How to get gradients with respect to input and change input (rather than trainable vars) to minimize loss

[Homa]

my problem was solved. thanks for your guidance.
I used from it:

How to add cosine similarity score in Cross Entropy Loss

Since you would like to maximize the cosine similarity, I would go with the first approach, as in the worst case, you’ll add 0.01 * 2 to the loss and in the best (trained) case, it will be 1 - 1 = 0. Here is a small dummy example of just rotating tensors: x = torch.tensor([[1., 1.]], requires_grad=True) y = torch.tensor([[-1, 0.]]) criterion = nn.CosineSimilarity() optimizer = torch.optim.SGD([x], lr=1.) for _ in range(20): optimizer.zero_grad() loss = 1. - criterion(x, y) loss.ba…