RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 10.92 GiB total capacity; 10.28 GiB already allocated; 11.00 MiB free; 33.95 MiB cached)

vision
1

I tried to decrease the dataset but error remain same.

Creating data loaders
Traceback (most recent call last):
  File "main_gdt.py", line 504, in <module>
    main(args)
  File "main_gdt.py", line 225, in main
    writer=writer,
  File "main_gdt.py", line 274, in train_one_epoch
    feats1 = compute_feats(model, video, audio)
  File "/DATA/rani1/GDT-main/gdt_helper.py", line 18, in compute_feats
    feat_v, feat_a = model(video1, audio1) if feats1 is None else feats1
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/GDT-main/model.py", line 259, in forward
    img_features = self.video_network(img).squeeze()
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/GDT-main/model.py", line 187, in forward
    x = self.base(x).squeeze()
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/GDT-main/src/vmz.py", line 237, in forward
    x = self.layer3(x)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/GDT-main/src/vmz.py", line 113, in forward
    out = self.conv2(out)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/DATA/rani1/miniconda3/envs/GDT/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 480, in forward
    self.padding, self.dilation, self.groups)
2

please share your forward function. It’s hard to follow this.