Open YTHmamba opened 2 years 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?
Hello, I have also encountered the same problem. Do you know why
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?