Ayush Thakur's Projects
[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
Fast and flexible AutoML with learning guarantees.
Repo for our talk at GDG Kolkata TensorFlow All Round event on 31st August.
[CVPR2020] Adversarial Latent Autoencoders
Online recognition of American Sign Language Finger Spelling from a video (webcam) and interpretation of the gestures.
TF2.0 port for Augmix paper
Semantic and drivable segmentation for autonomous driving using Keras and baked with Weights and Biases.
Awesome Object Detection based on handong1587 github: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html
Collection of awesome DL/Math resources to feel enlightened!
Pawan Kumar Portfolio
Personal website of Ayush Thakur π
A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis [ECCV 2022]
This repository contains arduino code for our bot which was capable of detecting blocks(cubes) using IR sensor and distinguish between two block sizes.
Used for adaptive human in the loop evaluation of language and embedding models.
Following this series : https://www.youtube.com/watch?v=tc8DU14qX6I
Code release for ConvNeXt model
List of Computer Science courses with video lectures.
DALLΒ·E Mini - Generate images from a text prompt
Implementation of modern data augmentation techniques in TensorFlow 2.x to be used in your training pipeline.
Data Structure in C
Concepts Explored in/with Pytorch
Towards Generative Modeling from (variational) Autoencoder to DCGAN
Deep Image Inpainting using UNET like Vanilla Autoencoder and Partial Convolution based Autoencoder.
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Detectron2 is FAIR's next-generation platform for object detection and segmentation.