lutzroeder/netron

在 GitHub 查看

lutzroeder/netron has 33,664 GitHub stars and 3,197 forks. GitHot measured 0 stars in 24 hours, +26 in 7 days, and +60 in 15 days. Last checked 2026-11-07 06:19 UTC. Last push 2026-11-01.

这些数字如何统计

神经网络、深度学习与机器学习模型的可视化工具

33,664 星标 3,197 forks

实测星标增长

24小时: 0
7天: +26
15天: +60
1个月: 正在收集历史

各周期内的星标净变化，周期相互重叠，并非每日新增。缺失的测量保持空白。星标代表关注度，不代表软件质量。

README.md

Netron is a viewer for neural network, deep learning and machine learning models.

Netron supports ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch, TorchScript, TensorFlow, Core ML, OpenVINO, Keras, Caffe, Darknet, Safetensors and NumPy.

Netron has experimental support for MLIR, JAX, GGUF, RKNN, ncnn, MNN, PaddlePaddle and scikit-learn.

Install

Browser: Start the browser version.

macOS: Download the .dmg file or run brew install --cask netron.

Linux: Download the .deb or .rpm file.

Windows: Download the .exe installer or run winget install -s winget netron.

Python: pip install netron, then run netron [FILE] or netron.start('[FILE]').

Models

Sample model files to download or open using the browser version:

ONNX: squeezenet [open]
TorchScript: traced_online_pred_layer [open]
TensorFlow Lite: yamnet [open]
TensorFlow: chessbot [open]
Keras: mobilenet [open]
MLIR: edge_detection [open]
Core ML: exermote [open]
Darknet: yolo [open]

探索相关项目

tensorflow/tensorflow

面向所有人的开源机器学习框架

huggingface/transformers

🤗 Transformers：面向文本、视觉、音频和多模态的最先进机器学习模型的模型定义框架，支持推理与训练。

AUTOMATIC1111/stable-diffusion-webui

Stable Diffusion 网页界面

Comfy-Org/ComfyUI

最强大、模块化程度最高的扩散模型 GUI、API 与后端，采用基于图与节点的界面。全球最快的本地推理引擎。