trw.layers.layer_config
¶
Module Contents¶
Classes¶
Representation of the normalization layer |
|
Representation of the pooling layer |
|
Representation of the dropout types |
|
Generic configuration of the layers_legacy |
Functions¶
|
Create the norm function from the ops and norm type |
|
Create the norm function from the ops and pool type |
|
Create the norm function from the ops and norm type |
|
Default layer configuration |
- class trw.layers.layer_config.NormType¶
Bases:
enum.Enum
Representation of the normalization layer
- BatchNorm = BatchNorm¶
- InstanceNorm = InstanceNorm¶
- GroupNorm = GroupNorm¶
- SyncBatchNorm = SyncBatchNorm¶
- LocalResponseNorm = LocalResponseNorm¶
- class trw.layers.layer_config.PoolType¶
Bases:
enum.Enum
Representation of the pooling layer
- MaxPool = MaxPool¶
- AvgPool = AvgPool¶
- FractionalMaxPool = FractionalMaxPool¶
- AdaptiveMaxPool = AdaptiveMaxPool¶
- AdaptiveAvgPool = AdaptiveAvgPool¶
- class trw.layers.layer_config.DropoutType¶
Bases:
enum.Enum
Representation of the dropout types
- Dropout1d = Dropout1d¶
- Dropout = Dropout¶
- AlphaDropout = AlphaDropout¶
- trw.layers.layer_config.create_dropout_fn(ops: trw.layers.ops_conversion.OpsConversion, dropout: Optional[DropoutType]) Optional[trw.basic_typing.ModuleCreator] ¶
Create the norm function from the ops and norm type
- Parameters
ops – the operations to be used
dropout – the norm type to create
- Returns
a normalization layer
- trw.layers.layer_config.create_pool_fn(ops: trw.layers.ops_conversion.OpsConversion, pool: Optional[PoolType]) Optional[trw.basic_typing.ModuleCreator] ¶
Create the norm function from the ops and pool type
- Parameters
ops – the operations to be used
pool – the pool type to create
- Returns
a normalization layer
- trw.layers.layer_config.create_norm_fn(ops: trw.layers.ops_conversion.OpsConversion, norm: Optional[NormType]) Optional[trw.basic_typing.ModuleCreator] ¶
Create the norm function from the ops and norm type
- Parameters
ops – the operations to be used
norm – the norm type to create
- Returns
a normalization layer
- class trw.layers.layer_config.LayerConfig(ops: trw.layers.ops_conversion.OpsConversion, norm_type: Optional[NormType] = NormType.BatchNorm, norm_kwargs: Dict = {}, pool_type: Optional[PoolType] = PoolType.MaxPool, pool_kwargs: Dict = {}, activation: Optional[Any] = nn.ReLU, activation_kwargs: Dict = {}, dropout_type: Optional[DropoutType] = DropoutType.Dropout1d, dropout_kwargs: Dict = {}, conv_kwargs: Dict = {'padding': 'same'}, deconv_kwargs: Dict = {'padding': 'same'})¶
Generic configuration of the layers_legacy
- set_dim(self, dimensionality: int)¶
- trw.layers.layer_config.default_layer_config(dimensionality: Optional[int] = None, norm_type: Optional[NormType] = NormType.BatchNorm, norm_kwargs: Dict = {}, pool_type: Optional[PoolType] = PoolType.MaxPool, pool_kwargs: Dict = {}, activation: Optional[Any] = nn.ReLU, activation_kwargs: Dict = {}, dropout_type: Optional[DropoutType] = DropoutType.Dropout1d, dropout_kwargs: Dict = {}, conv_kwargs: Dict = {'padding': 'same'}, deconv_kwargs: Dict = {'padding': 'same'}) LayerConfig ¶
Default layer configuration
- Parameters
dimensionality – the number of dimensions of the input (without the N and C components)
norm_type – the type of normalization
norm_kwargs – additional normalization parameters
activation – the activation
activation_kwargs – additional activation parameters
dropout_kwargs – if not None, dropout parameters
conv_kwargs – additional parameters for the convolutional layer
deconv_kwargs – additional arguments for the transposed convolutional layer
pool_type – the type of pooling
pool_kwargs – additional parameters for the pooling layers_legacy
dropout_type – the type of dropout