search

open-mmlab / mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
https://mmaction2.readthedocs.io
Apache License 2.0
4.28k stars 1.25k forks source link

train ava owner class error #866

Closed Deep-learning999 closed 3 years ago

Deep-learning999 commented 3 years ago

Before raising a question, you may need to check the following listed items.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. I have read the FAQ documentation but cannot get the expected help.
Traceback (most recent call last):
  File "tools/train.py", line 197, in <module>
    main()
  File "tools/train.py", line 185, in main
    train_model(
  File "/hy-nas/12/mm2/mmaction/apis/train.py", line 163, in train_model
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs, **runner_kwargs)
  File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/epoch_based_runner.py", line 125, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/epoch_based_runner.py", line 47, in train
    for i, data_batch in enumerate(self.data_loader):
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 517, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/dataloader.py", line 1225, in _process_data
    data.reraise()
  File "/usr/local/lib/python3.8/dist-packages/torch/_utils.py", line 429, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/hy-nas/12/mm2/mmaction/datasets/base.py", line 285, in __getitem__
    return self.prepare_train_frames(idx)
  File "/hy-nas/12/mm2/mmaction/datasets/ava_dataset.py", line 289, in prepare_train_frames
    return self.pipeline(results)
  File "/hy-nas/12/mm2/mmaction/datasets/pipelines/compose.py", line 41, in __call__
    data = t(data)
  File "/hy-nas/12/mm2/mmaction/datasets/pipelines/loading.py", line 1135, in __call__
    img_bytes = self.file_client.get(filepath)
  File "/usr/local/lib/python3.8/dist-packages/mmcv/fileio/file_client.py", line 306, in get
    return self.client.get(filepath)
  File "/usr/local/lib/python3.8/dist-packages/mmcv/fileio/file_client.py", line 184, in get
    with open(filepath, 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/hy-nas/12/mm2/data/rawframes/HV0H6oc4Kvs/img_24119.jpg'
Deep-learning999 commented 3 years ago

why have img_24119.jpg

Deep-learning999 commented 3 years ago

@kennymckormick

floriculture commented 3 years ago

@Deep-learning999 Sorry to disturb you, I saw that you successfully detected the pink ball in the TTNet project. In that issue, I tried to contact you, but you may not notice. So how do you train the model? I hope you can help me

innerlee commented 3 years ago

@Deep-learning999 How many frames are there in /hy-nas/12/mm2/data/rawframes/HV0H6oc4Kvs/? What is the start index of the frames?

innerlee commented 3 years ago

This thread might related https://github.com/open-mmlab/mmaction2/issues/806#issuecomment-838418208

Deep-learning999 commented 3 years ago

I found that training a few of the 80 categories requires all 299 mini video frames to be extracted. If you use mini video to train, you need to change some files.

floriculture commented 3 years ago

@Deep-learning999 Hello, sir! Could you share your training experience? It's very important for me, plz.

Deep-learning999 commented 3 years ago

Can ffmpeg's frame drawing be able to specify the shortest side,​Come to the size of the coaxial data set, how should the command line be written

Deep-learning999 commented 3 years ago

@kennymckormick

Deep-learning999 commented 3 years ago

@Deep-learning999 Hello, sir! Could you share your training experience? It's very important for me, plz.

That project is a pit, it is not recommended to continue research

kennymckormick commented 3 years ago

why have img_24119.jpg

Each 15min clip of AVA videos will generate 900s * 30fps = 27000 frames

kennymckormick commented 3 years ago

Can ffmpeg's frame drawing be able to specify the shortest side,​Come to the size of the coaxial data set, how should the command line be written

AFAIK, you can not specify the shortest side with ffmpeg. I will first look at the resolution of the video and specify either the height or the width.

floriculture commented 3 years ago

Sir, you have successfully positioned table tennis with pink in the picture you released. I can't even do this step. I really hope you could share your training experience.

Deep-learning999 commented 3 years ago

when bash cut_videos.sh The following prompts appear

[mov,mp4,m4a,3gp,3g2,mj2 @ 0x556fd9990a20] moov atom not found ../../../data/ava/videos/26V9UzqSguo.mp4: Invalid data found when processing input ffmpeg version 3.4.8-0ubuntu0.2 Copyright (c) 2000-2020 the FFmpeg developers built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04) configuration: --prefix=/usr --extra-version=0ubuntu0.2 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared libavutil 55. 78.100 / 55. 78.100 libavcodec 57.107.100 / 57.107.100 libavformat 57. 83.100 / 57. 83.100 libavdevice 57. 10.100 / 57. 10.100 libavfilter 6.107.100 / 6.107.100 libavresample 3. 7. 0 / 3. 7. 0 libswscale 4. 8.100 / 4. 8.100 libswresample 2. 9.100 / 2. 9.100 libpostproc 54. 7.100 / 54. 7.100 Input #0, matroska,webm, from '../../../data/ava/videos/2FIHxnZKg6A.webm': Metadata: encoder : Lavf56.40.101 Duration: 01:15:36.94, start: -0.007000, bitrate: 429 kb/s Stream #0:0(eng): Video: vp9 (Profile 0), yuv420p(tv), 640x480, SAR 1:1 DAR 4:3, 25 fps, 25 tbr, 1k tbn, 1k tbc (default) Stream #0:1(eng): Audio: opus, 48000 Hz, stereo, fltp (default) Codec AVOption preset (Configuration preset) specified for output file #0 (../../../data/ava/videos_15min/2FIHxnZKg6A.webm) has not been used for any stream. The most likely reason is either wrong type (e.g. a video option with no video streams) or that it is a private option of some encoder which was not actually used for any stream. Stream mapping: Stream #0:0 -> #0:0 (vp9 (native) -> vp9 (libvpx-vp9)) Stream #0:1 -> #0:1 (opus (native) -> opus (libopus)) Press [q] to stop, [?] for help [libopus @ 0x5632ecdbfc20] No bit rate set. Defaulting to 96000 bps. [libvpx-vp9 @ 0x5632ecdbd900] v1.7.0

Output #0, webm, to '../../../data/ava/videos_15min/2FIHxnZKg6A.webm': Metadata: encoder : Lavf57.83.100 Stream #0:0(eng): Video: vp9 (libvpx-vp9), yuv420p, 640x480 [SAR 1:1 DAR 4:3], q=-1--1, 200 kb/s, 30 fps, 1k tbn, 30 tbc (default) Metadata: encoder : Lavc57.107.100 libvpx-vp9 Side data: cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1 Stream #0:1(eng): Audio: opus (libopus), 48000 Hz, stereo, flt, 96 kb/s (default) Metadata: encoder : Lavc57.107.100 libopus frame= 4394 fps= 30 q=0.0 size= 8596kB time=00:02:56.29 bitrate= 399.4kbits/s speed=1.19x

Deep-learning999 commented 3 years ago

@kennymckormick

floriculture commented 3 years ago

@Deep-learning999 Sir, please share your training experience about TTNet. This is very important for me. I hope you can solve your own problems. look forward to your reply.

Deep-learning999 commented 3 years ago

Solved it myself

floriculture commented 3 years ago

@Deep-learning999 Hello! I sincerely hope you can share your experience, plz. I have been troubled by this problem for many days.