torch_frame.nn.models.ResNet
- class ResNet(channels: int, out_channels: int, num_layers: int, col_stats: dict[str, dict[StatType, Any]], col_names_dict: dict[torch_frame.stype, list[str]], stype_encoder_dict: dict[torch_frame.stype, StypeEncoder] | None = None, normalization: str | None = 'layer_norm', dropout_prob: float = 0.2)[source]
Bases:
Module
The ResNet model introduced in the “Revisiting Deep Learning Models for Tabular Data” paper.
Note
For an example of using ResNet, see examples/revisiting.py.
- Parameters:
channels (int) – The number of channels in the backbone layers.
out_channels (int) – The number of output channels in the decoder.
num_layers (int) – The number of layers in the backbone.
col_stats (dict[str,Dict[
torch_frame.data.stats.StatType
,Any]]) – A dictionary that maps column name into stats. Available asdataset.col_stats
.col_names_dict (dict[
torch_frame.stype
, List[str]]) – A dictionary that maps stype to a list of column names. The column names are sorted based on the ordering that appear intensor_frame.feat_dict
. Available astensor_frame.col_names_dict
.stype_encoder_dict – (dict[
torch_frame.stype
,torch_frame.nn.encoder.StypeEncoder
], optional): A dictionary mapping stypes into their stype encoders. (default:None
, will callEmbeddingEncoder()
for categorical feature andLinearEncoder()
for numerical feature)normalization (str, optional) – The type of normalization to use.
batch_norm
,layer_norm
, orNone
. (default:layer_norm
)dropout_prob (float) – The dropout probability (default: 0.2).
- forward(tf: TensorFrame) Tensor [source]
Transforming
TensorFrame
object into output prediction.- Parameters:
tf (TensorFrame) – Input
TensorFrame
object.- Returns:
Output of shape [batch_size, out_channels].
- Return type: