IndexError: tuple index out of range

[8acemak1rkey]

when i run the command
python train.py --name three_view_long_share_d0.75_256_s1_google --extra --views 3 --droprate 0.75 --share --stride 1 --h 256 --w 256 --fp16
everything is going on well until Epoch 0/119 starts.
Here is information in detail:

Defaults for this optimization level are:
enabled : True
opt_level : O1
cast_model_type : None
patch_torch_functions : True
keep_batchnorm_fp32 : None
master_weights : None
loss_scale : dynamic
Processing user overrides (additional kwargs that are not None)...
After processing overrides, optimization options are:
enabled : True
opt_level : O1
cast_model_type : None
patch_torch_functions : True
keep_batchnorm_fp32 : None
master_weights : None
loss_scale : dynamic
Epoch 0/119

Traceback (most recent call last):
File "train.py", line 529, in
model = train_model(model, model_test, criterion, optimizer_ft, exp_lr_scheduler,
File "train.py", line 272, in train_model
outputs, outputs2, outputs3, outputs4 = model(inputs, inputs2, inputs3, inputs4)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/qhc/University1652-Baseline-master/University1652-Baseline-master/model.py", line 274, in forward
y2 = self.classifier(x2)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/qhc/University1652-Baseline-master/University1652-Baseline-master/model.py", line 82, in forward
x = self.add_block(x)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/container.py", line 139, in forward
input = module(input)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/apex-0.1-py3.8-linux-x86_64.egg/apex/amp/wrap.py", line 21, in wrapper
args[i] = utils.cached_cast(cast_fn, args[i], handle.cache)
File "/home/qhc/anaconda3/envs/university/lib/python3.8/site-packages/apex-0.1-py3.8-linux-x86_64.egg/apex/amp/utils.py", line 97, in cached_cast
if cached_x.grad_fn.next_functions[1][0].variable is not x:
IndexError: tuple index out of range
Thanks!!!

[layumi]

Hi @8acemak1rkey

You are using apex? Do you install apex successfully?
Could you try the normal trainning without fp16?

[8acemak1rkey]

Hi @8acemak1rkey

You are using apex? Do you install apex successfully? Could you try the normal trainning without fp16?
Thanks for your reply! Training without apex works. It is a problem with apex. By the way, my apex version is 0.1, I'd like to know yours . Thanks again!