Hi,
I am getting list index out of range error during training
----------------EPOCH 1
Processing: | | 0/49[00:00<?,?it/s]Batch = nan|EMA = nanTraceback (most recent call last):
File "run_train.py", line 305, in
trainer.run()
File "run_train.py", line 288, in run
self.run_once(
File "run_train.py", line 265, in run_once
main_runner.run(opt["nr_epochs"])
File "E:\hover\hover_net-master\run_utils\engine.py", line 172, in run
for data_batch in self.dataloader:
File "E:\Anaconda\lib\site-packages\torch\utils\data\dataloader.py", line 633, in next
data = self._next_data()
File "E:\Anaconda\lib\site-packages\torch\utils\data\dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "E:\Anaconda\lib\site-packages\torch\utils\data\dataloader.py", line 1371, in _process_data
data.reraise()
File "E:\Anaconda\lib\site-packages\torch_utils.py", line 644, in reraise
raise exception
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "E:\Anaconda\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "E:\Anaconda\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\Anaconda\lib\site-packages\torch\utils\data_utils\fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "E:\hover\hover_net-master\dataloader\train_loader.py", line 98, in getitem
type_map = (ann[..., 1]).copy()
IndexError: index 1 is out of bounds for axis 2 with size 1
Looks like your data has not been prepared right. It is trying to grab the second channel for the type map, which apparently isn't there.
vqdang
