Diff-UNet icon indicating copy to clipboard operation
Diff-UNet copied to clipboard

received 0 items of ancdata

Open zzh1230 opened this issue 1 year ago • 1 comments

When I executed the train.py, I encountered the following error, how can I solve it?

Traceback (most recent call last): File "train.py", line 192, in trainer.train(train_dataset=train_ds, val_dataset=val_ds) File "/home/hdc/zjh/Diff-UNet-main/LiTS/light_training/trainer.py", line 262, in train self.train_epoch( File "/home/hdc/zjh/Diff-UNet-main/LiTS/light_training/trainer.py", line 361, in train_epoch for idx, batch in enumerate(loader): File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 517, in next data = self._next_data() File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1182, in _next_data idx, data = self._get_data() File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1148, in _get_data success, data = self._try_get_data() File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 986, in _try_get_data data = self._data_queue.get(timeout=timeout) File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/multiprocessing/queues.py", line 116, in get return _ForkingPickler.loads(res) File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 282, in rebuild_storage_fd fd = df.detach() File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/multiprocessing/resource_sharer.py", line 58, in detach return reduction.recv_handle(conn) File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/multiprocessing/reduction.py", line 189, in recv_handle return recvfds(s, 1)[0] File "/home/hdc/anaconda3/envs/pytorch/lib/python3.8/multiprocessing/reduction.py", line 164, in recvfds raise RuntimeError('received %d items of ancdata' %

zzh1230 avatar Apr 24 '23 05:04 zzh1230

First, you can switch the env from "DDP" to "pytorch", using single GPU or CPU to run the code. Then you also need to check the training data.

920232796 avatar Apr 24 '23 13:04 920232796