AttributeError: 'list' object has no attribute 'numel'

[gzgz-code]

🐛 Bug

To Reproduce

Steps to reproduce the behavior:

Expected behavior

Traceback (most recent call last):
File "/home/hyh/software/pycharm-community-2021.2.1/plugins/python-ce/helpers/pydev/pydevd.py", line 1483, in exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/hyh/software/pycharm-community-2021.2.1/plugins/python-ce/helpers/pydev/pydev_imps/pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/tools/train_net.py", line 266, in
main()
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/tools/train_net.py", line 259, in main
model = train(cfg, args.local_rank, args.distributed)
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/tools/train_net.py", line 157, in train
do_train(model, data_loader, optimizer, scheduler, checkpointer, device, checkpoint_period, arguments, summary_writer)
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/tools/train_net.py", line 77, in do_train
loss_dict,,,,_ = model(images, targets)
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/apex-0.1-py3.8-linux-x86_64.egg/apex/amp/_initialize.py", line 196, in new_fwd
output = old_fwd(*applier(args, input_caster),
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 62, in forward
features, backbone_features = self.backbone(images.tensors)
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/torch/nn/modules/container.py", line 117, in forward
input = module(input)
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/fpn.py", line 51, in forward
last_inner = getattr(self, self.inner_blocks[-1])(x[-1])
File "/home/hyh/anaconda3/envs/maskrcnn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/maskrcnn_benchmark/layers/misc.py", line 32, in forward
if x.numel() > 0:
AttributeError: 'list' object has no attribute 'numel'

Process finished with exit code 1

Environment

Please copy and paste the output from the
environment collection script from PyTorch
(or fill out the checklist below manually).

You can get the script and run it with:

wget https://raw.githubusercontent.com/pytorch/pytorch/master/torch/utils/collect_env.py
# For security purposes, please check the contents of collect_env.py before running it.
python collect_env.py

• PyTorch Version (e.g., 1.0):1.6.0
• OS (e.g., Linux):ubuntu
• How you installed PyTorch (conda, pip, source):conda
• Build command you used (if compiling from source):--config-file "/home/hyh/Code/python/CL/CL_OBJECT_DETECTION/copy/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_50_FPN_1x.yaml" SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025 SOLVER.MAX_ITER 720000 SOLVER.STEPS "(480000, 640000)" TEST.IMS_PER_BATCH 1 MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN 2000
• Python version:3.8
• CUDA/cuDNN version:10.1
• GPU models and configuration:GTX2080
• Any other relevant information:

Additional context

I don't understand why such a mistake happened. If someone can help me, I'm very grateful

[chenfangchenf]

Did you solve this problem, I have the same problem