td>
+    <td style="text-align: center;">Entry-level model, balancing compatibility. Low cost for running and secondary development.</td>
+    <td style="text-align: center;">Larger model with higher video generation quality and better visual effects.</td>
+    <td style="text-align: center;">CogVideoX-5B image-to-video version.</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Inference Precision</td>
+    <td style="text-align: center;"><b>FP16*(recommended)</b>, BF16, FP32, FP8*, INT8, not supported: INT4</td>
+    <td colspan="2" style="text-align: center;"><b>BF16 (recommended)</b>, FP16, FP32, FP8*, INT8, not supported: INT4</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Single GPU Memory Usage<br></td>
+    <td style="text-align: center;"><a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> FP16: 18GB <br><b>diffusers FP16: from 4GB* </b><br><b>diffusers INT8 (torchao): from 3.6GB*</b></td>
+    <td colspan="2" style="text-align: center;"><a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> BF16: 26GB <br><b>diffusers BF16: from 5GB* </b><br><b>diffusers INT8 (torchao): from 4.4GB*</b></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Multi-GPU Inference Memory Usage</td>
+    <td style="text-align: center;"><b>FP16: 10GB* using diffusers</b><br></td>
+    <td colspan="2" style="text-align: center;"><b>BF16: 15GB* using diffusers</b><br></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Inference Speed<br>(Step = 50, FP/BF16)</td>
+    <td style="text-align: center;">Single A100: ~90 seconds<br>Single H100: ~45 seconds</td>
+    <td colspan="2" style="text-align: center;">Single A100: ~180 seconds<br>Single H100: ~90 seconds</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Fine-tuning Precision</td>
+    <td style="text-align: center;"><b>FP16</b></td>
+    <td colspan="2" style="text-align: center;"><b>BF16</b></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Fine-tuning Memory Usage</td>
+    <td style="text-align: center;">47 GB (bs=1, LORA)<br> 61 GB (bs=2, LORA)<br> 62GB (bs=1, SFT)</td>
+    <td style="text-align: center;">63 GB (bs=1, LORA)<br> 80 GB (bs=2, LORA)<br> 75GB (bs=1, SFT)<br></td>
+    <td style="text-align: center;">78 GB (bs=1, LORA)<br> 75GB (bs=1, SFT, 16GPU)<br></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Prompt Language</td>
+    <td colspan="3" style="text-align: center;">English*</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Maximum Prompt Length</td>
+    <td colspan="3" style="text-align: center;">226 Tokens</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Video Length</td>
+    <td colspan="3" style="text-align: center;">6 Seconds</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Frame Rate</td>
+    <td colspan="3" style="text-align: center;">8 Frames / Second</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">Video Resolution</td>
+    <td colspan="3" style="text-align: center;">720 x 480, no support for other resolutions (including fine-tuning)</td>
+  </tr>
+    <tr>
+    <td style="text-align: center;">Position Embedding</td>
+    <td style="text-align: center;">3d_sincos_pos_embed</td>
+    <td style="text-align: center;">3d_rope_pos_embed</td>
+    <td style="text-align: center;">3d_rope_pos_embed + learnable_pos_embed</td>
+  </tr>
+</table>
+
+**Data Explanation**
+
++ While testing using the diffusers library, all optimizations included in the diffusers library were enabled. This
+  scheme has not been tested for actual memory usage on devices outside of **NVIDIA A100 / H100** architectures.
+  Generally, this scheme can be adapted to all **NVIDIA Ampere architecture** and above devices. If optimizations are
+  disabled, memory consumption will multiply, with peak memory usage being about 3 times the value in the table.
+  However, speed will increase by about 3-4 times. You can selectively disable some optimizations, including:
+
+```
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
+```
+
++ For multi-GPU inference, the `enable_sequential_cpu_offload()` optimization needs to be disabled.
++ Using INT8 models will slow down inference, which is done to accommodate lower-memory GPUs while maintaining minimal
+  video quality loss, though inference speed will significantly decrease.
++ The CogVideoX-2B model was trained in `FP16` precision, and all CogVideoX-5B models were trained in `BF16` precision.
+  We recommend using the precision in which the model was trained for inference.
++ [PytorchAO](https://github.com/pytorch/ao) and [Optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be
+  used to quantize the text encoder, transformer, and VAE modules to reduce the memory requirements of CogVideoX. This
+  allows the model to run on free T4 Colabs or GPUs with smaller memory! Also, note that TorchAO quantization is fully
+  compatible with `torch.compile`, which can significantly improve inference speed. FP8 precision must be used on
+  devices with NVIDIA H100 and above, requiring source installation of `torch`, `torchao`, `diffusers`, and `accelerate`
+  Python packages. CUDA 12.4 is recommended.
++ The inference speed tests also used the above memory optimization scheme. Without memory optimization, inference speed
+  increases by about 10%. Only the `diffusers` version of the model supports quantization.
++ The model only supports English input; other languages can be translated into English for use via large model
+  refinement.
++ The memory usage of model fine-tuning is tested in an `8 * H100` environment, and the program automatically
+  uses `Zero 2` optimization. If a specific number of GPUs is marked in the table, that number or more GPUs must be used
+  for fine-tuning.
+
+**Reminders**
+
++ Use [SAT](https://github.com/THUDM/SwissArmyTransformer) for inference and fine-tuning SAT version models. Feel free
+  to visit our GitHub for more details.
+
+## Getting Started Quickly 🤗
+
+This model supports deployment using the Hugging Face diffusers library. You can follow the steps below to get started.
+
+**We recommend that you visit our [GitHub](https://github.com/THUDM/CogVideo) to check out prompt optimization and
+conversion to get a better experience.**
+
+1. Install the required dependencies
+
+```shell
+# diffusers>=0.30.3
+# transformers>=0.44.2
+# accelerate>=0.34.0
+# imageio-ffmpeg>=0.5.1
+pip install --upgrade transformers accelerate diffusers imageio-ffmpeg 
+```
+
+2. Run the code
+
+```python
+import torch
+from diffusers import CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+
+prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
+image = load_image(image="input.jpg")
+pipe = CogVideoXImageToVideoPipeline.from_pretrained(
+    "THUDM/CogVideoX-5b-I2V",
+    torch_dtype=torch.bfloat16
+)
+
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
+video = pipe(
+    prompt=prompt,
+    image=image,
+    num_videos_per_prompt=1,
+    num_inference_steps=50,
+    num_frames=49,
+    guidance_scale=6,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).frames[0]
+
+export_to_video(video, "output.mp4", fps=8)
+```
+
+## Quantized Inference
+
+[PytorchAO](https://github.com/pytorch/ao) and [Optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be
+used to quantize the text encoder, transformer, and VAE modules to reduce CogVideoX's memory requirements. This allows
+the model to run on free T4 Colab or GPUs with lower VRAM! Also, note that TorchAO quantization is fully compatible
+with `torch.compile`, which can significantly accelerate inference.
+
+```
+# To get started, PytorchAO needs to be installed from the GitHub source and PyTorch Nightly.
+# Source and nightly installation is only required until the next release.
+
+import torch
+from diffusers import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel, CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+from transformers import T5EncoderModel
+from torchao.quantization import quantize_, int8_weight_only
+
+quantization = int8_weight_only
+
+text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX-5b-I2V", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+quantize_(text_encoder, quantization())
+
+transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-5b-I2V",subfolder="transformer", torch_dtype=torch.bfloat16)
+quantize_(transformer, quantization())
+
+vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-5b-I2V", subfolder="vae", torch_dtype=torch.bfloat16)
+quantize_(vae, quantization())
+
+# Create pipeline and run inference
+pipe = CogVideoXImageToVideoPipeline.from_pretrained(
+    "THUDM/CogVideoX-5b-I2V",
+    text_encoder=text_encoder,
+    transformer=transformer,
+    vae=vae,
+    torch_dtype=torch.bfloat16,
+)
+
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
+prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
+image = load_image(image="input.jpg")
+video = pipe(
+    prompt=prompt,
+    image=image,
+    num_videos_per_prompt=1,
+    num_inference_steps=50,
+    num_frames=49,
+    guidance_scale=6,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).frames[0]
+
+export_to_video(video, "output.mp4", fps=8)
+```
+
+Additionally, these models can be serialized and stored using PytorchAO in quantized data types to save disk space. You
+can find examples and benchmarks at the following links:
+
+- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
+- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
+
+## Further Exploration
+
+Feel free to enter our [GitHub](https://github.com/THUDM/CogVideo), where you'll find:
+
+1. More detailed technical explanations and code.
+2. Optimized prompt examples and conversions.
+3. Detailed code for model inference and fine-tuning.
+4. Project update logs and more interactive opportunities.
+5. CogVideoX toolchain to help you better use the model.
+6. INT8 model inference code.
+
+## Model License
+
+This model is released under the [CogVideoX LICENSE](LICENSE).
+
+## Citation
+
+```
+@article{yang2024cogvideox,
+  title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
+  author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
+  journal={arXiv preprint arXiv:2408.06072},
+  year={2024}
+}
+```

models/CogVideo/CogVideoX-5b-I2V/README_zh.md

@@ -0,0 +1,252 @@
+# CogVideoX-5B-I2V
+
+<p style="text-align: center;">
+  <div align="center">
+  <img src=https://github.com/THUDM/CogVideo/raw/main/resources/logo.svg width="50%"/>
+  </div>
+  <p align="center">
+  <a href="https://huggingface.co/THUDM/CogVideoX-5b-I2V/blob/main/README.md">📄 Read in English</a> | 
+  <a href="https://huggingface.co/spaces/THUDM/CogVideoX-5B-Space">🤗 Huggingface Space</a> |
+  <a href="https://github.com/THUDM/CogVideo">🌐 Github </a> | 
+  <a href="https://arxiv.org/pdf/2408.06072">📜 arxiv </a>
+</p>
+<p align="center">
+📍 前往<a href="https://chatglm.cn/video?fr=osm_cogvideox"> 清影</a> 和 <a href="https://open.bigmodel.cn/?utm_campaign=open&_channel_track_key=OWTVNma9"> API平台</a> 体验商业版视频生成模型
+</p>
+
+## 模型介绍
+
+CogVideoX是 [清影](https://chatglm.cn/video?fr=osm_cogvideo) 同源的开源版本视频生成模型。下表展示我们在本代提供的视频生成模型列表相关信息:
+
+<table  style="border-collapse: collapse; width: 100%;">
+  <tr>
+    <th style="text-align: center;">模型名</th>
+    <th style="text-align: center;">CogVideoX-2B</th>
+    <th style="text-align: center;">CogVideoX-5B</th>
+    <th style="text-align: center;">CogVideoX-5B-I2V (本仓库)</th>
+  </tr>
+  <tr>
+    <td style="text-align: center;">模型介绍</td>
+    <td style="text-align: center;">入门级模型，兼顾兼容性。运行，二次开发成本低。</td>
+    <td style="text-align: center;">视频生成质量更高，视觉效果更好的更大尺寸模型。</td>
+    <td style="text-align: center;">CogVideoX-5B 图生视频版本。</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">推理精度</td>
+    <td style="text-align: center;"><b>FP16*(推荐)</b>, BF16, FP32，FP8*，INT8，不支持INT4</td>
+    <td colspan="2" style="text-align: center;"><b>BF16(推荐)</b>, FP16, FP32，FP8*，INT8，不支持INT4</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">单GPU显存消耗<br></td>
+    <td style="text-align: center;"><a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> FP16: 18GB <br><b>diffusers FP16: 4GB起* </b><br><b>diffusers INT8(torchao): 3.6G起*</b></td>
+    <td colspan="2" style="text-align: center;"><a href="https://github.com/THUDM/SwissArmyTransformer">SAT</a> BF16: 26GB <br><b>diffusers BF16 : 5GB起* </b><br><b>diffusers INT8(torchao): 4.4G起* </b></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">多GPU推理显存消耗</td>
+    <td style="text-align: center;"><b>FP16: 10GB* using diffusers</b><br></td>
+    <td colspan="2" style="text-align: center;"><b>BF16: 15GB* using diffusers</b><br></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">推理速度<br>(Step = 50, FP/BF16)</td>
+    <td style="text-align: center;">单卡A100: ~90秒<br>单卡H100: ~45秒</td>
+    <td colspan="2" style="text-align: center;">单卡A100: ~180秒<br>单卡H100: ~90秒</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">微调精度</td>
+    <td style="text-align: center;"><b>FP16</b></td>
+    <td colspan="2" style="text-align: center;"><b>BF16</b></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">微调显存消耗</td>
+    <td style="text-align: center;">47 GB (bs=1, LORA)<br> 61 GB (bs=2, LORA)<br> 62GB (bs=1, SFT)</td>
+    <td style="text-align: center;">63 GB (bs=1, LORA)<br> 80 GB (bs=2, LORA)<br> 75GB (bs=1, SFT)<br></td>
+    <td style="text-align: center;">78 GB (bs=1, LORA)<br> 75GB (bs=1, SFT, 16GPU)<br></td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">提示词语言</td>
+    <td colspan="3" style="text-align: center;">English*</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">提示词长度上限</td>
+    <td colspan="3" style="text-align: center;">226 Tokens</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">视频长度</td>
+    <td colspan="3" style="text-align: center;">6 秒</td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">帧率</td>
+    <td colspan="3" style="text-align: center;">8 帧 / 秒 </td>
+  </tr>
+  <tr>
+    <td style="text-align: center;">视频分辨率</td>
+    <td colspan="3" style="text-align: center;">720 * 480，不支持其他分辨率(含微调)</td>
+  </tr>
+    <tr>
+    <td style="text-align: center;">位置编码</td>
+    <td style="text-align: center;">3d_sincos_pos_embed</td>
+    <td style="text-align: center;">3d_rope_pos_embed</td>
+    <td style="text-align: center;">3d_rope_pos_embed + learnable_pos_embed</td>
+  </tr>
+</table>
+
+**数据解释**
+
++ 使用 diffusers 库进行测试时，启用了全部`diffusers`库自带的优化，该方案未测试在非**NVIDIA A100 / H100**
+  外的设备上的实际显存 / 内存占用。通常，该方案可以适配于所有 **NVIDIA 安培架构**
+  以上的设备。若关闭优化，显存占用会成倍增加，峰值显存约为表格的3倍。但速度提升3-4倍左右。你可以选择性的关闭部分优化，这些优化包括:
+
+```
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_slicing()
+pipe.vae.enable_tiling()
+```
+
++ 多GPU推理时，需要关闭 `enable_sequential_cpu_offload()` 优化。
++ 使用 INT8 模型会导致推理速度降低，此举是为了满足显存较低的显卡能正常推理并保持较少的视频质量损失，推理速度大幅降低。
++ CogVideoX-2B 模型采用 `FP16` 精度训练， 搜有 CogVideoX-5B 模型采用 `BF16` 精度训练。我们推荐使用模型训练的精度进行推理。
++ [PytorchAO](https://github.com/pytorch/ao) 和 [Optimum-quanto](https://github.com/huggingface/optimum-quanto/)
+  可以用于量化文本编码器、Transformer 和 VAE 模块，以降低 CogVideoX 的内存需求。这使得在免费的 T4 Colab 或更小显存的 GPU
+  上运行模型成为可能！同样值得注意的是，TorchAO 量化完全兼容 `torch.compile`，这可以显著提高推理速度。在 `NVIDIA H100`
+  及以上设备上必须使用 `FP8` 精度，这需要源码安装 `torch`、`torchao`、`diffusers` 和 `accelerate` Python
+  包。建议使用 `CUDA 12.4`。
++ 推理速度测试同样采用了上述显存优化方案，不采用显存优化的情况下，推理速度提升约10%。 只有`diffusers`版本模型支持量化。
++ 模型仅支持英语输入，其他语言可以通过大模型润色时翻译为英语。
++ 模型微调所占用的显存是在 `8 * H100` 环境下进行测试，程序已经自动使用`Zero 2` 优化。表格中若有标注具体GPU数量则必须使用大于等于该数量的GPU进行微调。
+
+**提醒**
+
++ 使用 [SAT](https://github.com/THUDM/SwissArmyTransformer) 推理和微调SAT版本模型。欢迎前往我们的github查看。
+
+## 快速上手 🤗
+
+本模型已经支持使用 huggingface 的 diffusers 库进行部署，你可以按照以下步骤进行部署。
+
+**我们推荐您进入我们的 [github](https://github.com/THUDM/CogVideo) 并查看相关的提示词优化和转换，以获得更好的体验。**
+
+1. 安装对应的依赖
+
+```shell
+# diffusers>=0.30.3
+# transformers>=0.44.2
+# accelerate>=0.34.0
+# imageio-ffmpeg>=0.5.1
+pip install --upgrade transformers accelerate diffusers imageio-ffmpeg 
+```
+
+2. 运行代码
+
+```
+import torch
+from diffusers import CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+
+prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
+image = load_image(image="input.jpg")
+pipe = CogVideoXImageToVideoPipeline.from_pretrained(
+    "THUDM/CogVideoX-5b-I2V",
+    torch_dtype=torch.bfloat16
+)
+
+pipe.enable_sequential_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
+video = pipe(
+    prompt=prompt,
+    image=image,
+    num_videos_per_prompt=1,
+    num_inference_steps=50,
+    num_frames=49,
+    guidance_scale=6,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).frames[0]
+
+export_to_video(video, "output.mp4", fps=8)
+```
+
+## Quantized Inference
+
+[PytorchAO](https://github.com/pytorch/ao) 和 [Optimum-quanto](https://github.com/huggingface/optimum-quanto/)
+可以用于对文本编码器、Transformer 和 VAE 模块进行量化，从而降低 CogVideoX 的内存需求。这使得在免费的 T4 Colab 或较小 VRAM 的
+GPU 上运行该模型成为可能！值得注意的是，TorchAO 量化与 `torch.compile` 完全兼容，这可以显著加快推理速度。
+
+```python
+# To get started, PytorchAO needs to be installed from the GitHub source and PyTorch Nightly.
+# Source and nightly installation is only required until the next release.
+
+import torch
+from diffusers import AutoencoderKLCogVideoX, CogVideoXTransformer3DModel, CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+from transformers import T5EncoderModel
+from torchao.quantization import quantize_, int8_weight_only
+
+quantization = int8_weight_only
+
+text_encoder = T5EncoderModel.from_pretrained("THUDM/CogVideoX-5b-I2V", subfolder="text_encoder", torch_dtype=torch.bfloat16)
+quantize_(text_encoder, quantization())
+
+transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-5b-I2V",subfolder="transformer", torch_dtype=torch.bfloat16)
+quantize_(transformer, quantization())
+
+vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-5b-I2V", subfolder="vae", torch_dtype=torch.bfloat16)
+quantize_(vae, quantization())
+
+# Create pipeline and run inference
+pipe = CogVideoXImageToVideoPipeline.from_pretrained(
+    "THUDM/CogVideoX-5b-I2V",
+    text_encoder=text_encoder,
+    transformer=transformer,
+    vae=vae,
+    torch_dtype=torch.bfloat16,
+)
+
+pipe.enable_model_cpu_offload()
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+
+prompt = "A little girl is riding a bicycle at high speed. Focused, detailed, realistic."
+image = load_image(image="input.jpg")
+video = pipe(
+    prompt=prompt,
+    image=image,
+    num_videos_per_prompt=1,
+    num_inference_steps=50,
+    num_frames=49,
+    guidance_scale=6,
+    generator=torch.Generator(device="cuda").manual_seed(42),
+).frames[0]
+
+export_to_video(video, "output.mp4", fps=8)
+```
+
+此外，这些模型可以通过使用PytorchAO以量化数据类型序列化并存储，从而节省磁盘空间。你可以在以下链接中找到示例和基准测试。
+
+- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
+- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
+
+## 深入研究
+
+欢迎进入我们的 [github](https://github.com/THUDM/CogVideo)，你将获得：
+
+1. 更加详细的技术细节介绍和代码解释。
+2. 提示词的优化和转换。
+3. 模型推理和微调的详细代码。
+4. 项目更新日志动态，更多互动机会。
+5. CogVideoX 工具链，帮助您更好的使用模型。
+6. INT8 模型推理代码。
+
+## 模型协议
+
+该模型根据 [CogVideoX LICENSE](LICENSE) 许可证发布。
+
+## 引用
+
+```
+@article{yang2024cogvideox,
+  title={CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer},
+  author={Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and others},
+  journal={arXiv preprint arXiv:2408.06072},
+  year={2024}
+}
+```

models/CogVideo/CogVideoX-5b-I2V/configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"image-to-video"}

models/CogVideo/CogVideoX-5b-I2V/model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "CogVideoXImageToVideoPipeline",
+  "_diffusers_version": "0.31.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "CogVideoXDDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "CogVideoXTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLCogVideoX"
+  ]
+}

models/CogVideo/CogVideoX-5b-I2V/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

models/CogVideo/CogVideoX-5b-I2V/transformer/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 32,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "out_channels": 16,
+  "patch_size": 2,
+  "sample_frames": 49,
+  "sample_height": 60,
+  "sample_width": 90,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": true,
+  "use_rotary_positional_embeddings": true
+}

models/CogVideo/CogVideoX-5b-I2V/transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e3060199c34a0d18892a19d687455f938b0ac3d2ea7d48f37cb4090e141965
+size 4992465072

models/CogVideo/CogVideoX-5b-I2V/transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8d0c62d366b0d9cc3476d2b21ca54afbecea154d54d923da120b2ec174c7e7
+size 4985800640

models/CogVideo/CogVideoX-5b-I2V/transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da91a0051da3f39caf10944b7c9aa66b14ddeffb37a25b087c49fc1692c1a361
+size 1272025856

models/CogVideo/CogVideoX-5b-I2V/vae/config.json

@@ -0,0 +1,39 @@
+{
+  "_class_name": "AutoencoderKLCogVideoX",
+  "_diffusers_version": "0.31.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_height": 480,
+  "sample_width": 720,
+  "scaling_factor": 0.7,
+  "shift_factor": null,
+  "temporal_compression_ratio": 4,
+  "up_block_types": [
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

models/CogVideo/CogVideoX-5b-I2V/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd47d57ad948ff80da0af0cb2e4dcdef65073aba59bccfd383ada9a7d1c02024
+size 431221142

models/CogVideo/CogVideoX-5b/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}

models/CogVideo/CogVideoX-5b/transformer/config.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "CogVideoXTransformer3DModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 16,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_layers": 42,
+  "out_channels": 16,
+  "patch_size": 2,
+  "sample_frames": 49,
+  "sample_height": 60,
+  "sample_width": 90,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "text_embed_dim": 4096,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_rotary_positional_embeddings": true
+}

models/CogVideo/CogVideoX-5b/transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7101be7e75631130cdf4a63ad798452bdce29716aaa47829e882dd384c398bf
+size 9925342208

models/CogVideo/CogVideoX-5b/transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe6c0e34a52c89f8ea8032a3a8a278a9ff1880dc70e1e6f3b840bcfd0396647
+size 1215340384

models/CogVideo/CogVideoX-5b/vae/config.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "AutoencoderKLCogVideoX",
+  "_diffusers_version": "0.32.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D",
+    "CogVideoXDownBlock3D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 3,
+  "norm_eps": 1e-06,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_height": 480,
+  "sample_width": 720,
+  "scaling_factor": 0.7,
+  "shift_factor": null,
+  "temporal_compression_ratio": 4,
+  "up_block_types": [
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D",
+    "CogVideoXUpBlock3D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false,
+  "invert_scale_latents": false
+}

models/CogVideo/CogVideoX-5b/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e
+size 862388596

models/CogVideo/CogVideoX-Fun-V1.1-5b-Control/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "CogVideoXDDIMScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": true,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": true,
+  "snr_shift_scale": 1.0,
+  "steps_offset": 0,
+  "timestep_spacing": "trailing",
+  "trained_betas": null
+}