CLAIR: A (surprisingly) simple semantic text metric with large language models.

基于ClipCap的看图说话Image Caption模型

Open Source Computer Vision Library

Image-to-Image Translation in PyTorch

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

A curated list of image captioning and related area resources. :-)

Transformer模型Encoder原理精讲及其PyTorch逐行实现 笔记 https://www.bilibili.com/video/BV1cP4y1V7GF?spm_id_from=333.337.search-card.all.click&vd_source=afe449886875b2cd7aa123878846a9f3

这里面存放了一些目标检测算法的数据增强方法。如mosaic、mixup。

这是一个yolo3-pytorch的源码，可以用于训练自己的模型。

deep learning for image processing including classification and object-detection etc.

Pytorch🍊🍉 is delicious, just eat it! 😋😋

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite