memo
memo copied to clipboard
zhangmarvin
hello，i want to use memo to test coco. After calculating the marginal entropy, starting backpropagation to calculate the gradient, it will report an error here in loss.backward() Error detected in...
I am verifying the effect of pairwise cross entropy, and implement it with the following code: ```python class SoftCrossEntropyLoss(nn.Module): def __init__(self): super().__init__() def forward(self, y_hat, y): p = F.log_softmax(y_hat, 0)...
In the /test_adapt.py line 54 `net.load_state_dict(ckpt['state_dict'])` It means that adpat and predict on a image, but don't save the parameters?
