pytorch-video-recognition
pytorch-video-recognition copied to clipboard
jfzhang95
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
Thanks for the great work! Is the R3D model based on resnet-18 with the "basic building block"? It seems so, but want to confirm if it is the exactly same...
Hai @jfzhang95 @sdxass I have tried the UCF dataset with X labels and its results are too good. Now how to detect an action for a custom dataset (own dataset)?...
How do I load the model and fine tune it to the places-365 dataset for scene recognition?
When I downloaded the dataset,i run python train.py, But the terminal does not output any information, has been stagnant, what is the reason? 
D:\anaconda3\envs\pytorch114\lib\site-packages\torch\optim\lr_scheduler.py:134: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.st File "train.py", line 202, in train_model() File "train.py", line 137, in train_model loss = criterion(outputs, labels) File "D:\anaconda3\envs\pytorch114\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl...
Traceback (most recent call last): File "C:\MyWorkspace\pycharm_workapce\github\pytorch-video-recognition\train.py", line 202, in train_model() File "C:\MyWorkspace\pycharm_workapce\github\pytorch-video-recognition\train.py", line 97, in train_model train_dataloader = DataLoader(VideoDataset(dataset=dataset, split='train',clip_len=16), batch_size=20, shuffle=True, num_workers=4) File "C:\MyWorkspace\pycharm_workapce\github\pytorch-video-recognition\dataloaders\dataset.py", line 41, in __init__...
