Sayak Paul

diffusers-torchao. End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

TF-2.0-Hacks. Contains my explorations of TensorFlow 2.x

probing-vits. Probing the representations of Vision Transformers.

ml-deployment-k8s-fastapi. This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.

tt-scale-flux. Inference-time scaling of diffusion-based image and video generation models.

Adventures-in-TensorFlow-Lite. This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

cmmd-pytorch. PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.

caption-upsampling. This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.

nanoDiT. Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.

maxim-tf. Implementation of MAXIM in TensorFlow.

MIRNet-TFLite-TRT. TensorFlow Lite models for MIRNet for low-light image enhancement.

Supervised-Contrastive-Learning-in-TensorFlow-2. Implements the ideas presented in https://arxiv.org/pdf/2004.11362v1.pdf by Khosla et al.

robustness-vit. Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).

ConvNeXt-TF. Includes PyTorch -> Keras model porting code for ConvNeXt family of models with fine-tuning and inference notebooks.

flux-image-editing. Scripts to teach Flux the task of image editing from language with the Flux Control framework.

Grocery-Product-Detection. This repository builds a product detection model to recognize products from grocery shelf images.

SimSiam-TF. Minimal implementation of SimSiam (https://arxiv.org/abs/2011.10566) in TensorFlow 2.

SimCLR-in-TensorFlow-2. (Minimally) implements SimCLR (https://arxiv.org/abs/2002.05709) in TensorFlow 2.

dreambooth-keras. Implementation of DreamBooth in KerasCV and TensorFlow.

FunMatch-Distillation. TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.

Adaptive-Gradient-Clipping. Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.

single-video-curation-svd. Educational repository for applying the main video data curation techniques presented in the Stable Video Diffusion paper.

Sharpness-Aware-Minimization-TensorFlow. Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.

Breast-Cancer-Detection-using-Deep-Learning. Experiments to show the usage of deep learning to detect breast cancer from breast histopathology images

MLP-Mixer-CIFAR10. Implements MLP-Mixer (https://arxiv.org/abs/2105.01601) with the CIFAR-10 dataset.

Knowledge-Distillation-in-Keras. Demonstrates knowledge distillation for image-based models in Keras.

Barlow-Twins-TF. TensorFlow implementation of Barlow Twins (https://arxiv.org/abs/2103.03230).

keras-xla-benchmarks. Presents comprehensive benchmarks of XLA-compatible pre-trained models in Keras.

Spatial-Transformer-Networks-with-Keras. This repository provides a Colab Notebook that shows how to use Spatial Transformer Networks inside CNNs in Keras.

par-cvpr-21. Contains notebooks for the PAR tutorial at CVPR 2021.