# open3d.ml.tf.models.SparseConvUnet¶

class open3d.ml.tf.models.SparseConvUnet(*args, **kwargs)

Semantic Segmentation model.

Uses UNet architecture replacing convolutions with Sparse Convolutions.

name

Name of model. Default to “SparseConvUnet”.

device

Which device to use (cpu or cuda).

voxel_size

Voxel length for subsampling.

multiplier

min length of feature length in each layer.

conv_block_reps

repetition of Unet Blocks.

residual_blocks

Whether to use Residual Blocks.

in_channels

Number of features(default 3 for color).

num_classes

Number of classes.

__init__(name='SparseConvUnet', device='cuda', multiplier=16, voxel_size=0.05, conv_block_reps=1, residual_blocks=False, in_channels=3, num_classes=20, grid_size=4096, augment=None, **kwargs)

Initialize self. See help(type(self)) for accurate signature.

call(inputs, training=False)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Note: This method should not be called directly. It is only meant to be overridden when subclassing tf.keras.Model. To call a model on an input, always use the __call__() method, i.e. model(inputs), which relies on the underlying call() method.

Parameters
• inputs – Input tensor, or dict/list/tuple of input tensors.

• training – Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.

A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide

Returns

A tensor if there is a single output, or a list of tensors if there are more than one outputs.

get_batch_gen(dataset, steps_per_epoch=None, batch_size=1)
get_loss(Loss, results, inputs)

Calculate the loss on output of the model.

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.

Parameters
• data – A sample from the dataset.

• attr – The corresponding attributes.

Returns

Returns the preprocessed data

transform(point, feat, label, lengths)

Transform function for the point cloud and features.

Parameters

args – A list of tf Tensors.