TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
Adjusting supply of a token and connector balance of bancor during final phase of boot.