File size: 5,885 Bytes
1fea0a0 |
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 |
import torch
import os
from ChatUniVi.constants import *
from ChatUniVi.conversation import conv_templates, SeparatorStyle
from ChatUniVi.model.builder import load_pretrained_model
from ChatUniVi.utils import disable_torch_init
from ChatUniVi.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image
from decord import VideoReader, cpu
import numpy as np
def _get_rawvideo_dec(video_path, image_processor, max_frames=MAX_IMAGE_LENGTH, image_resolution=224, video_framerate=1, s=None, e=None):
# speed up video decode via decord.
video_mask = np.zeros(max_frames, dtype=np.int64)
max_video_length = 0
# T x 3 x H x W
video = np.zeros((max_frames, 3, image_resolution, image_resolution), dtype=np.float64)
if s is None:
start_time, end_time = None, None
else:
start_time = int(s)
end_time = int(e)
start_time = start_time if start_time >= 0. else 0.
end_time = end_time if end_time >= 0. else 0.
if start_time > end_time:
start_time, end_time = end_time, start_time
elif start_time == end_time:
end_time = start_time + 1
if os.path.exists(video_path):
vreader = VideoReader(video_path, ctx=cpu(0))
else:
print(video_path)
raise FileNotFoundError
fps = vreader.get_avg_fps()
f_start = 0 if start_time is None else int(start_time * fps)
f_end = int(min(1000000000 if end_time is None else end_time * fps, len(vreader) - 1))
num_frames = f_end - f_start + 1
if num_frames > 0:
# T x 3 x H x W
sample_fps = int(video_framerate)
t_stride = int(round(float(fps) / sample_fps))
all_pos = list(range(f_start, f_end + 1, t_stride))
if len(all_pos) > max_frames:
sample_pos = [all_pos[_] for _ in np.linspace(0, len(all_pos) - 1, num=max_frames, dtype=int)]
else:
sample_pos = all_pos
patch_images = [Image.fromarray(f) for f in vreader.get_batch(sample_pos).asnumpy()]
patch_images = torch.stack([image_processor.preprocess(img, return_tensors='pt')['pixel_values'][0] for img in patch_images])
slice_len = patch_images.shape[0]
max_video_length = max_video_length if max_video_length > slice_len else slice_len
if slice_len < 1:
pass
else:
video[:slice_len, ...] = patch_images
return patch_images, video_mask
else:
print("video path: {} error.".format(video_path))
video_mask[:max_video_length] = [1] * max_video_length
return torch.from_numpy(video), video_mask
if __name__ == '__main__':
# Model
model_path = ${model_path}
video_path = ${video_path}
max_frames = ${max_frames}
qs = "Describe the video."
conv_mode = "simple"
temperature = 0.2
top_p = None
num_beams = 1
disable_torch_init()
model_path = os.path.expanduser(model_path)
model_name = "ChatUniVi"
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name)
mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False)
mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True)
if mm_use_im_patch_token:
tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
if mm_use_im_start_end:
tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
model.resize_token_embeddings(len(tokenizer))
vision_tower = model.get_vision_tower()
if not vision_tower.is_loaded:
vision_tower.load_model()
image_processor = vision_tower.image_processor
if model.config.config["use_cluster"]:
for n, m in model.named_modules():
m = m.to(dtype=torch.bfloat16)
# Check if the video exists
if video_path is not None:
video_frames, _ = _get_rawvideo_dec(video_path, image_processor, max_frames=max_frames)
cur_prompt = qs
if model.config.mm_use_im_start_end:
qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN * MAX_IMAGE_LENGTH + DEFAULT_IM_END_TOKEN + '\n' + qs
else:
qs = DEFAULT_IMAGE_TOKEN * MAX_IMAGE_LENGTH + '\n' + qs
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], qs)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(
0).cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=video_frames.half().cuda(),
do_sample=True,
temperature=temperature,
top_p=top_p,
num_beams=num_beams,
output_scores=True,
return_dict_in_generate=True,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
output_ids = output_ids.sequences
input_token_len = input_ids.shape[1]
n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
if n_diff_input_output > 0:
print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
outputs = outputs.strip()
if outputs.endswith(stop_str):
outputs = outputs[:-len(stop_str)]
outputs = outputs.strip()
print(outputs) |