"labels": [3, 3, 1, 3, 3, 0, 1, 0, 0, 1, 0, 3, 3, 3, 3, 3, 2, 1, 3, 3, 3, 0, 1, 3, 3, 3], "logits": [-0.7609173059463501, -0.826463520526886, -1.4745299816131592, -2.041656017303467, -2.14640212059021, -2.262834310531616, -2.360511064529419, -2.403244972229004, -2.417006...
PyTorch version: 2.4.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS: Ubuntu 22.04.4 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version: Could not collect CMake version: Could not collect Libc version:...
top_two_logits, top_two_classes = torch.topk(adv_logits, 2) target_class_logit = adv_logits[target_class] if top_two_classes[0] == target_class: nontarget_max = top_two_logits[1] else: nontarget_max = top_two_logits[0] loss = torch.maximum(nontarget_max - target_class_logit, ...
However, during the test phase, all labels (current + old) are present. Overlap: It’s the same scenario as Disjoint except that the model can also see images containing a future class, as long as a current class is present. config.yaml is the main configuration file that reference all ...