从 65,729 个高星开源项目里，
找到你要的下一个。

Pytorch-UNet 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

darkflow 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

deep-learning-v2-pytorch 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

darts 是用 Python 编写的学习资料，用于系统学习与查阅。

Differentiable architecture search for convolutional and recurrent networks

towhee 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理，主打速度快、易用。

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

DeblurGAN 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

Image Deblurring using Generative Adversarial Networks

Awesome-Graph-Neural-Networks 是一个学习资料，用于系统学习与查阅。

Paper Lists for Graph Neural Networks

micronet 是用 Python 编写的 AI 工具，用于大模型训练与推理。

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and T…

pytorch-fcn 是用 Python 编写的 AI 工具，用于人工智能方向的建模与推理。

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

keras-yolo2 是用 Jupyter Notebook 编写的学习资料，用于系统学习与查阅，主打易用。

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is acce…

must-read-papers-for-ml 是一个 AI 工具，用于人工智能方向的建模与推理。

Collection of must read papers for Data Science, or Machine Learning / Deep Learning Engineer

pytorch-image-classification 是用 Jupyter Notebook 编写的 AI 工具，用于人工智能方向的建模与推理。

Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.