Resume started from zero again!

[zobeirraisi]

When I resume the trained model, it starts from zero?
Or when I specify the path, it gives me the following error:
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

[PeizeSun]

Hi~
Can you provide your command line?

[zobeirraisi]

Thanks for your response,
I tried the following:
python projects/SparseRCNN/train_net.py --num-gpus 1 \ --config-file projects/SparseRCNN/configs/sparsercnn.res50.300pro.3x.yaml --resume
and
python projects/SparseRCNN/train_net.py --num-gpus 1 \ --config-file projects/SparseRCNN/configs/sparsercnn.res50.300pro.3x.yaml --resume output/
The above worked but started from zero .

[PeizeSun]

python projects/SparseRCNN/train_net.py --num-gpus 1 --config-file projects/SparseRCNN/configs/sparsercnn.res50.300pro.3x.yaml --resume
works well in my case.

Do you delete last_checkpoint in output folder?