依赖 Keras >= 1.0 且声明兼容 Python 2.7-3.5，新版 TensorFlow/Keras 与 Python 3.6+ 可能不兼容；训练数据仅 30 张 512×512 图像，需依赖数据增强；README 未给出模型权重下载，需自行训练或按 notebook 运行
pip install tensorflow keras
python main.py 硬件要求按 README 说明
README 未说明显存要求；Keras 本身可在 CPU 和 GPU 上运行，但未列出具体 GPU 厂商或型号
用 Keras 实现的 U-Net 图像分割示例，含 ISBI 细胞膜数据与训练脚本，适合快速上手分割任务
基于 Keras 实现的 U-Net 图像分割模型，提供训练与推理代码，适合医学影像等像素级分割任务的快速复现与二次开发。
核心能力
- 用 Keras 函数式 API 搭建 U-Net 网络
- 用 ImageDataGenerator 做数据增强扩充样本
- 输出 512×512 掩码并用 Sigmoid 限制到 0~1
- 提供 data/membrane 预处理好的 ISBI 数据集
- 训练 5 个 epoch 后准确率约 0.97
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
暂无 release 数据（可能没有发版，或尚未同步）。
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
Implementation of deep learning framework -- Unet, using Keras
The architecture was inspired by U-Net: Convolutional Networks for Biomedical Image Segmentation.
Overview
Data
The original dataset is from isbi challenge, and I've downloaded it and done the pre-processing.
You can find it in folder data/membrane.
Data augmentation
The data for training contains 30 512*512 images, which are far not enough to feed a deep learning neural network. I use a module called ImageDataGenerator in keras.preprocessing.image to do data augmentation.
See dataPrepare.ipynb and data.py for detail.
Model
This deep neural network is implemented with Keras functional API, which makes it extremely easy to experiment with different interesting architectures.
Output from the network is a 512*512 which represents mask that should be learned. Sigmoid activation function makes sure that mask pixels are in [0, 1] range.
Training
The model is trained for 5 epochs.
After 5 epochs, calculated accuracy is about 0.97.
Loss function for the training is basically just a binary crossentropy.
How to use
Dependencies
This tutorial depends on the following libraries:
- Tensorflow
- Keras >= 1.0
Also, this code should be compatible with Python versions 2.7-3.5.
Run main.py
You will see the predicted results of test image in data/membrane/test
Or follow notebook trainUnet
Results
Use the trained model to do segmentation on test images, the result is statisfactory.
About Keras
Keras is a minimalist, highly modular neural networks library, written in Python and capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.
Use Keras if you need a deep learning library that:
allows for easy and fast prototyping (through total modularity, minimalism, and extensibility). supports both convolutional networks and recurrent networks, as well as combinations of the two. supports arbitrary connectivity schemes (including multi-input and multi-output training). runs seamlessly on CPU and GPU. Read the documentation Keras.io
Keras is compatible with: Python 2.7-3.5.
ultralytics
ultralytics·Python
YOLO 系列官方实现库，一套 PyTorch 代码覆盖目标检测、实例与语义分割、图像分类、姿态估计和目标跟踪，训练到部署全流程打通。
目标检测+4检测 / 分割入门
63283+10012kv8.4.2102026-11-10 23:12 UTC
yolov5
ultralytics·Python
基于 PyTorch 的目标检测全家桶，覆盖训练、推理、实例分割、图像分类和模型导出，开箱即用，适合快速落地视觉任务。
目标检测+4检测 / 分割进阶
58260+717kv7.02026-11-07 16:59 UTC
pytorch-image-models
huggingface·Python
收录最全的 PyTorch 图像骨干网络合集，涵盖 ResNet、ViT、ConvNeXt 等主流模型，自带训练、评估、推理和导出脚本及预训练权重，省去自己搭网络和找权重的麻烦。
图像分类+4检测 / 分割进阶
37274+95.2kv1.0.312026-11-07 23:22 UTC
detectron2
facebookresearch·Python
Detectron2 是 Facebook 开源的目标检测与分割平台，提供模块化架构和丰富预训练模型，方便快速搭建和训练视觉识别任务。
目标检测+4检测 / 分割进阶
34981+67.9kv0.62026-10-27 09:21 UTC