v1.0.5
Updates:
- Managers now perform to
torchmanager_core.devices.DeviceMovableandtrain.StateDictLoadableprotocol - Save weights only now supports any kind of objects that perform to
StateDictLoadableprotocol EarlyStopcallback implementation to stop the training when monitored metrics not improvement for several epochsLossnow supports weight coefficient value- Performance improved for multi-GPUs running
- Minor bugs fixed