mlreco.models.layers.common.mobilenet module

class mlreco.models.layers.common.mobilenet.MobileNetV3(cfg, name='mobilenetv3')[source]

Bases: torch.nn.modules.module.Module

Vanilla UResNet with access to intermediate feature planes.

depthint

Depth of UResNet, also corresponds to how many times we down/upsample.

num_filtersint

Number of filters in the first convolution of UResNet. Will increase linearly with depth.

repsint, optional

Convolution block repetition factor

kernel_sizeint, optional

Kernel size for the SC (sparse convolutions for down/upsample).

input_kernelint, optional

Receptive field size for very first convolution after input layer.

__init__(cfg, name='mobilenetv3')[source]

Initializes internal Module state, shared by both nn.Module and ScriptModule.

encoder(x)[source]

Vanilla UResNet Encoder.

INPUTS:

  • x (SparseTensor): MinkowskiEngine SparseTensor

Returns

dictionary of encoder output with intermediate feature planes:

  1. encoderTensors (list): list of intermediate SparseTensors

2) finalTensor (SparseTensor): feature tensor at deepest layer.

Return type

  • result (dict)

decoder(final, encoderTensors)[source]

Vanilla UResNet Decoder INPUTS:

  • encoderTensors (list of SparseTensor): output of encoder.

Returns

list of feature tensors in decoding path at each spatial resolution.

Return type

  • decoderTensors (list of SparseTensor)

forward(input)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

__module__ = 'mlreco.models.layers.common.mobilenet'
training: bool
class mlreco.models.layers.common.mobilenet.MB3Encoder(cfg, name='mobilenetv3_encoder')[source]

Bases: torch.nn.modules.module.Module

Vanilla UResNet with access to intermediate feature planes.

depthint

Depth of UResNet, also corresponds to how many times we down/upsample.

num_filtersint

Number of filters in the first convolution of UResNet. Will increase linearly with depth.

repsint, optional

Convolution block repetition factor

kernel_sizeint, optional

Kernel size for the SC (sparse convolutions for down/upsample).

input_kernelint, optional

Receptive field size for very first convolution after input layer.

__init__(cfg, name='mobilenetv3_encoder')[source]

Initializes internal Module state, shared by both nn.Module and ScriptModule.

__module__ = 'mlreco.models.layers.common.mobilenet'
training: bool
encoder(x)[source]

Vanilla UResNet Encoder.

INPUTS:

  • x (SparseTensor): MinkowskiEngine SparseTensor

Returns

dictionary of encoder output with intermediate feature planes:

  1. encoderTensors (list): list of intermediate SparseTensors

2) finalTensor (SparseTensor): feature tensor at deepest layer.

Return type

  • result (dict)

forward(input)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

mlreco.models.layers.common.gnn_full_chain module mlreco.models.layers.common.momentum module