it will report an error here in loss.backward()

[CCJing14]

hello，i want to use memo to test coco. After calculating the marginal entropy, starting backpropagation to calculate the gradient, it will report an error here in loss.backward() Error detected in SigmoidBackward0. Traceback of forward call that caused the error: File "test.py", line 636, in test(opt.data, File "test.py", line 235, in test adapt_single(image, optimizer, batch_size, model, device) File "test.py", line 62, in adapt_single outputs,train_output = model(inputs) # [batch_size, num_boxes, 85] File "miniconda3/envs/memo/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "miniconda3/envs/memo/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "models/yolo.py", line 599, in forward return self.forward_once(x, profile) # single-scale inference, train File "models/yolo.py", line 625, in forward_once x = m(x) # run File "miniconda3/envs/memo/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "miniconda3/envs/memo/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "models/yolo.py", line 153, in fuseforward y = x[i].sigmoid() (Triggered internally at ../torch/csrc/autograd/python_anomaly_mode.cpp:114.)