Open YTHmamba opened 1 year ago
I found that when fine-tuning UCF101, split1 partition was used to verify that the number in the dataset was 11349 instead of 3783, and why was batchsize opt.batch_size // opt.n_val_samples?
I found that when fine-tuning UCF101, split1 partition was used to verify that the number in the dataset was 11349 instead of 3783, and why was batchsize opt.batch_size // opt.n_val_samples?