mindflow.cell

API Name	Description	Supported Platforms
`mindflow.cell.AttentionBlock`	AttentionBlock comprises an MultiHeadAttention and an MLP layer.	`Ascend` `CPU`
`mindflow.cell.ConditionDiffusionTransformer`	Conditioned Diffusion Transformer implementation.	`Ascend`
`mindflow.cell.DiffusionTrainer`	Diffusion Trainer base class.	`Ascend`
`mindflow.cell.DiffusionTransformer`	Diffusion model with Transformer backbone implementation.	`Ascend`
`mindflow.cell.DDIMPipeline`	Pipeline for DDIM generation.	`Ascend`
`mindflow.cell.DDIMScheduler`	DDIMScheduler extends the denoising procedure introduced in denoising diffusion probabilistic models.	`Ascend`
`mindflow.cell.DDPMPipeline`	Pipeline for DDPM generation.	`Ascend`
`mindflow.cell.DDPMScheduler`	DDPMScheduler is an implementation of the denoising procedure introduced in denoising diffusion probabilistic models (DDPMs).	`Ascend`
`mindflow.cell.FCSequential`	A sequential container of the dense layers, dense layers are added to the container sequentially.	`Ascend` `GPU`
`mindflow.cell.FNO1D`	The 1D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer.	`Ascend` `GPU`
`mindflow.cell.FNO2D`	The 2D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer.	`Ascend` `GPU`
`mindflow.cell.FNO3D`	The 3D Fourier Neural Operator, which usually contains a Lifting Layer, a Fourier Block Layer and a Projection Layer.	`Ascend` `GPU`
`mindflow.cell.InputScale`	Scale the input value to specified region based on $(x_{i} - i n p u t_c e n t e r) * i n p u t_s c a l e$	`Ascend` `GPU`
`mindflow.cell.LinearBlock`	The LinearBlock.	`Ascend` `GPU`
`mindflow.cell.MultiHeadAttention`	Multi Head Attention proposed in Attention Is All You Need.	`Ascend` `CPU`
`mindflow.cell.MultiScaleFCSequential`	The multi-scale fully conneted network.	`Ascend` `GPU`
`mindflow.cell.PDENet`	The PDE-Net model.	`Ascend` `GPU`
`mindflow.cell.PeRCNN`	Physics-embedded Recurrent Convolutional Neural Network (PeRCNN) Cell.	`Ascend` `GPU`
`mindflow.cell.ResBlock`	The ResBlock of dense layer.	`Ascend` `GPU`
`mindflow.cell.SNO`
`mindflow.cell.SNO1D`	The 1D SNO, which contains a lifting layer (encoder), multiple spectral transform layers and a projection layer (decoder).	`Ascend` `GPU` `CPU`
`mindflow.cell.SNO2D`	The 2D SNO, which contains a lifting layer (encoder), multiple spectral transform layers and a projection layer (decoder).	`Ascend` `GPU` `CPU`
`mindflow.cell.SNO3D`	The 3D SNO, which contains a lifting layer (encoder), multiple spectral transform layers and a projection layer (decoder).	`Ascend` `GPU` `CPU`
`mindflow.cell.UNet2D`	The 2-dimensional U-Net model.	`Ascend` `GPU`
`mindflow.cell.ViT`	This module based on ViT backbone which including encoder, decoding_embedding, decoder and dense layer.	`Ascend` `GPU`
`mindflow.cell.get_activation`	Gets the activation function.	`Ascend` `GPU`