darts
darts copied to clipboard
train_search.py ConnectionResetError
I use python train_search.py --unrolled
get:
train_search.py:154: UserWarning: torch.nn.utils.clip_grad_norm is now deprecated in favor of torch.nn.utils.clip_grad_norm_. nn.utils.clip_grad_norm(model.parameters(), args.grad_clip) train_search.py:158: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number objs.update(loss.data[0], n) train_search.py:159: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number top1.update(prec1.data[0], n) train_search.py:160: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number top5.update(prec5.data[0], n) 06/13 05:42:02 PM train 000 2.354113e+00 10.937500 53.125000 Exception ignored in: <bound method _DataLoaderIter.del of <torch.utils.data.dataloader._DataLoaderIter object at 0x7f43244c02e8>> Traceback (most recent call last): File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 399, in del self._shutdown_workers() File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 378, in _shutdown_workers self.worker_result_queue.get() File "/opt/conda/lib/python3.6/multiprocessing/queues.py", line 337, in get return _ForkingPickler.loads(res) File "/opt/conda/lib/python3.6/site-packages/torch/multiprocessing/reductions.py", line 151, in rebuild_storage_fd fd = df.detach() File "/opt/conda/lib/python3.6/multiprocessing/resource_sharer.py", line 58, in detach return reduction.recv_handle(conn) File "/opt/conda/lib/python3.6/multiprocessing/reduction.py", line 182, in recv_handle return recvfds(s, 1)[0] File "/opt/conda/lib/python3.6/multiprocessing/reduction.py", line 153, in recvfds msg, ancdata, flags, addr = sock.recvmsg(1, socket.CMSG_LEN(bytes_size)) ConnectionResetError: [Errno 104] Connection reset by peer
I reimplement a the CNN part that support latest Pytorch, and the code is available at https://github.com/MandyMo/DARTS.