Training error

[GreaBugs]

Running train_ net.py file occurred Error: TypeError :__ init__ () Got an unexpected keyword argument 'dtype', error location is detection2/engine/train_ loop.py
May I ask if anyone has encountered the same problem? How did you solve it?

[JIAZHAOQIAN]

This is because torch.cuda.amp.autocast() does not have the dtype parameter. Please modify "with autocast(dtype=self.precision)" to "with autocast()" to fix this problem (line 491 in detectron2/detectron2/engine/train_loop.py).

[GreaBugs]

anaconda3/envs/fastinst/lib/python3.8/site-packages/shapely/set_operations.py:133: RuntimeWarning: invalid value encountered in intersection
return lib.intersection(a, b, **kwargs)

File "/anaconda3/envs/fastinst/lib/python3.8/site-packages/torch/utils/tensorboard/init.py", line 4, in
LooseVersion = distutils.version.LooseVersion

AttributeError: module 'distutils' has no attribute 'version'
As you said, what is the reason for this error now?

[JIAZHAOQIAN]

This is due to the update of setuptools. First, pip uninstall setuptools, then, pip or conda install setuptools==58.0.4.

[GreaBugs]

pip uninstall setuptools
pip install setuptools==58.0.4
and
pip uninstall shapely
pip install shapely==v1.8.5