Computer Vision Finetuning#
TAO is a pre-training, finetuning, and optimization application for computer vision DNNs (deep neural networks). The pipelines in TAO are implemented across the TensorFlow and PyTorch Deep Learning Frameworks. The details of the finetuning pipelines, including hyperparameters and features, are covered in the subsequent sections.
- PyTorch
- Self-Supervised Learning
- Synthetic Data Generation with StyleGAN-XL
- Metric Learning Recognition
- Instance Segmentation
- CenterPose
- Character Recognition
- VisualChangeNet
- 3D Object Detection
- ReIdentificationNet Transformer
- Optical Inspection
- Pose Classification
- Object Detection
- ReIdentificationNet
- ActionRecognitionNet
- BEVFusion
- Image Classification PyT
- SegFormer
- Sparse4D
- TensorFlow 2.x
- TensorFlow 1.x [Deprecated]