ttnn.upsample

ttnn.upsample(input_tensor: ttnn.Tensor, scale_factor: int or tt::tt_metal::Array2D, *, memory_config: ttnn.MemoryConfig | None = None) → ttnn.Tensor

Upsamples a given multi-channel 2D (spatial) data. The input data is assumed to be of the form [N, H, W, C].

The algorithms available for upsampling are ‘nearest’ for now.

Parameters:

• input_tensor (ttnn.Tensor) – the input tensor.

• scale_factor (int or tt::tt_metal::Array2D) – multiplier for spatial size.

Keyword Arguments:

memory_config (ttnn.MemoryConfig, optional) – Memory configuration for the operation. Defaults to None.

Returns:

ttnn.Tensor – the output tensor.