Aashish Kumar's repositories
stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models
doctr
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
PromCSE
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
DifferentiableBinarization
DB (Real-time Scene Text Detection with Differentiable Binarization) implementation in Keras and Tensorflow
CenterNet
Object detection, 3D detection, and pose estimation using center point detection:
detr
End-to-End Object Detection with Transformers
NAFNet
The state-of-the-art image restoration model without nonlinear activation functions.
ml-mobileone
This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".
HighRes-net
Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin competition. This is a ServiceNow Research project that was started at Element AI.
Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
trans-encoder
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
full-page-handwriting-recognition
Implementation of the paper "Full Page Handwriting Recognition via Image to Sequence Extraction" by Singh et al. (2021).
scrabble-gan
Adversarial Generation of Handwritten Text Images
Handwriting-Transformers
Handwriting-Transformers (ICCV21)
DB
A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
PolygonObjectDetection
This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes.
SegLoss
A collection of loss functions for medical image segmentation
detr-tensorflow
Tensorflow implementation of DETR : Object Detection with Transformers
DeblurGANv2
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
image_stacking
Automatic Image Stacking in OpenCV
CTC-OptimizedLoss
Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
multi-mnist
MNIST dataset with multiple digits. This dataset can be use for learning number (more than 1 digit) regconizer model.
CrossDomainFewShot
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation (ICLR 2020 spotlight)
tf2_adda
TF 2 implementation of ADDA paper
keras-ocr
A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.
iterdet
[S+SSPR2020] IterDet: Iterative Scheme for Object Detection in Crowded Environments
SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow.