作者你好，我将AOLM模块加入到我的模型以后会出现一下错误，当我从双卡GPU切换到单卡GPU依然会出现这个问题。但奇怪的是，我曾经在相同参数的情况下完成过一次完整的训练，然而再次训练时就会报出ValueError: max() arg is an empty sequence的错误。
Traceback (most recent call last):
File "train.py", line 33, in
do_train(
File "/root/autodl-tmp/PART-master/processor/processor.py", line 102, in do_train
cls_g, cls_1 = model(img, target,mode='train') #0515
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 168, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 178, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 86, in parallel_apply
output.reraise()
File "/root/miniconda3/lib/python3.8/site-packages/torch/_utils.py", line 425, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
output = module(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/PART-master/model/make_model.py", line 321, in forward
return self.forward_multi(inputs, label)
File "/root/autodl-tmp/PART-master/model/make_model.py", line 406, in forward_multi
coordinates = torch.tensor(AOLM(out.detach()))
File "/root/autodl-tmp/PART-master/model/make_model.py", line 33, in AOLM
max_idx = areas.index(max(areas))
ValueError: max() arg is an empty sequence
ZF4444
