人間では判定できない101すくみじゃんけんをコンピュータに判定させたい for Keras.js
0 likes523 views
The document discusses Keras.js, a library that allows running Keras models in the browser. Keras.js can load Keras models saved in HDF5 format along with weights and metadata files. It supports running models on the GPU or CPU via WebGL. The document provides an example of using Keras.js to load a model, make a prediction on input data, and log the output. It also links to a GitHub repository with a machine learning rock-paper-scissors demo built with Keras.js.
1 of 19
Download to read offline
More Related Content
What's hot (20)
Ad
More from KatsuyaENDOH (20)
Ad
Recently uploaded (20)
人間では判定できない101すくみじゃんけんをコンピュータに判定させたい for Keras.js
- 3. N
- 12. Keras.js
- 13. Keras.js Tensor ow Keras (GPU !) Keras JSON HDF5 Node.js (CPU ) https://github.com/transcranial/keras-js
- 15. const model = new KerasJS.Model({ filepaths: { model: 'url/path/to/model.json', weights: 'url/path/to/model_weights.buf', metadata: 'url/path/to/model_metadata.json' }, gpu: true })
- 16. model.ready().then( function () { const inputData = { 'input': new Float32Array(testData) }; console.log(inputData); return model.predict(inputData) }).then( function (outputData) { console.log(outputData); } ).catch( function (err) { console.log(err); } );