pytorch-image-models/models/__init__.py

from .model_factory import create_model, load_checkpoint
from .test_time_pool import TestTimePoolHead
Lots of refactoring and cleanup. * Move 'test time pool' to Module that can be used by any model, remove from DPN * Remove ResNext model file and combine with ResNet * Remove fbresnet200 as it was an old conversion and pretrained performance not worth param count * Cleanup adaptive avgmax pooling and add back conctat variant * Factor out checkpoint load fn 2019-04-10 14:12:28 -07:00			`from .model_factory import create_model, load_checkpoint`
			`from .test_time_pool import TestTimePoolHead`
Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms 2019-03-10 14:23:16 -07:00