Pinned Repositories
Advanced_EAST
AdvancedEAST is an algorithm used for Scene image text detect. This repository is edited from https://github.com/huoyijie/AdvancedEAST. Released under MIT license
Alpha-Matting-Delphi
Trimap alpha matting
BackgroundMattingV2
Real-Time High-Resolution Background Matting
BSRGAN
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (PyTorch) - We released the testing code!
cnn_lstm_ctc_ocr
Tensorflow-based CNN+LSTM trained with CTC-loss for OCR
Delphi-Tensorflow-Lite
Fast and accurate face detection with Delphi FMX and Tensorflow Lite
mnn-yolov8
YOLOv8 using MNN. Support Python, C++.
ncnn-delphi-fmx
ncnn delphi inference demo
Text-Recognition-Dataset
Synthetic dataset for text recognition
TONNXRuntime
TOnnxRuntime is a Microsoft ONNXRuntime AI and Machine Learning Library for Freepascal / Delphi
DonkeySmall's Repositories
DonkeySmall/Delphi-Tensorflow-Lite
Fast and accurate face detection with Delphi FMX and Tensorflow Lite
DonkeySmall/Text-Recognition-Dataset
Synthetic dataset for text recognition
DonkeySmall/Alpha-Matting-Delphi
Trimap alpha matting
DonkeySmall/mnn-yolov8
YOLOv8 using MNN. Support Python, C++.
DonkeySmall/ncnn-delphi-fmx
ncnn delphi inference demo
DonkeySmall/TONNXRuntime
TOnnxRuntime is a Microsoft ONNXRuntime AI and Machine Learning Library for Freepascal / Delphi
DonkeySmall/deep-text-recognition-benchmark
PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
DonkeySmall/DRSformer
Learning A Sparse Transformer Network for Effective Image Deraining (CVPR 2023)
DonkeySmall/Face-Upscalers-ONNX
ONNX-Powered Inference for State-of-the-Art Face Upscalers
DonkeySmall/FudanOCR
A toolbox of scene text detection and recognition
DonkeySmall/GFPGAN-ncnn
a naive NCNN implementation of GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration
DonkeySmall/handwriting-synthesis
Handwriting Synthesis with RNNs ✏️
DonkeySmall/keras_cv_attention_models
Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam
DonkeySmall/Keras_insightface
Insightface Keras implementation
DonkeySmall/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
DonkeySmall/ocr-transformer
transformer-based ocr model
DonkeySmall/PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
DonkeySmall/parseq
Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)
DonkeySmall/Parseq-Vietnamese
DonkeySmall/SAM
Official Implementation for "Only a Matter of Style: Age Transformation Using a Style-Based Regression Model" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02754
DonkeySmall/segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.
DonkeySmall/Single_Image_Super_Resolution
A tensorflow-based implementation of SISR using EDSR, SRResNet, and SRGAN
DonkeySmall/skia4delphi
Skia4Delphi is a cross-platform 2D graphics API for Delphi platforms based on Google's Skia Graphics Library. It provides a comprehensive 2D API that can be used across mobile, server and desktop models to render images.
DonkeySmall/synthtiger
Official implementation of SynthTIGER (Synthetic Text Image GEneratoR) ICDAR 2021
DonkeySmall/TrOCR--BKAI
TrOCR model with Huggingface
DonkeySmall/trocr-chinese
transformers ocr for chinese
DonkeySmall/vitstr
DonkeySmall/ViTSTR_OCR
PyTorch-Lightning code of ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
DonkeySmall/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
DonkeySmall/YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~