Ingress for a single lazy_tensor column.
Parameters
shape::integer()|NULL|"infer"
The shape of the tensor, where the first dimension (batch) must beNA. When it is not specified, the lazy tensor input column needs to have a known shape. When it is set to"infer", the shape is inferred from an example batch.
Input and Output Channels
One input channel called "input" and one output channel called "output".
For an explanation see PipeOpTorch.
See also
Other PipeOps:
mlr_pipeops_nn_adaptive_avg_pool1d,
mlr_pipeops_nn_adaptive_avg_pool2d,
mlr_pipeops_nn_adaptive_avg_pool3d,
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_block,
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_ft_cls,
mlr_pipeops_nn_geglu,
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_identity,
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_reglu,
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_tokenizer_categ,
mlr_pipeops_nn_tokenizer_num,
mlr_pipeops_nn_unsqueeze,
mlr_pipeops_torch_ingress,
mlr_pipeops_torch_ingress_categ,
mlr_pipeops_torch_ingress_num,
mlr_pipeops_torch_loss,
mlr_pipeops_torch_model,
mlr_pipeops_torch_model_classif,
mlr_pipeops_torch_model_regr
Other Graph Network:
ModelDescriptor(),
TorchIngressToken(),
mlr_learners_torch_model,
mlr_pipeops_module,
mlr_pipeops_torch,
mlr_pipeops_torch_ingress,
mlr_pipeops_torch_ingress_categ,
mlr_pipeops_torch_ingress_num,
model_descriptor_to_learner(),
model_descriptor_to_module(),
model_descriptor_union(),
nn_graph()
Super classes
mlr3pipelines::PipeOp -> mlr3torch::PipeOpTorchIngress -> PipeOpTorchIngressLazyTensor
Methods
Method new()
Creates a new instance of this R6 class.
Usage
PipeOpTorchIngressLazyTensor$new(
id = "torch_ingress_ltnsr",
param_vals = list()
)Arguments
id(
character(1))
Identifier of the resulting object.param_vals(
list())
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction.
Examples
po_ingress = po("torch_ingress_ltnsr")
task = tsk("lazy_iris")
md = po_ingress$train(list(task))[[1L]]
ingress = md$ingress
x_batch = ingress[[1L]]$batchgetter(data = task$data(1, "x"), cache = NULL)
x_batch
#> torch_tensor
#> 5.1000 3.5000 1.4000 0.2000
#> [ CPUFloatType{1,4} ]
# Now we try a lazy tensor with unknown shape, i.e. the shapes between the rows can differ
ds = dataset(
initialize = function() self$x = list(torch_randn(3, 10, 10), torch_randn(3, 8, 8)),
.getitem = function(i) list(x = self$x[[i]]),
.length = function() 2)()
task_unknown = as_task_regr(data.table(
x = as_lazy_tensor(ds, dataset_shapes = list(x = NULL)),
y = rnorm(2)
), target = "y", id = "example2")
# this task (as it is) can NOT be processed by PipeOpTorchIngressLazyTensor
# It therefore needs to be preprocessed
po_resize = po("trafo_resize", size = c(6, 6))
task_unknown_resize = po_resize$train(list(task_unknown))[[1L]]
# printing the transformed column still shows unknown shapes,
# because the preprocessing pipeop cannot infer them,
# however we know that the shape is now (3, 10, 10) for all rows
task_unknown_resize$data(1:2, "x")
#> x
#> <lazy_tensor>
#> 1: <tnsr[]>
#> 2: <tnsr[]>
po_ingress$param_set$set_values(shape = c(NA, 3, 6, 6))
md2 = po_ingress$train(list(task_unknown_resize))[[1L]]
ingress2 = md2$ingress
x_batch2 = ingress2[[1L]]$batchgetter(
data = task_unknown_resize$data(1:2, "x"),
cache = NULL
)
x_batch2
#> torch_tensor
#> (1,1,.,.) =
#> 0.1429 0.6060 -0.1367 -0.1423 -0.3589 0.3601
#> 0.6447 0.5635 -0.4174 -0.2986 -1.4100 -0.0520
#> -0.4055 -0.7032 0.6515 0.0701 -0.9616 -0.5564
#> 0.2518 0.4698 -0.2232 0.2935 1.0947 0.0485
#> 0.7657 0.3982 0.1345 0.7697 -0.4583 -1.0288
#> -0.3101 -0.3415 -1.1483 -0.7909 -0.7900 -0.2217
#>
#> (2,1,.,.) =
#> 0.6854 -0.1737 -0.6508 0.1081 -0.0739 0.1163
#> 1.0744 -0.1783 -0.8385 -0.7435 0.4896 -0.6768
#> 0.7492 -0.6389 -1.3307 -0.5887 -0.4642 -0.9855
#> 1.4973 -0.8472 -0.1724 -0.1378 -1.1936 -0.8533
#> 0.5686 -0.5603 0.1931 -0.9314 -0.4579 0.1818
#> 0.4349 1.0978 -0.2194 -0.4418 -0.0982 0.2969
#>
#> (1,2,.,.) =
#> -0.5221 -0.1983 0.1939 -0.8390 -0.3913 0.2012
#> 1.1904 -2.2536 0.4041 0.3487 0.7309 1.1197
#> -0.1744 0.1363 -0.3780 0.3967 0.6181 0.0648
#> 0.6620 0.6584 -0.4082 -0.1056 -0.4960 -0.3865
#> -0.6390 0.1946 -0.4941 0.3461 1.3342 -1.0890
#> 0.7345 0.5748 0.6175 0.2039 -0.2023 0.2817
#>
#> (2,2,.,.) =
#> -0.1077 0.1588 1.9025 1.6584 -0.0752 -0.4695
#> 0.3839 0.2202 0.4835 -0.3239 -1.0335 -0.8727
#> 0.8401 -0.5630 0.5178 -0.0417 -0.0122 0.8314
#> -0.3048 -0.2981 -0.1696 0.2417 -0.5846 -0.1651
#> -0.7550 -0.7362 -1.0507 0.0607 0.4245 -0.3796
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{2,3,6,6} ]