Visualizer for neural network, deep learning, and machine learning models

Overview

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

Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), TensorFlow Lite (.tflite), Caffe (.caffemodel, .prototxt), Darknet (.cfg), Core ML (.mlmodel), MNN (.mnn), MXNet (.model, -symbol.json), ncnn (.param), PaddlePaddle (.zip, __model__), Caffe2 (predict_net.pb), Barracuda (.nn), Tengine (.tmfile), TNN (.tnnproto), RKNN (.rknn), MindSpore Lite (.ms), UFF (.uff).

Netron has experimental support for TensorFlow (.pb, .meta, .pbtxt, .ckpt, .index), PyTorch (.pt, .pth), TorchScript (.pt, .pth), OpenVINO (.xml), Torch (.t7), Arm NN (.armnn), BigDL (.bigdl, .model), Chainer (.npz, .h5), CNTK (.model, .cntk), Deeplearning4j (.zip), MediaPipe (.pbtxt), ML.NET (.zip), scikit-learn (.pkl), TensorFlow.js (model.json, .pb).

Install

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

Linux: Download the .AppImage file or run snap install netron

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

Browser: Start the browser version.

Python Server: Run pip install netron and netron [FILE] or netron.start('[FILE]').

Models

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

Comments
  • Windows app not closing properly

    Windows app not closing properly

    After the latest update, Netron remains open taking up memory and CPU after closing the program. I must close it through task manager each time. I am on Windows 10

    no repro 
    opened by idenc 22
  • TorchScript: ValueError: not enough values to unpack

    TorchScript: ValueError: not enough values to unpack

    • Netron app and version: web app 5.5.9?
    • OS and browser version: Manjaro GNOME on firefox 97.0.1

    Steps to Reproduce:

    1. use torch.broadcast_tensors
    2. export with torch.trace(...).save()
    3. open in netron.app

    I have also gotten a Unsupported function 'torch.broadcast_tensors', but have been unable to reproduce it due to this current error. Most likely, the fix for the following repro will cover two bugs.

    Please attach or link model files to reproduce the issue if necessary.

    image

    Repro:

    import torch
    
    class Test(torch.nn.Module):
        def forward(self, a, b):
            a, b = torch.broadcast_tensors(a, b)
            assert a.shape == b.shape == (3, 5)
            return a + b
    
    torch.jit.trace(
        Test(),
        (torch.ones(3, 1), torch.ones(1, 5)),
    ).save("foobar.pt")
    

    Zipped foobar.pt: foobar.zip

    help wanted bug 
    opened by pbsds 15
  • OpenVINO support

    OpenVINO support

    • [x] 1. Opening rm_lstm4f.xml results in TypeError (#192)
    • [x] 2. dot files are not opened any more - need to fix it (#192)
    • [x] 3. add preflight check for invalid xml and dot content
    • [x] 6. Add test files to ./test/models.json (#195) (#211)
    • [x] 9. Add support for the version 3 of IR (#196)
    • [x] 10. Category color support (#203)
    • [x] 11. -metadata.json for coloring, documentation and attribute default filtering (#203).
    • [x] 5. Filter attribute defaults based on -metadata.json to show fewer attributes in the graph
    • [ ] 7. Show weight tensors
    • [x] 8. Graph inputs and outputs should be exposed as Graph.inputs and Graph.outputs
    • [x] 12. Move to DOMParser
    • [x] 13. Remove dot support
    feature 
    opened by lutzroeder 15
  • RangeError: Maximum call stack size exceeded

    RangeError: Maximum call stack size exceeded

    • Netron app and version: 4.4.8 App and Browser
    • OS and browser version: Windows 10 + Chrome Version 84.0.4147.135

    Steps to Reproduce:

    EfficientDet-d0.zip

    Please attach or link model files to reproduce the issue if necessary.

    help wanted no repro bug 
    opened by ryusaeba 14
  • Debugging Tensorflow Lite Model

    Debugging Tensorflow Lite Model

    Hi there,

    First off, just wanted to say thanks for creating such a great tool - Netron is very useful.

    I'm having an issue that likely stems from Tensorflow, rather than from Netron, but thought you might have some insights. In my flow, I use TF 1.15 to go from .ckpt --> frozen .pb --> .tflite. Normally it works reasonably smoothly, but a recent run shows an issue with the .tflite file: it is created without errors, it runs, but it performs poorly. Opening it with Netron shows that the activation functions (relu6 in this case) have been removed for every layer. Opening the equivalent .pb file in Netron shows the relu6 functions are present.

    Have you seen any cases in which Netron struggled with a TF Lite model (perhaps it can open, but isn't displaying correctly)? Also, how did you figure out the format for .tflite files (perhaps knowing this would allow me to debug it more deeply)?

    Thanks in advance.

    no repro 
    opened by mm7721 12
  • add armnn serialized format support

    add armnn serialized format support

    here's patch to support armnn format. (experimental)

    armnn-schema.js is compiled from ArmnnSchema.fbs included in armNN serailizer.

    see also:

    armnn: https://github.com/ARM-software/armnn

    As mensioned in #363, I will check items in below:

    • [x] Add sample files to test/models.json and run node test/test.js armnn
    • [x] Add tools/armnn script and sync, schema to automate regenerating armnn-schema.js
    • [x] Add tools/armnn script to run as part of ./Makefile
    • [x] Run make lint
    opened by Tee0125 12
  • TorchScript: Argument names to match runtime

    TorchScript: Argument names to match runtime

    Hi, there is some questions about node's name which in pt model saved by TorchScript. I use netron to view my pt model exported by torch.jit.save(),but the node's name doesn't match with it's real name resolved by TorchScript interface. It looks like the names in pt are arranged numerically from smallest to largest,but this is clearly not the case when they are parsed from TorchScript's interface. I wonder how this kind of situation can be solved, thanks a lot !! Looking forward to your reply.

    help wanted 
    opened by daodaoawaker 11
  • Support torch.fx IR visualization using netron

    Support torch.fx IR visualization using netron

    torch.fx is a library in PyTorch 1.8 that allows python-python model transformations. It works by symbolically tracing the PyTorch model into a graph (fx.GraphModule), which can be transformed and finally exported back to code, or used as a nn.Module directly. Currently there is no mechanism to import the graph IR into netron. An indirect path is to export to ONNX to visualize, which is not as useful if debugging transformations that potentially break ONNX exportability. It seems valuable to visualize the traced graph directly in netron.

    feature help wanted no repro 
    opened by sjain-stanford 11
  • TorchScript unsupported functions in after update

    TorchScript unsupported functions in after update

    I have a lot of basic model files saved in TorchScript and they were able to be opened weeks ago. However I cannot many of them after update Netron to v3.9.1. Many common functions are not supported not, e.g. torch.constant_pad_nd, torch.bmm, torch.avg_pool3d.

    opened by lujq96 11
  • OpenVINO IR v10 LSTM support

    OpenVINO IR v10 LSTM support

    • Netron app and version: 4.4.4
    • OS and browser version: Windows 10 64bit

    Steps to Reproduce:

    1. Open OpenVINO IR XML file in netron

    Please attach or link model files to reproduce the issue if necessary.

    I cannot share the proprietary model that shows dozens of disconnected nodes, but the one linked below does show disconnected subgraphs after conversion to OpenVINO IR. Note that the IR generated using the --generate_deprecated_IR_V7 option displays correctly.

    https://github.com/ARM-software/ML-KWS-for-MCU/blob/master/Pretrained_models/Basic_LSTM/Basic_LSTM_S.pb

    Convert using:

    python 'C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo.py' --input_model .\Basic_LSTM_S.pb --input=Reshape:0 --input_shape=[1,490] --output=Output-Layer/add

    This results in the following disconnected graph display:

    image

    no repro external bug 
    opened by mdeisher 10
  • Full support for scikit-learn (joblib)

    Full support for scikit-learn (joblib)

    For recoverable estimator persistence scikit-learn recommends to use joblib (instead of pickle). Sidenote: It is possible to export trained models into ONNX or PMML but the estimators are not recoverable. For more info refer to here.

    bug 
    opened by fkromer 9
  • Export full size image

    Export full size image

    I have onnx file successfully exported from mmsegmentation (swin-transformer), huge model (975.4) MB, I managed to open it in netron, however when I try to export it and preview in full size its blured.

    Any way I can fix it ? Thanks

    no repro bug 
    opened by adrianodac 0
  • TorchScript: torch.jit.mobile.serialization support

    TorchScript: torch.jit.mobile.serialization support

    Export PyTorch model to FlatBuffers file:

    import torch
    import torchvision
    model = torchvision.models.resnet34(weights=torchvision.models.ResNet34_Weights.DEFAULT)
    torch.jit.save_jit_module_to_flatbuffer(torch.jit.script(model), 'resnet34.ff')
    

    Sample files: scriptmodule.ff.zip squeezenet1_1_traced.ff.zip

    feature 
    opened by lutzroeder 0
  • MegEngine: fix some bugs

    MegEngine: fix some bugs

    fix some bugs of megengine C++ model (.mge) visualization:

    1. show the shape of the middle tensor;
    2. fix scope matching model identifier (mgv2) due to possible leading information;

    please help review, thanks~

    opened by Ysllllll 0
  • TorchScript server

    TorchScript server

    import torch
    import torchvision
    import torch.utils.tensorboard
    model = torchvision.models.detection.fasterrcnn_resnet50_fpn()
    script = torch.jit.script(model)
    script.save('fasterrcnn_resnet50_fpn.pt')
    with torch.utils.tensorboard.SummaryWriter('log') as writer:
        writer.add_graph(script, ())
    

    fasterrcnn_resnet50_fpn.pt.zip

    feature 
    opened by lutzroeder 0
Zalo AI challenge 2021 task hum to song

Zalo AI challenge 2021 task Hum to Song pipeline: Chuẩn bị dữ liệu cho quá trình train: Sửa các file đường dẫn trong config/preprocess.yaml raw_path:

Vo Van Phuc 105 Dec 16, 2022
Code for Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data? (SDM 2022)

Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data? (SDM 2022) We consider how a user of a web servi

joisino 20 Aug 21, 2022
LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

This project is based on ultralytics/yolov3. LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image. The related paper is avai

26 Dec 13, 2022
Session-aware Item-combination Recommendation with Transformer Network

Session-aware Item-combination Recommendation with Transformer Network 2nd place (0.39224) code and report for IEEE BigData Cup 2021 Track1 Report EDA

Tzu-Heng Lin 6 Mar 10, 2022
Towards Debiasing NLU Models from Unknown Biases

Towards Debiasing NLU Models from Unknown Biases Abstract: NLU models often exploit biased features to achieve high dataset-specific performance witho

Ubiquitous Knowledge Processing Lab 22 Jun 14, 2022
Nightmare-Writeup - Writeup for the Nightmare CTF Challenge from 2022 DiceCTF

Nightmare: One Byte to ROP // Alternate Solution TLDR: One byte write, no leak.

1 Feb 17, 2022
Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)

CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding (CVPR'22) Paper Link | Project Page Abstract : Manual an

Mohamed Afham 152 Dec 23, 2022
PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

Improving Visual-Semantic Embeddings with Hard Negatives Code for the image-caption retrieval methods from VSE++: Improving Visual-Semantic Embeddings

Fartash Faghri 441 Dec 05, 2022
Code for the CVPR2021 workshop paper "Noise Conditional Flow Model for Learning the Super-Resolution Space"

NCSR: Noise Conditional Flow Model for Learning the Super-Resolution Space Official NCSR training PyTorch Code for the CVPR2021 workshop paper "Noise

57 Oct 03, 2022
PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"

PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"

76 Jan 03, 2023
A framework for GPU based high-performance medical image processing and visualization

FAST is an open-source cross-platform framework with the main goal of making it easier to do high-performance processing and visualization of medical images on heterogeneous systems utilizing both mu

Erik Smistad 315 Dec 30, 2022
Julia package for multiway (inverse) covariance estimation.

TensorGraphicalModels TensorGraphicalModels.jl is a suite of Julia tools for estimating high-dimensional multiway (tensor-variate) covariance and inve

Wayne Wang 3 Sep 23, 2022
Visual Question Answering in Pytorch

Visual Question Answering in pytorch /!\ New version of pytorch for VQA available here: https://github.com/Cadene/block.bootstrap.pytorch This repo wa

Remi 672 Jan 01, 2023
Code image classification of MNIST dataset using different architectures: simple linear NN, autoencoder, and highway network

Deep Learning for image classification pip install -r http://webia.lip6.fr/~baskiotisn/requirements-amal.txt Train an autoencoder python3 train_auto

Hector Kohler 0 Mar 30, 2022
classify fashion-mnist dataset with pytorch

Fashion-Mnist Classifier with PyTorch Inference 1- clone this repository: git clone https://github.com/Jhamed7/Fashion-Mnist-Classifier.git 2- Instal

1 Jan 14, 2022
Official Codes for Graph Modularity:Towards Understanding the Cross-Layer Transition of Feature Representations in Deep Neural Networks.

Dynamic-Graphs-Construction Official Codes for Graph Modularity:Towards Understanding the Cross-Layer Transition of Feature Representations in Deep Ne

11 Dec 14, 2022
Official implementation of ETH-XGaze dataset baseline

ETH-XGaze baseline Official implementation of ETH-XGaze dataset baseline. ETH-XGaze dataset ETH-XGaze dataset is a gaze estimation dataset consisting

Xucong Zhang 134 Jan 03, 2023
CVPR 2022 "Online Convolutional Re-parameterization"

OREPA: Online Convolutional Re-parameterization This repo is the PyTorch implementation of our paper to appear in CVPR2022 on "Online Convolutional Re

Mu Hu 121 Dec 21, 2022
Face detection using deep learning.

Face Detection Docker Solution Using Faster R-CNN Dockerface is a deep learning face detector. It deploys a trained Faster R-CNN network on Caffe thro

Nataniel Ruiz 181 Dec 19, 2022
Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

This repo is the official implementation of "Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework". @inproceedings{zhou2021insta

34 Dec 31, 2022