attack_of_cifar | Master-IASD | upnquick | Error | 0 | 0 | 0 | 0 | 0 | 0 | RuntimeError: Error(s) in loading state_dict for Net:
Missing key(s) in state_dict: "conv1.weight", "conv1.bias", "conv2.weight", "conv2.bias", "conv3.weight", "conv3.bias", "fc1.weight", "fc1.bias", "fc2.weight", "fc2.bias", "fc3.weight", "fc3.bias", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "bn2.weight", "bn2.bias", "bn2.running_mean", "bn2.running_var", "bn3.weight", "bn3.bias", "bn3.running_mean", "bn3.running_var".
Unexpected key(s) in state_dict: "accurate_model_state", "robust_model_state", "s", "p", "c", "alpha". |
naive_implem | profs | kaisertrot | Error | 0 | 0 | 0 | 0 | 0 | 0 | OutOfMemoryError: CUDA out of memory. Tried to allocate 260.00 MiB. GPU 0 has a total capacity of 47.54 GiB of which 108.00 MiB is free. Process 2471154 has 480.00 MiB memory in use. Process 1024293 has 43.14 GiB memory in use. Including non-PyTorch memory, this process has 3.81 GiB memory in use. Of the allocated memory 2.93 GiB is allocated by PyTorch, and 581.12 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables) |