Hi, I wonder if this implementation is correct?

When I run the code with softmax, I get weights like this:

tensor([[0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [1.7646, 1.7646, 1.7646, 1.7646, 1.7646],
        [1.7646, 1.7646, 1.7646, 1.7646, 1.7646],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824],
        [0.8824, 0.8824, 0.8824, 0.8824, 0.8824]])

where each sample enjoin the same weights.

This is weird, right? According to the original paper, we should have different weight for each class (column), right?

Hi @vandit15,

Thanks for sharing your code.

In line 73, weights = weights / np.sum(weights) * no_of_classes, why is no_of_classes included here to normalise the weights? Any help would be thankful.

Thanks

Thanks for sharing code.I have modified the code. I want to calculate the multivariate classification. The code is as follows. I can always report errors. I wonder if you have tried it?

pred = logits.log_softmax(dim=1)
cb_loss = F.cross_etropy(input=pred, target=labels, weights=weights)

Thanks.

thank you for sharing Pytorch implementation, I was wondering if we need to specify "reduction="none"" for the "binary_cross_entropy_with_logits" function here since we are going to do weighting and reduction on our own later? https://github.com/vandit15/Class-balanced-loss-pytorch/blob/fb634a6e42ecaa2e3d7e974cd124180c679da6c7/class_balanced_loss.py#L35

https://github.com/vandit15/Class-balanced-loss-pytorch/blob/91a7832d86c8b66576018e5377df391424b3fd11/class_balanced_loss.py#L87

It seems that you forgot to include weights for sigmoid loss

https://github.com/vandit15/Class-balanced-loss-pytorch/blob/921ccb8725b1eb0903b2c22a1a752a594fcae138/class_balanced_loss.py#L28

should be alpha: A float tensor of size [num_classes]

Hi, thanks for your code sharing!

I am now trying to understand how do you implement and I have something want to discuss.

In your main function you have provide us with a toy example, I noticed that you have set samples_per_cls equals [2,3,1,2,2] which indicates label 0 has 2 samples , am i right? But you have random labels,so should I count samples of each class every times ?

I would be appreciated if you can answer my question as quick as possible. Have a good day!

the keyword had a typo: 'weight' instead of 'weights'. in case weights requires grads, it needs to be detached first as BCEwithlogits is not implemented for grad tracked tensor

Instead calculating a weight for each batch, applying to class using pos_weight argument in torch.nn.BCELoss(pos_weights=weights)

Simply, https://github.com/vandit15/Class-balanced-loss-pytorch/blob/master/class_balanced_loss.py#L71-L82

Are those line of codes same with

effective_num = 1.0 - np.power(beta, samples_per_cls)
weights = (1.0 - beta) / np.array(effective_num)
weights = weights / np.sum(weights) * no_of_classes
loss = torch.nn.BCELoss(reduction='mean', pos_weight=weights)

this code?