Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
- document-ai
- eccv-2022
- multimodal-pre-trained-model
- ocr
132,241 visible repositories in the index
1–10 of 10 · Most stars
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
The author's officially unofficial PyTorch BigGAN implementation.
:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
PyTorch implementation of MeanFlow & iMF (one-step generative modeling).
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
:zap: A newly designed ultra lightweight anchor free target detection algorithm, weight only 250K parameters, reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
A Guidance on PyTorch Coding Style Based on Kaggle Dogs vs. Cats
Python package for Causal Discovery by learning the graphical structure of Bayesian networks. Structure Learning, Parameter Learning, Inferences, Sampling methods.
猫狗大战