Muhammad Bilal Shaikh

what is the correct shape for TSM expected?

1

params = [] for child in list(model.children())[:-1]: params.extend(list(child.parameters())) model.avg_pool = nn.Identity() print(len(X),X.shape) # shape of x: [N, T, C, H, W] d = torch.rand((64,8,3,256,256),dtype=torch.float32).to(device) preds = model(d,8) File "/home/muhammadbsheikh/anaconda3/envs/open-mmlab2/lib/python3.7/site-packages/torch/nn/functional.py", line...

Not running on official splits without validation

1

for ucf101 I have modified the preprocess code and generated official splits But this code is producing below error. Need help. pytorch-video-recognition/dataloaders/dataset.py", line 294, in crop time_index = np.random.randint(buffer.shape[0] -...