Hi,
Is the magic number[100] in new_weight a class number?
new_weight = torch.zeros(100, d_emb)
for i in range(100):
tmp = output_stack[target_stack == (i + 100)].mean(0) if not random else torch.randn(d_emb, device=device)
new_weight[i] = tmp / tmp.norm(p=2)
Hi, Is the magic number[100] in new_weight a class number? new_weight = torch.zeros(100, d_emb) for i in range(100): tmp = output_stack[target_stack == (i + 100)].mean(0) if not random else torch.randn(d_emb, device=device) new_weight[i] = tmp / tmp.norm(p=2)