video-classification-3d-cnn-pytorch
video-classification-3d-cnn-pytorch copied to clipboard
resnext-101-64f-kinetics-hmdb51_split1.pth model question?
when I use resnext-101-64f-kinetics-hmdb51_split1.pth model, dataset is hmdb51. should I choose which parameter for opt ?
for example : mode = score batch_size = 32 n_threads = 4 model_name=resnext model_depth=101 resnet_shortcut='A' resnext_cardinality = 32 is ok?
Yes, it's OK. In addition, you have to change sample_duration in main.py to use 64 frame inputs. https://github.com/kenshohara/video-classification-3d-cnn-pytorch/blob/master/main.py#L19