how can I fix RuntimeError: CUDA error: out of memory

[northmachine]

loading model ./resnext-101-kinetics.pth
resnext-101
resnext-101
./resnext-101-kinetics.pth
./videos/video1.mp4
ffmpeg version 4.1-static https://johnvansickle.com/ffmpeg/ Copyright (c) 2000-2018 the FFmpeg developers
built with gcc 6.3.0 (Debian 6.3.0-18+deb9u1) 20170516
configuration: --enable-gpl --enable-version3 --enable-static --disable-debug --disable-ffplay --disable-indev=sndio --disable-outdev=sndio --cc=gcc-6 --enable-fontconfig --enable-frei0r --enable-gnutls --enable-gray --enable-libaom --enable-libfribidi --enable-libass --enable-libvmaf --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-librubberband --enable-libsoxr --enable-libspeex --enable-libvorbis --enable-libopus --enable-libtheora --enable-libvidstab --enable-libvo-amrwbenc --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg
libavutil 56. 22.100 / 56. 22.100
libavcodec 58. 35.100 / 58. 35.100
libavformat 58. 20.100 / 58. 20.100
libavdevice 58. 5.100 / 58. 5.100
libavfilter 7. 40.101 / 7. 40.101
libswscale 5. 3.100 / 5. 3.100
libswresample 3. 3.100 / 3. 3.100
libpostproc 55. 3.100 / 55. 3.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from './videos/video1.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf56.13.100
Duration: 00:00:22.00, start: 0.000000, bitrate: 408 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 320x240 [SAR 15:16 DAR 5:4], 304 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
handler_name : VideoHandler
Stream #0:1(und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 96 kb/s (default)
Metadata:
handler_name : SoundHandler
Stream mapping:
Stream #0:0 -> #0:0 (h264 (native) -> mjpeg (native))
Press [q] to stop, [?] for help
[swscaler @ 0x6972a40] deprecated pixel format used, make sure you did set range correctly
Output #0, image2, to 'tmp/image_%05d.jpg':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.20.100
Stream #0:0(und): Video: mjpeg, yuvj420p(pc), 320x240 [SAR 15:16 DAR 5:4], q=2-31, 200 kb/s, 25 fps, 25 tbn, 25 tbc (default)
Metadata:
handler_name : VideoHandler
encoder : Lavc58.35.100 mjpeg
Side data:
cpb: bitrate max/min/avg: 0/0/200000 buffer size: 0 vbv_delay: -1
frame= 550 fps=0.0 q=24.8 Lsize=N/A time=00:00:22.00 bitrate=N/A speed=49.2x
video:2103kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/classify.py:25: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
inputs = Variable(inputs, volatile=True)
Traceback (most recent call last):
File "/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/main.py", line 61, in
result = classify_video('tmp', input_file, class_names, model, opt)
File "/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/classify.py", line 26, in classify_video
outputs = model(inputs)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 121, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/models/resnext.py", line 127, in forward
x = self.layer1(x)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/models/resnext.py", line 58, in forward
out = self.conv3(out)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/northmachine/.conda/envs/tensorflow-gpu/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 421, in forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDA error: out of memory

I run with --input ./input --video_root ./videos --output ./output.json --model ./resnext-101-kinetics.pth --mode score --model_depth 101 --model_name resnext --resnet_shortcut B --resnext_cardinality 32 --batch_size 128
I use a gtx1060 3G, is there any parameter I miss

[shiyonglian]

降低batchsize的数量

[suxb201]

/home/northmachine/Desktop/video-classification-3d-cnn-pytorch-master/classify.py:25: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
inputs = Variable(inputs, volatile=True)

You need to add torch.no_grad():