Paschalis Melissas
Results
2
issues of
Paschalis Melissas
During training, a single line for each epoch is printed, nevertheless the loss is not printed. Neither during validation. For the validation I managed to print the metrics (ap,recall,mAP) for...
``` loss = F.cross_entropy(out, pred_1.to(self.device)) grads = torch.autograd.grad(loss, var_emb)[0].data.cpu() ``` In my understanding both **out** and **pred_1** hold the same passage of the unlabeled samples through the model, but the...