Dexterp37 / fontina
Data generation, model training and inference for Visual Font Recognition using PyTorch
☆13Updated last year
Alternatives and similar repositories for fontina:
Users that are interested in fontina are comparing it to the libraries listed below
- This is the github repository for converting craft pretrained model to tflite version☆34Updated 4 years ago
- ☆52Updated last year
- Convert LORE model from torch format to ONNX format.☆10Updated 5 months ago
- An application of high resolution GANs to dewarp images of perturbed documents☆140Updated 3 years ago
- Python scripts for performing object detection with the 1000 labels of the ImageNet dataset in ONNX. The repository combines a class agno…☆34Updated 3 years ago
- Synthesize distorted document image and control points.☆47Updated 2 years ago
- Python scripts for performing Image Inpainting using the MST model in ONNX☆16Updated 2 years ago
- The code and the DIW dataset for "Learning From Documents in the Wild to Improve Document Unwarping" (SIGGRAPH 2022)☆129Updated 8 months ago
- Attention-based sequence-to-sequence model for handwritten word recognition☆57Updated 7 months ago
- ☆40Updated 9 months ago
- A function that takes as input a cropped text line image, and outputs the dewarped image.☆18Updated 5 months ago
- A way to rectify curve text images using spatial transformer by pairs of points.☆37Updated 4 years ago
- The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.☆81Updated 2 weeks ago
- OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR☆101Updated last week
- A search engine implementation using OpenAI's clip model☆10Updated 3 years ago
- EfficientNet for Deep Face Recognition☆20Updated 4 years ago
- Automatic Text Removal using CRAFT and LaMa☆40Updated last year
- Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"☆110Updated 4 years ago
- A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier …☆13Updated 10 months ago
- Official PyTorch implementation of PyramidTabNet: Transformer-based Table Recognition in Image-based Documents☆25Updated 6 months ago
- [WIP] A Pytorch implementation of DB-Text - Real-time Scene Text Detection with Differentiable Binarization☆38Updated 2 years ago
- Scene-OCR: CRAFT: text detection + TPS-ResNet-BiLSTM-Attn: text recognition☆10Updated 2 years ago
- Detect mathematical expressions in worksheets and draw bounding boxes.☆21Updated 4 years ago
- DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction☆20Updated last year
- This project is under development.☆23Updated last year
- ☆22Updated 2 years ago
- Segmenting a given document using recursive xy-cut algorithm.☆12Updated 6 years ago
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆37Updated last year
- ☆20Updated 3 years ago
- OCR(Korean)☆8Updated 2 years ago