{ "info": { "author": "TensorSpace Team", "author_email": "tensorspaceteam@gmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 1 - Planning", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Science/Research", "License :: OSI Approved :: Apache Software License", "Programming Language :: JavaScript", "Programming Language :: Python :: 2", "Programming Language :: Python :: 3", "Topic :: Scientific/Engineering", "Topic :: Scientific/Engineering :: Artificial Intelligence", "Topic :: Scientific/Engineering :: Mathematics", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Python Modules" ], "description": "
\n
\n
\nEnglish | \u4e2d\u6587\n
\n\n\nAbout TensorSpace \ud83e\udd14: TensorSpace Github\n
\n\n\n\nTensorSpace-Converter is a tool used to generate a TensorSpace compatible model from a pre-trained model built by TensorFlow, Keras and TensorFlow.js. TensorSpace-Converter includes the functions of: extracting information from hidden layers, matching intermediate data based on the configurations and exporting preprocessed TensorSpace compatible model. TensorSpace simplifies the preprocess and helps developers to focus on the development of model visualization.\n\n## Table of Content\n\n* [Motivation](#motivation)\n* [Getting Started](#start)\n * [Install](#install)\n * [Usage](#usage)\n* [Running with Docker](#docker)\n* [Converter API](#api)\n* [Converter Usage Examples](#examples)\n * [TensorFlow](#tensorflow)\n * [Keras](#keras)\n * [TensorFlow.js](#tensorflowjs)\n* [Development](#development)\n* [Contributors](#contributors)\n* [Contact](#contact)\n* [License](#license)\n\n##\n
\n
\nFig. 1 - TensorSpace-Converter Usage\n
\n\n##\n
\n
\nFig. 2 - TensorSpace-Converter Workflow\n
\n\n#### Step 1: Use TensorSpace-Converter to preprocess pre-trained model\n\nTensorSpace-Converter will convert an input model into a multi-output model, checkout this [article](https://tensorspace.org/html/docs/preIntro.html) for more information about multi-output model and model preprocessing. \n\n```shell\n$ tensorspacejs_converter \\\n --input_model_from=\"tensorflow\" \\\n --input_model_format=\"tf_keras\" \\\n --output_layer_names=\"conv_1,maxpool_1,conv_2,maxpool_2,dense_1,dense_2,softmax\" \\\n ./PATH/TO/MODEL/tf_keras_model.h5 \\\n ./PATH/TO/SAVE/DIR\n```\n\n\n
\n
\nFig. 3 - converted multi-output model\n
\n\n#### Step 2: Apply TensorSpace for model visualization\n\n```javascript\nmodel.load({\n type: \"tensorflow\",\n url: \"/PATH/TO/MODEL/model.json\"\n});\n```\n\n\n
\n
\nFig. 4 - LeNet Visualization\n
\n\n##\n
\n
\n
\n
\n
\n
\n
\n