kapitsa2811's repositories
2nd-place-solution-Digital-Peter
2nd place Solution for Digital Peter competition
academic
All academic activities
awesome-ocr-1
Links to awesome OCR projects
best_AI_papers_2021
A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code. [work in progress]
BMS-Molecular-Translation-1
Kaggle | 70th place solution for Bristol-Myers Squibb – Molecular Translation.
clip-guided-diffusion
A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
conformer_ocr
Transformer OCR is a Optical Character Recognition tookit built for researchers working on both OCR for both Vietnamese and English. This project only focused on variants of vanilla Transformer (Conformer) and Feature Extraction (CNN-based approach).
deep-daze
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
Document_Blur_Detection
Document blur detection based on Laplacian operator and text detection.
glide-text2im
GLIDE: a diffusion-based text-conditional image synthesis model
Kaggle
Kaggle Publications: Explaining the summary and publishing Kaggle Medals Award Python Code in Data Science and Artificial Intelligence
kraken
OCR engine for all the languages
ocr-lowresolution
Source code for low resolution OCR experiments
OCR-model
An easy-to-run OCR model pipeline based on CRNN and CTC loss
pytorch-phocnet
PHOCNet implementation in Pytorch based on Sudholt's implementation
ru-dalle
Generate images from texts. In Russian
StyleCLIP
Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)
TensorFlow-2.x-YOLOv3
YOLOv3 implementation in TensorFlow 2.3.1
Treasure-of-Transformers
💁 Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. 🛫☑️
U-2-Net-Demo
Demonstration using Google Colab to show how U-2-NET can be used for Background Removal, Changing Backgrounds, Bounding Box Creation, Salient Feature Highlighting and Salient Object Cropping.
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
x-clip
A concise but complete implementation of CLIP with various experimental improvements from recent papers