open3d.ml.tf.models.PointTransformer¶
-
class
open3d.ml.tf.models.PointTransformer(*args, **kwargs)¶ Semantic Segmentation model. Based on PointTransformer architecture https://arxiv.org/pdf/2012.09164.pdf
Uses Encoder-Decoder architecture with Transformer layers.
-
name¶ Name of model. Default to “PointTransformer”.
-
blocks¶ Number of Bottleneck layers.
-
in_channels¶ Number of features(default 6).
-
num_classes¶ Number of classes.
-
voxel_size¶ Voxel length for subsampling.
-
max_voxels¶ Maximum number of voxels.
-
augment¶ dictionary for augmentation.
-
__init__(name='PointTransformer', blocks=[2, 2, 2, 2, 2], in_channels=6, num_classes=13, voxel_size=0.04, max_voxels=80000, augment=None, **kwargs)¶ Initialize self. See help(type(self)) for accurate signature.
-
call(inputs, training=False)¶ Forward pass for the model.
- Parameters
inputs – A dict object for inputs with following keys point (tf.float32): Input pointcloud (N,3) feat (tf.float32): Input features (N, 3) row_splits (tf.int64): row splits for batches (b+1,)
training – training mode of model.
- Returns
Returns the probability distribution.
-
get_batch_gen(dataset, steps_per_epoch=None, batch_size=1)¶
-
get_loss(sem_seg_loss, results, inputs)¶ Calculate the loss on output of the model.
- Parameters
sem_seg_loss – Object of type SemSegLoss.
results – Output of the model.
inputs – Input of the model.
device – device(cpu or cuda).
- Returns
Returns loss, labels and scores.
-
get_optimizer(cfg_pipeline)¶ Returns an optimizer object for the model.
- Parameters
cfg_pipeline – A Config object with the configuration of the pipeline.
- Returns
Returns a new optimizer object.
-
inference_begin(data)¶ Function called right before running inference.
- Parameters
data – A data from the dataset.
-
inference_end(results)¶ This function is called after the inference.
This function can be implemented to apply post-processing on the network outputs.
- Parameters
results – The model outputs as returned by the call() function. Post-processing is applied on this object.
- Returns
Returns True if the inference is complete and otherwise False. Returning False can be used to implement inference for large point clouds which require multiple passes.
-
inference_preprocess()¶ This function prepares the inputs for the model.
- Returns
The inputs to be consumed by the call() function of the model.
-
preprocess(data, attr)¶ Data preprocessing function.
This function is called before training to preprocess the data from a dataset. It consists of subsampling pointcloud with voxelization, augmentation and normalizing the features.
- Parameters
data – A sample from the dataset.
attr – The corresponding attributes.
- Returns
Returns the preprocessed data
-
transform(point, feat, label, splits)¶ Transform function for the point cloud and features.
This function is called after preprocess method by dataset generator. It consists of mapping data to dict.
- Parameters
point – Input pointcloud.
feat – Input features.
label – Input labels.
splits – row_splits defining batches.
- Returns
Returns dictionary data with keys (point, feat, label, row_splits).
-