Dépôts
Dépôts de DayBreak-u
Object detection, 3D detection, and pose estimation using center point detection:
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Implementation RefinedetLite
the C++ version of solov2 with ncnn
SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
train Snet(by thundernet) in imagenet
Implementation Thundernet
the C++ version of Transformer with ncnn
Video Question Answering
centernet_mobilenetv2 inference by ncnn
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
加入关键点的darknet训练框架,轻量级的人脸检测,支持ncnn推理
csv or xls input into hive
A face detection algorithm
Android paddleocr demo infer by ncnn
it's my personal website
the C++ version of Seq2Seq with ncnn
SRMD super resolution implemented with ncnn library
thundernet ncnn