Siladittya Manna
Siladittya Manna
Did you succeed in reproducing the results I am also facing the same problems. However, I used VGG-13 net instead of the one used in the paper.
@sansinghsanjay 0 is the output label for the unknown images, after openmax the output labels of the known images will be [1-10]. If that is not the issue, then I...
When using callback **LearningRateScheduler**, the `AttributeError : 'AccumOptimizer' object has no attribute 'lr'` occurs. This error can only be solved by replacing all occurences of `lr` by `learning_rate` and making...
Also this error `RuntimeError: Cannot set 'iterations' to a new Variable after the Optimizer weights have been created` is thrown when saving the model after each epoch. To avoid this...
super(AccumOptimizer,self).__init__(name='AccumOptimizer',**kwargs)
This modified LARS code was tested on CIFAR-10 with ResNet-50 backbone. Linear Evaluation Test Accuracy is ~85% after 100 epochs.
@Ektagavas Hi, I used a batch size of 64, LR 0.2, and temperature 0.5. 100 epochs for contrastive learning. Also, I used a pre-trained encoder. The results may differ if...
@Ektagavas I used `torchvision.models.resnet50(pretrained = True)`
In relation to the above question, I have tried using `sobel` from `kornia.filter` but I haven't been able to replicate the results reported in the extended version. Any information about...
@cheng-01037 Did you use a fixed convolutional kernel? A little nudge in the right direction will be greatly appreciated.