Susant's Projects
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Just draw a bounding box and you can remove the object you want to remove.
Build Live Video Streaming Server use Ffmpeg Nginx Rtmp Module & Nodejs
Code for the paper "VirTex: Learning Visual Representations from Textual Annotations"
Datasets, Transforms and Models specific to Computer Vision
Vision Transformer using TensorFlow 2.0
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
High Level Lib for experimenting for learner and building applications
A platform to visualize the deep learning process and result.
A high-throughput and memory-efficient inference and serving engine for LLMs
VoVNet backbone networks for detectron2, in CVPR 2020
Sample AI Apps built with H2O Wave. Maintained by the Wave core team.
WaveGAN: Learn to synthesize raw audio with generative adversarial networks
Robust Speech Recognition via Large-Scale Weak Supervision
Hackable and optimized Transformers building blocks, supporting a composable construction.
Xv6 for RISC-V
Visual analysis and diagnostic tools to facilitate machine learning model selection.
yolo implementation in keras and tensorflow 2.2
This repository walks you through how to Build and Run YOLOv4 Object Detections with Darknet in the Cloud with Google Colab.
YOLOv5 in PyTorch > ONNX > CoreML > TFLite
ZenML š: Build portable, production-ready MLOps pipelines. https://zenml.io.