mindflow.cell
API Name |
Description |
Supported Platforms |
A sequential container of the dense layers, dense layers are added to the container sequentially. |
|
|
The 1D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer. |
|
|
The 2D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer. |
|
|
The 3D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer. |
|
|
Scale the input value to specified region based on \((x_i - input\_center)*input\_scale\) |
|
|
The LinearBlock. |
|
|
The multi-scale fully conneted network. |
|
|
The PDE-Net model. |
|
|
Recurrent convolutional neural network Cell. |
|
|
The ResBlock of dense layer. |
|
|
The 2-dimensional U-Net model. |
|
|
This module based on ViT backbone which including encoder, decoding_embedding, decoder and dense layer. |
|
|
Gets the activation function. |
|