OpenVLA: An open-source vision-language-action model for robotic manipulation.

运用tensorflow实现自然场景文字检测,keras/pytorch实现crnn+ctc实现不定长中文OCR识别

Stable Diffusion web UI

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow for Mobile Deployment

MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition

Controlnet extension of AnimateDiff.

Character-Based Handwritten Text Transcription with Attention Networks

Faster R-CNN, an MXNet implementation with distributed implementation and data parallelization.

Bag of Visual Words and HOG based object detection in python/opencv

Generate text images for training deep learning ocr model

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching

Faster R-CNN (with support for Hard Negative Example Mining)

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

WebUI extension for ControlNet, Integrated with ControlNetMediaPipeFace

Train Faster R-CNN on WIDER FACE dataset