RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous

[ghost]

I followed all the instructions and get:

loading annotations into memory... loading annotations into memory... Done (t=0.43s) creating index... index created! Done (t=0.43s) creating index... index created! Traceback (most recent call last): File "./mmdetection/tools/train.py", line 108, in <module> main() File "./mmdetection/tools/train.py", line 104, in main logger=logger) File "/root/sharedfolder/production/2020/det/RepPoints/mmdetection/mmdet/apis/train.py", line 58, in train_detector _dist_train(model, dataset, cfg, validate=validate) File "/root/sharedfolder/production/2020/det/RepPoints/mmdetection/mmdet/apis/train.py", line 186, in _dist_train runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/opt/conda/lib/python3.6/site-packages/mmcv/runner/runner.py", line 358, in run epoch_runner(data_loaders[i], **kwargs) File "/opt/conda/lib/python3.6/site-packages/mmcv/runner/runner.py", line 271, in train self.call_hook('after_train_iter') File "/opt/conda/lib/python3.6/site-packages/mmcv/runner/runner.py", line 229, in call_hook getattr(hook, fn_name)(self) File "/root/sharedfolder/production/2020/det/RepPoints/mmdetection/mmdet/core/utils/dist_utils.py", line 53, in after_train_iter runner.outputs['loss'].backward() File "/opt/conda/lib/python3.6/site-packages/torch/tensor.py", line 198, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/opt/conda/lib/python3.6/site-packages/torch/autograd/__init__.py", line 99, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.