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_ft_transformer_block
,
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,.,.) =
#> -0.1591 -0.0373 -0.5276 0.3484 -0.2633 -0.8719
#> -1.2758 0.8287 -0.5748 -0.1102 -0.6849 0.6116
#> 0.3008 0.4174 0.8262 -0.0147 0.0733 0.5093
#> -0.1226 1.2597 -0.1016 -0.8207 0.7705 -0.0613
#> 0.3762 1.2275 0.4520 0.6847 -0.0991 0.1996
#> 0.3894 -0.1423 -0.9474 -0.4182 -0.4854 1.1556
#>
#> (2,1,.,.) =
#> -0.4824 0.7364 2.5017 -0.5698 -0.3112 -0.4884
#> 0.8915 0.1622 0.2159 0.0342 -0.6658 -0.7226
#> 0.1038 0.5041 0.5580 -0.1288 0.6155 -0.1746
#> -0.1330 -0.5063 0.0987 -0.5467 -0.9229 0.8990
#> -1.2983 -0.0711 -1.3266 -0.4710 -0.1074 0.6741
#> 1.2523 0.1727 -0.8014 -1.2477 1.3194 -0.2595
#>
#> (1,2,.,.) =
#> 0.1699 -0.5428 -0.1023 0.2284 -0.6291 1.0429
#> 0.8201 0.3818 -0.2014 1.7740 0.6350 0.5770
#> -0.3044 1.3574 0.9402 0.5956 -1.0345 -0.6575
#> -0.0547 -0.2553 -0.5989 -0.0656 -0.0947 -0.3671
#> 1.0449 -0.8892 -0.3385 0.8756 1.6308 0.7791
#> -1.4454 0.1280 0.8319 0.4147 -0.9732 0.1682
#>
#> (2,2,.,.) =
#> -0.3763 -0.4274 -0.1365 -0.5724 0.1778 0.6315
#> 0.1619 0.6429 0.0121 1.3598 -0.2833 0.1456
#> 0.3777 0.7204 -0.7640 -0.4519 -0.1345 0.3015
#> 0.3672 -0.1110 0.5987 0.7851 0.3000 -0.0044
#> -1.0375 -0.4362 0.9820 0.7790 0.5227 -0.6400
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{2,3,6,6} ]