mlr_pipeops_nn_block {mlr3torch} | R Documentation |
Repeat a block n_blocks
times.
The parameters available for the block itself, as well as
n_blocks
:: integer(1)
How often to repeat the block.
The PipeOp
sets its input and output channels to those from the block
(Graph)
it received during construction.
The state is the value calculated by the public method $shapes_out()
.
Part of this documentation have been copied or adapted from the documentation of torch.
mlr3pipelines::PipeOp
-> mlr3torch::PipeOpTorch
-> PipeOpTorchBlock
block
(Graph
)
The neural network segment that is repeated by this PipeOp
.
new()
Creates a new instance of this R6 class.
PipeOpTorchBlock$new(block, id = "nn_block", param_vals = list())
block
(Graph
)
A graph consisting primarily of PipeOpTorch
objects that is to be
repeated.
id
(character(1)
)
The id for of the new object.
param_vals
(named list()
)
Parameter values to be set after construction.
clone()
The objects of this class are cloneable with this method.
PipeOpTorchBlock$clone(deep = FALSE)
deep
Whether to make a deep clone.
Other PipeOps:
mlr_pipeops_nn_avg_pool1d
,
mlr_pipeops_nn_avg_pool2d
,
mlr_pipeops_nn_avg_pool3d
,
mlr_pipeops_nn_batch_norm1d
,
mlr_pipeops_nn_batch_norm2d
,
mlr_pipeops_nn_batch_norm3d
,
mlr_pipeops_nn_celu
,
mlr_pipeops_nn_conv1d
,
mlr_pipeops_nn_conv2d
,
mlr_pipeops_nn_conv3d
,
mlr_pipeops_nn_conv_transpose1d
,
mlr_pipeops_nn_conv_transpose2d
,
mlr_pipeops_nn_conv_transpose3d
,
mlr_pipeops_nn_dropout
,
mlr_pipeops_nn_elu
,
mlr_pipeops_nn_flatten
,
mlr_pipeops_nn_gelu
,
mlr_pipeops_nn_glu
,
mlr_pipeops_nn_hardshrink
,
mlr_pipeops_nn_hardsigmoid
,
mlr_pipeops_nn_hardtanh
,
mlr_pipeops_nn_head
,
mlr_pipeops_nn_layer_norm
,
mlr_pipeops_nn_leaky_relu
,
mlr_pipeops_nn_linear
,
mlr_pipeops_nn_log_sigmoid
,
mlr_pipeops_nn_max_pool1d
,
mlr_pipeops_nn_max_pool2d
,
mlr_pipeops_nn_max_pool3d
,
mlr_pipeops_nn_merge
,
mlr_pipeops_nn_merge_cat
,
mlr_pipeops_nn_merge_prod
,
mlr_pipeops_nn_merge_sum
,
mlr_pipeops_nn_prelu
,
mlr_pipeops_nn_relu
,
mlr_pipeops_nn_relu6
,
mlr_pipeops_nn_reshape
,
mlr_pipeops_nn_rrelu
,
mlr_pipeops_nn_selu
,
mlr_pipeops_nn_sigmoid
,
mlr_pipeops_nn_softmax
,
mlr_pipeops_nn_softplus
,
mlr_pipeops_nn_softshrink
,
mlr_pipeops_nn_softsign
,
mlr_pipeops_nn_squeeze
,
mlr_pipeops_nn_tanh
,
mlr_pipeops_nn_tanhshrink
,
mlr_pipeops_nn_threshold
,
mlr_pipeops_nn_unsqueeze
,
mlr_pipeops_torch_ingress
,
mlr_pipeops_torch_ingress_categ
,
mlr_pipeops_torch_ingress_ltnsr
,
mlr_pipeops_torch_ingress_num
,
mlr_pipeops_torch_loss
,
mlr_pipeops_torch_model
,
mlr_pipeops_torch_model_classif
,
mlr_pipeops_torch_model_regr
block = po("nn_linear") %>>% po("nn_relu")
po_block = po("nn_block", block,
nn_linear.out_features = 10L, n_blocks = 3)
network = po("torch_ingress_num") %>>%
po_block %>>%
po("nn_head") %>>%
po("torch_loss", t_loss("cross_entropy")) %>>%
po("torch_optimizer", t_opt("adam")) %>>%
po("torch_model_classif",
batch_size = 50,
epochs = 3)
task = tsk("iris")
network$train(task)