This chapter contain all details of layer APIs. You can check the content in left side bar.
The basic format of all layers API is referenced by TensorFlow.js.
Usage of Constructor
How to use constructor to create a new layer with the necessary arguments.
If you're looking for the easiest way to create a layer instance, but you don't know which parameters to pass in, this section will help you
Optional Constructor List
This section is a large table that contains all the optional configuration properties, along with samples and utility effects for each property. This section is primarily a reference manual for the list of configurations
In particular, to make it more intuitive for users to go through the list, we use the Tag represent the basic characteristic of argument. You can check Lookup list as follows
|⭐️||Required||Must be provided, cannot be empty. Meanwhile constructor works properly if this arguments provided. Control arguments use default value.|
|🔧||Suggest||Recommended for giving. The API can work without them.|
|⚙️||Optional||As an auxiliary adjustment parameter when used, selectively added according to the specific situation The parameters here have no effect on the structure of the layer (3D visualized form).|
|📦||Model||Configure the properties of the Layer. It changes the output shape.|
|🎨||Style||Override the properties in TSP.model (model configuration)|
|🎦||Animation||Override the properties in TSP.model (model configuration)|
This properties can be accessed on the prototype chain, containing inputShape, outputShape, neuralValue of data, layerType and name set by user.
Properties can be fetched directly through . syntax after the object has been created.
When you use TensorSpace, this method will be useful to be called on the prototype chain, including expand and collapse.
Here is the a table about the layer in TensorFlow, TensorFlow.js, Keras. To help you find which API to use