vp_suite.model_blocks.conv_lstm_hzzone

class ConvLSTM(device, in_channels, enc_channels, state_h, state_w, kernel_size, stride=1, padding=1)

Bases: vp_suite.base.base_model_block.VPModelBlock

This class implements a convolutional LSTM, as introduced in Shi et al. (https://arxiv.org/abs/1506.04214) and implemented in https://github.com/Hzzone/Precipitation-Nowcasting. This is the ‘original’ ConvLSTM.

CODE_REFERENCE = 'https://github.com/Hzzone/Precipitation-Nowcasting'

The code location of the reference implementation.

MATCHES_REFERENCE: str = 'Yes'

A comment indicating whether the implementation in this package matches the reference.

NAME: str = 'ConvLSTM (Shi et al.)'

The clear-text name for this model block.

PAPER_REFERENCE = 'https://arxiv.org/abs/1506.04214'

The publication where this model was introduced first.

__init__(device, in_channels, enc_channels, state_h, state_w, kernel_size, stride=1, padding=1)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(inputs, states, seq_len)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool