pomelloa
commented
4 days ago Did you use the data transforms called 'PhotoMetricDistortion'? The step may convert color from BGR to HSV, so the data is limited to a(3).
Open ZhoumingZhang opened 1 week ago
pomelloa
commented
4 days ago Did you use the data transforms called 'PhotoMetricDistortion'? The step may convert color from BGR to HSV, so the data is limited to a(3).
Traceback (most recent call last): File "C:\Git clone\mmsegmentation\tools\train.py", line 104, in
main()
File "C:\Git clone\mmsegmentation\tools\train.py", line 100, in main
runner.train()
File "C:\Users\13785.conda\envs\pytorch\lib\site-packages\mmengine\runner\runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
File "C:\Users\13785.conda\envs\pytorch\lib\site-packages\mmengine\runner\loops.py", line 287, in run
self.run_iter(data_batch)
File "C:\Users\13785.conda\envs\pytorch\lib\site-packages\mmengine\runner\loops.py", line 311, in run_iter
outputs = self.runner.model.train_step(
File "C:\Users\13785.conda\envs\pytorch\lib\site-packages\mmengine\model\base_model\base_model.py", line 113, in train_step
data = self.data_preprocessor(data, True)
File "C:\Users\13785.conda\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Git clone\mmsegmentation\mmseg\models\data_preprocessor.py", line 118, in forward
inputs = [(_input - self.mean) / self.std for _input in inputs]
File "C:\Git clone\mmsegmentation\mmseg\models\data_preprocessor.py", line 118, in
inputs = [(_input - self.mean) / self.std for _input in inputs]
RuntimeError: The size of tensor a (3) must match the size of tensor b (6) at non-singleton dimension 0