yamcomnet

> Hi! > > Personnaly, i use GD for make a diagonal watermark... > > `$im = \imagerotate($im, 45, $background_color);` > > Regards, > LBF Sure, this is the only...

Sounds good approach. I see this package is already very nice for fine tuning. Would be superb to save models and use those to predict. Nice work!

Traceback (most recent call last): File "train.py", line 188, in train_net(net=net, File "train.py", line 79, in train_net for batch in train_loader: File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 578, in __next__ data = self._next_data()...