MqLeet
commented
3 days ago Hi @chaserRen , I run your code on the video generated by OpenAI's Sora, and everything runs well.
In the Outputs Info, I notice that the bug occurs in torchvision.io.write_video. What's your version of torchvision, pyav?
Please check your dependency's version. Our dev environment is:
Package Version
------------------------ ------------------
absl-py 2.1.0
accelerate 0.30.0
addict 2.4.0
antlr4-python3-runtime 4.9.3
attrs 23.2.0
av 12.0.0
bitsandbytes 0.42.0
black 24.2.0
boto3 1.34.62
botocore 1.34.62
certifi 2024.2.2
charset-normalizer 3.3.2
click 8.1.7
cloudpickle 3.0.0
contourpy 1.2.0
cycler 0.12.1
Cython 3.0.9
decorator 4.4.2
decord 0.6.0
detectron2 0.6
dreamsim 0.1.3
easydict 1.13
einops 0.7.0
exceptiongroup 1.2.0
facexlib 0.3.0
fairscale 0.4.13
ffmpeg 1.4
filelock 3.13.1
filterpy 1.4.5
fonttools 4.49.0
fsspec 2024.2.0
ftfy 6.1.3
future 1.0.0
fvcore 0.1.5.post20221221
grpcio 1.62.1
h11 0.14.0
huggingface-hub 0.21.4
hydra-core 1.3.2
idna 3.6
imageio 2.34.0
imageio-ffmpeg 0.4.9
imgaug 0.4.0
importlib_metadata 7.0.2
importlib_resources 6.3.0
iopath 0.1.9
Jinja2 3.1.3
jmespath 1.0.1
joblib 1.3.2
kiwisolver 1.4.5
lazy_loader 0.3
llvmlite 0.42.0
lmdb 1.4.1
lvis 0.5.3
Markdown 3.5.2
MarkupSafe 2.1.5
matplotlib 3.8.3
moviepy 1.0.3
mypy-extensions 1.0.0
networkx 3.2.1
numba 0.59.0
numpy 1.26.4
nvidia-cublas-cu11 11.10.3.66
nvidia-cuda-nvrtc-cu11 11.7.99
nvidia-cuda-runtime-cu11 11.7.99
nvidia-cudnn-cu11 8.5.0.96
omegaconf 2.3.0
open-clip-torch 2.24.0
openai-clip 1.0.1
opencv-python 4.9.0.80
outcome 1.3.0.post0
packaging 24.0
pandas 2.2.1
pathspec 0.12.1
peft 0.1.0
pillow 10.2.0
pip 23.3.1
platformdirs 4.2.0
portalocker 2.8.2
prettytable 3.10.0
proglog 0.1.10
protobuf 5.26.0
psutil 5.9.8
pyav 12.0.4
pycocoevalcap 1.2
pycocotools 2.0.7
pyecharts 2.0.5
pyiqa 0.1.10
pyparsing 3.1.2
PySocks 1.7.1
python-dateutil 2.9.0.post0
pytz 2024.1
PyYAML 6.0.1
regex 2023.12.25
requests 2.31.0
s3transfer 0.10.0
safetensors 0.4.2
scenedetect 0.6.3
scikit-image 0.22.0
scikit-learn 1.4.1.post1
scipy 1.12.0
selenium 4.19.0
sentencepiece 0.2.0
setuptools 68.2.2
shapely 2.0.3
simplejson 3.19.2
six 1.16.0
snapshot-selenium 0.0.2
sniffio 1.3.1
sortedcontainers 2.4.0
tabulate 0.9.0
tensorboard 2.16.2
tensorboard-data-server 0.7.2
termcolor 2.4.0
threadpoolctl 3.3.0
tifffile 2024.2.12
timm 0.9.16
tokenizers 0.13.3
tomli 2.0.1
torch 1.13.1
torchvision 0.14.1
tqdm 4.66.2
transformers 4.33.2
trio 0.25.0
trio-websocket 0.11.1
typing_extensions 4.10.0
tzdata 2024.1
urllib3 1.26.18
wcwidth 0.2.13
Werkzeug 3.0.1
wheel 0.41.2
wsproto 1.2.0
yacs 0.1.8
yapf 0.40.2
zipp 3.18.0
chaserRen
Here is my code:
from vbench2_beta_long.utils import split_video_into_scenes video_path = "video_files/inputs/_b2ZthqQG24.mp4" # 2分15秒视频 output_dir = "video_files/outputs/_b2ZthqQG24/" threshold = 20 # 2秒切割 split_video_into_scenes(video_path, output_dir, threshold)
Outputs is as following: (renzhifei) (base) [qa-caif-cicd@SH-IDCA1404-10-140-54-48 VBench]$ /home/qa-caif-cicd/anaconda3/envs/renzhifei/bin/python /home/qa-caif-cicd/renzhifei/VBench/split_video.py 2024-07-03 15:15:49,146 - pyscenedetect - INFO - Downscale factor set to 5, effective resolution: 256 x 144 Detected: 0 | Progress: 0%| | 0/3384 [00:00<?, ?frames/s]2024-07-03 15:15:49,149 - pyscenedetect - INFO - Detecting scenes... Detected: 12 | Progress: 100%|███████████████████████████████████████████████| 3384/3384 [00:06<00:00, 540.68frames/s] Traceback (most recent call last): File "/home/qa-caif-cicd/renzhifei/VBench/split_video.py", line 6, in
split_video_into_scenes(video_path, output_dir, threshold)
File "/home/qa-caif-cicd/renzhifei/VBench/vbench2_beta_long/utils.py", line 89, in split_video_into_scenes
save_video_by_scene_list(video_path, video_name, scene_list, output_dir=output_dir)
File "/home/qa-caif-cicd/renzhifei/VBench/vbench2_beta_long/utils.py", line 120, in save_video_by_scene_list
write_video(output_filename, current_scene_frames, fps=fps)
File "/home/qa-caif-cicd/anaconda3/envs/renzhifei/lib/python3.8/site-packages/torchvision/io/video.py", line 135, in write_video
container.mux(packet)
File "av/container/output.pyx", line 207, in av.container.output.OutputContainer.mux
File "av/container/output.pyx", line 213, in av.container.output.OutputContainer.mux_one
File "av/container/output.pyx", line 168, in av.container.output.OutputContainer.start_encoding
File "av/error.pyx", line 326, in av.error.err_check
av.error.FileNotFoundError: [Errno 2] No such file or directory
video can be download on s3 : s3://xyz-process-2/video/ar/video/v001/_b2ZthqQG24.mp4
information of the video: "format": "MP4", "codec": "h264", "resolution": "720x1280", "frame_rate": "25/1", "duration": "135.360000"