feedInputs for TensorSpace model

[syt123450]

Add feedInputs for model. TensorSpace model load a pre-trained tfjs model for prediction. Pre-trained model may have multi-inputs, however, TensorSpace model may only visualize some of them, use feedInputs to configure it.

For example, ACGAN's generative model, has two inputs random data ( tf.randomNormal([1, 100]) ) and label ( tf.randomNromal([1, 1]) ), if we only want to visualize the random data, we can config model like:

let model = TSP.models.Sequential({
    feedInputs: [ 0 ]
});

0 means the first applied input. In this example, as pre-trained model has two inputs, default to feedInputs: [ 0, 1 ].