Spaces:
Running
on
Zero
Running
on
Zero
File size: 8,726 Bytes
570db9a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
import torch
from torch import nn
import numpy as np
from typing import Tuple, Union
from .image_encoder import ModifiedResNet, VisionTransformer
from .text_encoder import LayerNorm, Transformer
class CLIP(nn.Module):
def __init__(
self,
embed_dim: int,
# vision
image_resolution: int,
vision_layers: Union[Tuple[int, int, int, int], int],
vision_width: int,
vision_patch_size: int,
# text
context_length: int,
vocab_size: int,
transformer_width: int,
transformer_heads: int,
transformer_layers: int
) -> None:
super().__init__()
self.embed_dim = embed_dim
self.image_resolution = image_resolution
self.vision_layers = vision_layers
self.vision_width = vision_width
self.vision_patch_size = vision_patch_size
self.context_length = context_length
self.vocab_size = vocab_size
self.transformer_width = transformer_width
self.transformer_heads = transformer_heads
self.transformer_layers = transformer_layers
if isinstance(vision_layers, (tuple, list)):
vision_heads = vision_width * 32 // 64
self.visual = ModifiedResNet(
layers=vision_layers,
output_dim=embed_dim,
heads=vision_heads,
input_resolution=image_resolution,
width=vision_width,
features_only=False,
)
else:
vision_heads = vision_width // 64
self.visual = VisionTransformer(
input_resolution=image_resolution,
patch_size=vision_patch_size,
width=vision_width,
layers=vision_layers,
heads=vision_heads,
output_dim=embed_dim,
features_only=False,
)
self.vision_heads = vision_heads
self.transformer = Transformer(
width=transformer_width,
layers=transformer_layers,
heads=transformer_heads,
attn_mask=self.build_attention_mask()
)
self.token_embedding = nn.Embedding(vocab_size, transformer_width)
self.positional_embedding = nn.Parameter(torch.empty(self.context_length, transformer_width))
self.ln_final = LayerNorm(transformer_width)
self.text_projection = nn.Parameter(torch.empty(transformer_width, embed_dim))
self.logit_scale = nn.Parameter(torch.ones([]) * np.log(1 / 0.07))
self.initialize_parameters()
def initialize_parameters(self):
nn.init.normal_(self.token_embedding.weight, std=0.02)
nn.init.normal_(self.positional_embedding, std=0.01)
if isinstance(self.visual, ModifiedResNet):
if self.visual.attnpool is not None:
std = self.visual.attnpool.c_proj.in_features ** -0.5
nn.init.normal_(self.visual.attnpool.q_proj.weight, std=std)
nn.init.normal_(self.visual.attnpool.k_proj.weight, std=std)
nn.init.normal_(self.visual.attnpool.v_proj.weight, std=std)
nn.init.normal_(self.visual.attnpool.c_proj.weight, std=std)
for resnet_block in [self.visual.layer1, self.visual.layer2, self.visual.layer3, self.visual.layer4]:
for name, param in resnet_block.named_parameters():
if name.endswith("bn3.weight"):
nn.init.zeros_(param)
proj_std = (self.transformer.width ** -0.5) * ((2 * self.transformer.layers) ** -0.5)
attn_std = self.transformer.width ** -0.5
fc_std = (2 * self.transformer.width) ** -0.5
for block in self.transformer.resblocks:
nn.init.normal_(block.attn.in_proj_weight, std=attn_std)
nn.init.normal_(block.attn.out_proj.weight, std=proj_std)
nn.init.normal_(block.mlp.c_fc.weight, std=fc_std)
nn.init.normal_(block.mlp.c_proj.weight, std=proj_std)
if self.text_projection is not None:
nn.init.normal_(self.text_projection, std=self.transformer.width ** -0.5)
def build_attention_mask(self):
# lazily create causal attention mask, with full attention between the vision tokens
# pytorch uses additive attention mask; fill with -inf
mask = torch.empty(self.context_length, self.context_length)
mask.fill_(float("-inf"))
mask.triu_(1) # zero out the lower diagonal
return mask
@property
def dtype(self):
return self.visual.conv1.weight.dtype
def encode_image(self, image):
return self.visual(image.type(self.dtype))
def encode_text(self, text):
x = self.token_embedding(text).type(self.dtype) # [batch_size, n_ctx, d_model]
x = x + self.positional_embedding.type(self.dtype)
x = x.permute(1, 0, 2) # NLD -> LND
x = self.transformer(x)
x = x.permute(1, 0, 2) # LND -> NLD
x = self.ln_final(x).type(self.dtype)
# x.shape = [batch_size, n_ctx, transformer.width]
# take features from the eot embedding (eot_token is the highest number in each sequence)
x = x[torch.arange(x.shape[0]), text.argmax(dim=-1)] @ self.text_projection
return x
def forward(self, image, text):
image_features = self.encode_image(image)
text_features = self.encode_text(text)
# normalized features
image_features = image_features / image_features.norm(dim=1, keepdim=True)
text_features = text_features / text_features.norm(dim=1, keepdim=True)
# cosine similarity as logits
logit_scale = self.logit_scale.exp()
logits_per_image = logit_scale * image_features @ text_features.t()
logits_per_text = logits_per_image.t()
# shape = [global_batch_size, global_batch_size]
return logits_per_image, logits_per_text
def convert_weights(model: nn.Module):
"""Convert applicable model parameters to fp16"""
def _convert_weights_to_fp16(l):
if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Linear)):
l.weight.data = l.weight.data.half()
if l.bias is not None:
l.bias.data = l.bias.data.half()
if isinstance(l, nn.MultiheadAttention):
for attr in [*[f"{s}_proj_weight" for s in ["in", "q", "k", "v"]], "in_proj_bias", "bias_k", "bias_v"]:
tensor = getattr(l, attr)
if tensor is not None:
tensor.data = tensor.data.half()
for name in ["text_projection", "proj"]:
if hasattr(l, name):
attr = getattr(l, name)
if attr is not None:
attr.data = attr.data.half()
model.apply(_convert_weights_to_fp16)
def build_model(state_dict: dict):
vit = "visual.proj" in state_dict
if vit:
vision_width = state_dict["visual.conv1.weight"].shape[0]
vision_layers = len([k for k in state_dict.keys() if k.startswith("visual.") and k.endswith(".attn.in_proj_weight")])
vision_patch_size = state_dict["visual.conv1.weight"].shape[-1]
grid_size = round((state_dict["visual.positional_embedding"].shape[0] - 1) ** 0.5)
image_resolution = vision_patch_size * grid_size
else:
counts: list = [len(set(k.split(".")[2] for k in state_dict if k.startswith(f"visual.layer{b}"))) for b in [1, 2, 3, 4]]
vision_layers = tuple(counts)
vision_width = state_dict["visual.layer1.0.conv1.weight"].shape[0]
output_width = round((state_dict["visual.attnpool.positional_embedding"].shape[0] - 1) ** 0.5)
vision_patch_size = None
assert output_width ** 2 + 1 == state_dict["visual.attnpool.positional_embedding"].shape[0]
image_resolution = output_width * 32
embed_dim = state_dict["text_projection"].shape[1]
context_length = state_dict["positional_embedding"].shape[0]
vocab_size = state_dict["token_embedding.weight"].shape[0]
transformer_width = state_dict["ln_final.weight"].shape[0]
transformer_heads = transformer_width // 64
transformer_layers = len(set(k.split(".")[2] for k in state_dict if k.startswith("transformer.resblocks")))
model = CLIP(
embed_dim,
image_resolution, vision_layers, vision_width, vision_patch_size,
context_length, vocab_size, transformer_width, transformer_heads, transformer_layers
)
for key in ["input_resolution", "context_length", "vocab_size"]:
if key in state_dict:
del state_dict[key]
convert_weights(model)
model.load_state_dict(state_dict, strict=False)
return model.eval()
|