Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
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…
State-of-the-art 2D and 3D Face Analysis Project
deep learning for image processing including classification and object-detection etc.
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Efficient 3D human pose estimation in video using 2D keypoint trajectories
A synthetic data generator for text recognition
Siamese and triplet networks with online pair/triplet mining in PyTorch
ROS Wrapper for Intel(R) RealSense(TM) Cameras
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
在 oxford hand 数据集上对 YOLOv3 做模型剪枝(network slimming)
这是一个faster-rcnn的pytorch实现的库,可以利用voc数据集格式的数据进行训练。
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏
Pyramid Stereo Matching Network (CVPR2018)
[ECCV'22 Oral] Towards Grand Unification of Object Tracking
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Extremely simple implement for CRNN by Tensorflow
Hierarchical Deep Stereo Matching on High Resolution Images, CVPR 2019.
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)
no reference image/video quaity assessment(BRISQUE/NIQE/PIQE/DIQA/deepBIQ/VSFA