CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

PyTorch code and models for the DINOv2 self-supervised learning method.

unet for image segmentation

exercise for nndl

深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

中文nlp解决方案(大模型、数据、模型、训练、推理)

3D U-Net model for volumetric semantic segmentation written in pytorch

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

Coursera Machine Learning - Python code

RETFound - A foundation model for retinal image

cell detection in calcium imaging recordings

code for reading and processing Allen Institute for Brain Science data

Multimodal Whole Slide Foundation Model for Pathology

对numpy包中常用函数的官方文档进行翻译

Notebooks accompanying the 2-photon random access mesoscope (2p-RAM) paper