デモ
TensorFlow.js で作成されたデモとコード例をご覧ください。
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_lip_sync_demo.jpg?authuser=0&hl=ja)
LipSync by YouTube
ヒット曲「ダンス・モンキー」の歌詞にうまく口パクを合わせられるか試してみましょう。このブラウザ上のエクスペリエンスには facemesh モデルが使用されています。唇の周囲にある主要なポイントを推定し、口パクの精度を評価します。
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_emoji.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_webcam.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_teachable.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_move_mirror_demo.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_piano.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_pitch.jpg?authuser=0&hl=ja)
![](https://www.tensorflow.org/static/site-assets/images/marketing/cards/tile_visualize_model_training_demo.png?authuser=0&hl=ja)
コミュニティのデモ
まずは公式テンプレートから始めましょう。コミュニティのおすすめから、アイデアを得られます。
#MadewithTFJS on Twitter
このハッシュタグで、TensorFlow.js を使って作成された新しいプロジェクトに関する最新情報を確認するとともに、自分の持っている情報を共有しましょう。
Example | Input data type | Task type | Model type | Training environment | Inference environment | API type | Demo |
---|---|---|---|---|---|---|---|
abalone-node | Numeric | Loading data from local file and training in Node.js | Multilayer perceptron | Node.js | Node.js | Layers | No demo |
addition-rnn | テキスト | Sequence-to-sequence | RNN: SimpleRNN, GRU and LSTM | Browser | Browser | Layers | View Demo |
addition-rnn-webworker | テキスト | Sequence-to-sequence | RNN: SimpleRNN, GRU and LSTM | Browser: Web Worker | Browser: Web Worker | Layers | No demo |
angular-predictive-prefetching | Numeric | Multiclass predictor | Deep Neural Network | Browser: Service Worker | Browser: Service Worker | Layers | No demo |
baseball-node | Numeric | Multiclass classification | Multilayer perceptron | Node.js | Node.js | Layers | No demo |
boston-housing | Numeric | Regression | Multilayer perceptron | Browser | Browser | Layers | View Demo |
cart-pole | horizontal_rule | 強化学習 | Policy gradient | Browser | Browser | Layers | View Demo |
chrome-extension | Image | (Deploying TF.js in Chrome extension) | Convolutional neural network | horizontal_rule | Browser | horizontal_rule | No demo |
custom-layer | horizontal_rule | (Defining a custom Layer subtype) | horizontal_rule | horizontal_rule | Browser | Layers | View Demo |
data-csv | horizontal_rule | Building a tf.data.Dataset from a remote CSV | horizontal_rule | horizontal_rule | horizontal_rule | horizontal_rule | View Demo |
data-generator | horizontal_rule | Building a tf.data.Dataset using a generator | Regression | Browser | Browser | Layers | View Demo |
date-conversion-attention | テキスト | Text-to-text conversion | Attention mechanism, RNN | Node.js | Browser and Node.js | Layers | View Demo |
electron | Image | (Deploying TF.js in Electron-based desktop apps) | Convolutional neural network | horizontal_rule | Node.js | horizontal_rule | No demo |
fashion-mnist-vae | Image | 生成 | Variational autoencoder | Node.js | Browser | Layers | No demo |
interactive-visualizers | Image | Multiclass classification, object detection, segmentation | horizontal_rule | horizontal_rule | Browser | horizontal_rule | No demo |
iris | Numeric | Multiclass classification | Multilayer perceptron | Browser | Browser | Layers | View Demo |
iris-fitDataset | Sequence-to-sequence | Multiclass classification | Multilayer perceptron | Browser | Browser | Layers | View Demo |
jena-weather | テキスト | Sequence-to-prediction | MLP and RNNs | Browser and Node.js | Browser | Layers | View Demo |
lstm-text-generation | Image | Sequence-to-prediction | RNN: LSTM | Browser | Browser | Layers | View Demo |
mnist | Image | Multiclass classification | Convolutional neural network | Browser | Browser | Layers | View Demo |
mnist-acgan | Image | Generative adversarial network | Convolutional neural network; GAN | Node.js | Browser | Layers | View Demo |
mnist-core | Image | Multiclass classification | Convolutional neural network | Browser | Browser | Core (Ops) | View Demo |
mnist-node | Image | Multiclass classification | Convolutional neural network | Node.js | Node.js | Layers | No demo |
mnist-transfer-cnn | Image | Multiclass classification (transfer learning) | Convolutional neural network | Browser | Browser | Layers | No demo |
mobilenet | Image | Multiclass classification | Convolutional neural network | horizontal_rule | Browser | Layers | View Demo |
polynomial-regression | Numeric | Regression | Shallow neural network | Browser | Browser | Layers | View Demo |
polynomial-regression-core | Numeric | Regression | Shallow neural network | Browser | Browser | Core (Ops) | View Demo |
quantization | Various | Demonstrates the effect of post-training weight quantization | Various | Node.js | Node.js | Layers | No demo |
sentiment | テキスト | Sequence-to-binary-prediction | LSTM, 1D ConvNet | Node.js | Node.js or Python | Layers | View Demo |
simple-object-detection | Image | オブジェクト検出 | Convolutional neural network (transfer learning) | Node.js | Browser | Layers | View Demo |
snake-dqn | horizontal_rule | オブジェクト検出 | Deep Q-Network | Node.js | Browser | Layers | View Demo |
translation | テキスト | Sequence-to-sequence | LSTM encoder and decoder | Node.js or Python | Browser | Layers | View Demo |
tsne-mnist-canvas | horizontal_rule | Dimension reduction and data visualization | tSNE | Browser | Browser | Core (Ops) | No demo |
webcam-transfer-learning | Image | Multiclass classification (transfer learning) | Convolutional neural network | Browser | Browser | Layers | View Demo |
website-phishing | Numeric | Binary classification | Multilayer perceptron | Browser | Browser | Layers | View Demo |