Gated recurrent unit as introduced by Cho et al. There are two variants. The default one is based on 1406.1078v3 and has reset ga…

This layer applies max pooling in a single dimension. Corresponds to the Keras Max Pooling 1D Layer .

This layer applies max pooling in two dimensions. Corresponds to the Keras Max Pooling 2D Layer .

This layer applies max pooling in three dimensions. Corresponds to the Keras Max Pooling 3D Layer .

This layer applies average pooling in a single dimension. Corresponds to the Keras Average Pooling 1D Layer .

This layer applies average pooling in two dimensions. Corresponds to the Keras Average Pooling 2D Layer .

This layer applies average pooling in three dimensions. Corresponds to the Keras Average Pooling 3D Layer .

Gated recurrent unit as introduced by Cho et al. There are two variants. The default one is based on 1406.1078v3 and has reset ga…

The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …

This layer creates a convolution kernel that is convolved with the layer input over two dimensions. Corresponds to the Keras Conv…

This layer creates a convolution kernel that is convolved with the layer input over three dimensions. Corresponds to the Keras Co…

This layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…

This layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …

This layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…

This layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …

The need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …

This layer creates a convolution kernel that is convolved with the layer input over two dimensions. Corresponds to the Keras Conv…

This layer creates a convolution kernel that is convolved with the layer input over three dimensions. Corresponds to the Keras Co…

This layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…

This layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…