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,.,.) =
#> 0.4050 -1.1027 0.6417 0.8322 -0.8784 0.6563
#> 0.5468 -0.7310 0.4312 1.3461 -1.9823 -1.0975
#> -0.0835 -0.6281 0.8250 1.4338 -1.0353 0.0304
#> 0.0273 0.5251 0.5885 0.2523 -0.8257 -0.6894
#> 0.1774 1.2543 -0.3262 0.6202 -1.4956 -0.4127
#> 0.2390 -0.6622 -0.1426 0.8725 0.3147 -0.8882
#>
#> (2,1,.,.) =
#> -0.6217 0.5273 0.4822 -0.1031 -0.0281 -0.5784
#> 0.4718 1.0429 0.5135 -0.5013 0.4798 -0.2969
#> 0.7012 1.3080 0.3186 -0.1644 0.3783 1.0006
#> 0.3169 0.9232 -0.0072 -0.8701 -0.1937 0.9416
#> 0.0187 0.0390 0.8367 -0.3835 0.2330 1.2538
#> 0.0071 0.3930 1.1974 0.2176 0.7486 0.1961
#>
#> (1,2,.,.) =
#> 0.4969 -0.2439 -0.1012 -0.1340 -0.0512 -1.0353
#> -0.5335 -0.9099 -0.1829 -0.0847 -0.0763 -0.0411
#> -0.2817 0.1135 0.6154 -0.7394 -0.9292 -0.1604
#> -0.3897 1.5889 -0.0196 0.1458 0.4931 -0.2684
#> 1.5751 0.1273 -0.3152 0.3599 -0.0682 0.0368
#> -0.7287 -0.9366 0.2093 1.1013 0.8797 -0.7175
#>
#> (2,2,.,.) =
#> 0.6743 0.9461 0.2851 -0.1977 0.5018 0.9125
#> 0.5075 0.0129 0.1514 -0.6193 0.3940 0.6797
#> 1.1370 0.5518 0.3224 0.6491 0.0291 -0.5421
#> 0.5263 0.0266 0.6072 0.6653 -0.3403 -0.6022
#> -0.0763 -0.8443 -0.6133 0.2050 -0.1350 -0.4699
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{2,3,6,6} ]