Sync
Results
2
comments of
Sync
I used this code to finetune. ```Python import pretrainedmodels model_name = 'se_resnext101_32x4d' model = pretrainedmodels.__dict__[model_name](num_classes=1000, pretrained='imagenet') ```
Thank you for your opinion. but as the implementation, minimum value of duration is 1 because torch.clamp_min is applied. an extreme case, if you got duration [1.1, 1.1, 1.1, ....],...