[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1923":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":42,"readmeContent":43,"aiSummary":44,"trendingCount":16,"starSnapshotCount":16,"syncStatus":45,"lastSyncTime":46,"discoverSource":47},1923,"netron","lutzroeder\u002Fnetron","lutzroeder","Visualizer for neural network, deep learning and machine learning models","https:\u002F\u002Fnetron.app",null,"JavaScript",33062,3127,319,17,0,3,31,209,21,45,"MIT License",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"ai","coreml","deep-learning","deeplearning","keras","machine-learning","machinelearning","ml","neural-network","numpy","onnx","pytorch","safetensors","tensorflow","tensorflow-lite","visualizer","2026-06-12 02:00:34","\u003Cdiv align=\"center\">\n\u003Cimg width=\"400px\" height=\"100px\" src=\"https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron\u002Fraw\u002Fmain\u002F.github\u002Flogo-light.svg#gh-light-mode-only\">\n\u003Cimg width=\"400px\" height=\"100px\" src=\"https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron\u002Fraw\u002Fmain\u002F.github\u002Flogo-dark.svg#gh-dark-mode-only\">\n\u003C\u002Fdiv>\n\nNetron is a viewer for neural network, deep learning and machine learning models.\n\nNetron supports ONNX, TensorFlow Lite, PyTorch, torch.export, ExecuTorch, Core ML, Keras, Caffe, Darknet, TensorFlow.js, Safetensors and NumPy.\n\nNetron has experimental support for TorchScript, MLIR, TensorFlow, OpenVINO, RKNN, ncnn, MNN, PaddlePaddle, GGUF and scikit-learn.\n\n\u003Cp align='center'>\u003Ca href='https:\u002F\u002Fwww.lutzroeder.com\u002Fai'>\u003Cimg src='.github\u002Fscreenshot.png' width='800'>\u003C\u002Fa>\u003C\u002Fp>\n\n## Install\n\n**Browser**: [**Start**](https:\u002F\u002Fnetron.app) the browser version.\n\n**macOS**: [**Download**](https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron\u002Freleases\u002Flatest) the `.dmg` file or run `brew install --cask netron`.\n\n**Linux**: [**Download**](https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron\u002Freleases\u002Flatest) the `.deb` or `.rpm` file.\n\n**Windows**: [**Download**](https:\u002F\u002Fgithub.com\u002Flutzroeder\u002Fnetron\u002Freleases\u002Flatest) the `.exe` installer or run `winget install -s winget netron`.\n\n**Python**: `pip install netron`, then run `netron [FILE]` or `netron.start('[FILE]')`.\n\n## Models\n\nSample model files to download or open using the browser version:\n\n * **ONNX**: [squeezenet](https:\u002F\u002Fgithub.com\u002Fonnx\u002Fmodels\u002Fraw\u002Fmain\u002Fvalidated\u002Fvision\u002Fclassification\u002Fsqueezenet\u002Fmodel\u002Fsqueezenet1.0-3.onnx) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002Fonnx\u002Fmodels\u002Fraw\u002Fmain\u002Fvalidated\u002Fvision\u002Fclassification\u002Fsqueezenet\u002Fmodel\u002Fsqueezenet1.0-3.onnx)]\n * **TorchScript**: [traced_online_pred_layer](https:\u002F\u002Fgithub.com\u002FApolloAuto\u002Fapollo\u002Fraw\u002Fmaster\u002Fmodules\u002Fprediction\u002Fdata\u002Ftraced_online_pred_layer.pt) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002FApolloAuto\u002Fapollo\u002Fraw\u002Fmaster\u002Fmodules\u002Fprediction\u002Fdata\u002Ftraced_online_pred_layer.pt)]\n * **TensorFlow Lite**: [yamnet](https:\u002F\u002Fhuggingface.co\u002Fthelou1s\u002Fyamnet\u002Fresolve\u002Fmain\u002Flite-model_yamnet_tflite_1.tflite) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fhuggingface.co\u002Fthelou1s\u002Fyamnet\u002Fblob\u002Fmain\u002Flite-model_yamnet_tflite_1.tflite)]\n * **TensorFlow**: [chessbot](https:\u002F\u002Fgithub.com\u002Fsrom\u002Fchessbot\u002Fraw\u002Fmaster\u002Fmodel\u002Fchessbot.pb) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002Fsrom\u002Fchessbot\u002Fraw\u002Fmaster\u002Fmodel\u002Fchessbot.pb)]\n * **Keras**: [mobilenet](https:\u002F\u002Fgithub.com\u002Faio-libs\u002Faiohttp-demos\u002Fraw\u002Fmaster\u002Fdemos\u002Fimagetagger\u002Ftests\u002Fdata\u002Fmobilenet.h5) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002Faio-libs\u002Faiohttp-demos\u002Fraw\u002Fmaster\u002Fdemos\u002Fimagetagger\u002Ftests\u002Fdata\u002Fmobilenet.h5)]\n\n* **MLIR**: [edge_detection](https:\u002F\u002Fgithub.com\u002Firee-org\u002Firee\u002Fraw\u002Fmain\u002Ftests\u002Fe2e\u002Fstablehlo_models\u002Fedge_detection.mlir) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002Firee-org\u002Firee\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Fstablehlo_models\u002Fedge_detection.mlir)]\n\n * **Core ML**: [exermote](https:\u002F\u002Fgithub.com\u002FLausbert\u002FExermote\u002Fraw\u002Fmaster\u002FExermoteInference\u002FExermoteCoreML\u002FExermoteCoreML\u002FModel\u002FExermote.mlmodel) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002FLausbert\u002FExermote\u002Fraw\u002Fmaster\u002FExermoteInference\u002FExermoteCoreML\u002FExermoteCoreML\u002FModel\u002FExermote.mlmodel)]\n * **Darknet**: [yolo](https:\u002F\u002Fgithub.com\u002FAlexeyAB\u002Fdarknet\u002Fraw\u002Fmaster\u002Fcfg\u002Fyolo.cfg) [[open](https:\u002F\u002Fnetron.app?url=https:\u002F\u002Fgithub.com\u002FAlexeyAB\u002Fdarknet\u002Fraw\u002Fmaster\u002Fcfg\u002Fyolo.cfg)]\n","Netron 是一个用于可视化神经网络、深度学习和机器学习模型的工具。它支持多种主流框架如ONNX、TensorFlow Lite、PyTorch等，并且能够解析和展示这些模型的结构与参数，帮助用户更直观地理解模型的工作机制。此外，Netron还提供了对实验性格式的支持，比如TorchScript、MLIR等。此工具非常适合需要调试或教学场景下的模型开发者及研究人员使用，无论是通过浏览器直接访问还是安装桌面应用程序都非常便捷。",2,"2026-06-11 02:46:52","top_all"]