- Simplified training and evalution, running on CPU, GPU and TPU, more powerful than Keras
- Easily extended to supervised learning tasks (Classification, Detection, Segmentation, NAS, Super Resolution, Keypoint Detection)
- High quality and out-of-the-box reimplementation of popular computer vision models, modules and tricks with reproduced experimental results
- Classification (ResNet-D, Res2Net, RegNet, SENet, ECA-Net, ...)
- Detection (RetinaNet, ATSS, FCOS, GFL, GFLV2, BiFPN, CIoU)
- Segmentation (DeepLabV3, DeepLabV3+)
- Data Augmentation and Regularization (RandAugment, CutMix, DropPath, DropBlock, ...)
- Repeatable training code and detailed training log for all reimplementation
-
Notifications
You must be signed in to change notification settings - Fork 2
sbl1996/hanser
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A library to help with training for different tasks in TensorFlow
Topics
Resources
Stars
Watchers
Forks
Packages 0
No packages published