SegNet

Semantic Segmentation Link

SegNetBasic

class chainercv.links.model.segnet.SegNetBasic(n_class=None, pretrained_model=None, initialW=None)

SegNet Basic for semantic segmentation.

This is a SegNet 1 model for semantic segmenation. This is based on SegNetBasic model that is found here.

When you specify the path of a pretrained chainer model serialized as a npz file in the constructor, this chain model automatically initializes all the parameters with it. When a string in prespecified set is provided, a pretrained model is loaded from weights distributed on the Internet. The list of pretrained models supported are as follows:

• camvid: Loads weights trained with the train split of CamVid dataset.

1

Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.” PAMI, 2017

Parameters

• n_class (int) – The number of classes. If None, it can be infered if pretrained_model is given.

• pretrained_model (string) – The destination of the pretrained chainer model serialized as a npz file. If this is one of the strings described above, it automatically loads weights stored under a directory $CHAINER_DATASET_ROOT/pfnet/chainercv/models/, where $CHAINER_DATASET_ROOT is set as $HOME/.chainer/dataset unless you specify another value by modifying the environment variable.

• initialW (callable) – Initializer for convolution layers.

forward(x)

Compute an image-wise score from a batch of images

Parameters

x (chainer.Variable) – A variable with 4D image array.

Returns

An image-wise score. Its channel size is self.n_class.

Return type

chainer.Variable

predict(imgs)

Conduct semantic segmentations from images.

Parameters

imgs (iterable of numpy.ndarray) – Arrays holding images. All images are in CHW and RGB format and the range of their values are \([0, 255]\).

Returns

List of integer labels predicted from each image in the input list.

Return type

list of numpy.ndarray