Repositories (9)
Probing the representations of Vision Transformers.
This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.
Implements the ideas presented in https://arxiv.org/pdf/2004.11362v1.pdf by Khosla et al.
Implementation of MAXIM in TensorFlow.
Implements the ideas presented in https://arxiv.org/pdf/2004.11362v1.pdf by Khosla et al.
Includes PyTorch -> Keras model porting code for ConvNeXt family of models with fine-tuning and inference notebooks.
(Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.
Implementation of DreamBooth in KerasCV and TensorFlow.
TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.