本项目基于PaddleDetection目标检测开发套件,选取1.3M超轻量PPYOLO tiny进行项目开发,并部署于windows端。
DocTr++ in PaddlePaddle
Instruction Following Agents with Multimodal Transforemrs
YOLO: You only look once real-time object detector
[ECCV2022] New benchmark for evaluating pre-trained model; New supervised contrastive learning fr...
首个完整封装、一体化训练stable diffusion dreambooth的autodl镜像环境,可训练定制自己的独特大模型风格、人物,开箱即用,内含详细教程。
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
Dataset Viber is your chill repo for data collection, annotation and vibe checks.
We present NoticIA, a dataset consisting of 850 Spanish news articles featuring prominent clickba...
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Fine-tuning stable diffusion to generate planet/moon textures.
Parameterized fit and prediction harnesses for pytorch