Segmentation Models Python API¶
Getting started with segmentation models is easy.
Unet¶
-
segmentation_models.
Unet
(backbone_name='vgg16', input_shape=(None, None, 3), classes=1, activation='sigmoid', weights=None, encoder_weights='imagenet', encoder_freeze=False, encoder_features='default', decoder_block_type='upsampling', decoder_filters=(256, 128, 64, 32, 16), decoder_use_batchnorm=True, **kwargs)¶ Unet is a fully convolution neural network for image semantic segmentation
Parameters: - backbone_name – name of classification model (without last dense layers) used as feature extractor to build segmentation model.
- input_shape – shape of input data/image
(H, W, C)
, in general case you do not need to setH
andW
shapes, just pass(None, None, C)
to make your model be able to process images af any size, butH
andW
of input images should be divisible by factor32
. - classes – a number of classes for output (output shape -
(h, w, classes)
). - activation – name of one of
keras.activations
for last model layer (e.g.sigmoid
,softmax
,linear
). - weights – optional, path to model weights.
- encoder_weights – one of
None
(random initialization),imagenet
(pre-training on ImageNet). - encoder_freeze – if
True
set all layers of encoder (backbone model) as non-trainable. - encoder_features – a list of layer numbers or names starting from top of the model.
Each of these layers will be concatenated with corresponding decoder block. If
default
is used layer names are taken fromDEFAULT_SKIP_CONNECTIONS
. - decoder_block_type –
one of blocks with following layers structure:
- upsampling:
UpSampling2D
->Conv2D
->Conv2D
- transpose:
Transpose2D
->Conv2D
- upsampling:
- decoder_filters – list of numbers of
Conv2D
layer filters in decoder blocks - decoder_use_batchnorm – if
True
,BatchNormalisation
layer betweenConv2D
andActivation
layers is used.
Returns: Unet
Return type: keras.models.Model
Linknet¶
-
segmentation_models.
Linknet
(backbone_name='vgg16', input_shape=(None, None, 3), classes=1, activation='sigmoid', weights=None, encoder_weights='imagenet', encoder_freeze=False, encoder_features='default', decoder_block_type='upsampling', decoder_filters=(None, None, None, None, 16), decoder_use_batchnorm=True, **kwargs)¶ Linknet is a fully convolution neural network for fast image semantic segmentation
Note
This implementation by default has 4 skip connections (original - 3).
Parameters: - backbone_name – name of classification model (without last dense layers) used as feature extractor to build segmentation model.
- input_shape – shape of input data/image
(H, W, C)
, in general case you do not need to setH
andW
shapes, just pass(None, None, C)
to make your model be able to process images af any size, butH
andW
of input images should be divisible by factor32
. - classes – a number of classes for output (output shape -
(h, w, classes)
). - activation – name of one of
keras.activations
for last model layer (e.g.sigmoid
,softmax
,linear
). - weights – optional, path to model weights.
- encoder_weights – one of
None
(random initialization),imagenet
(pre-training on ImageNet). - encoder_freeze – if
True
set all layers of encoder (backbone model) as non-trainable. - encoder_features – a list of layer numbers or names starting from top of the model.
Each of these layers will be concatenated with corresponding decoder block. If
default
is used layer names are taken fromDEFAULT_SKIP_CONNECTIONS
. - decoder_filters – list of numbers of
Conv2D
layer filters in decoder blocks, for block with skip connection a number of filters is equal to number of filters in corresponding encoder block (estimates automatically and can be passed asNone
value). - decoder_use_batchnorm – if
True
,BatchNormalisation
layer betweenConv2D
andActivation
layers is used. - decoder_block_type – one of
- upsampling: use
UpSampling2D
keras layer - transpose: useTranspose2D
keras layer
Returns: Linknet
Return type: keras.models.Model
FPN¶
-
segmentation_models.
FPN
(backbone_name='vgg16', input_shape=(None, None, 3), classes=21, activation='softmax', weights=None, encoder_weights='imagenet', encoder_freeze=False, encoder_features='default', pyramid_block_filters=256, pyramid_use_batchnorm=True, pyramid_aggregation='concat', pyramid_dropout=None, **kwargs)¶ FPN is a fully convolution neural network for image semantic segmentation
Parameters: - backbone_name – name of classification model (without last dense layers) used as feature extractor to build segmentation model.
- input_shape – shape of input data/image
(H, W, C)
, in general case you do not need to setH
andW
shapes, just pass(None, None, C)
to make your model be able to process images af any size, butH
andW
of input images should be divisible by factor32
. - classes – a number of classes for output (output shape -
(h, w, classes)
). - weights – optional, path to model weights.
- activation – name of one of
keras.activations
for last model layer (e.g.sigmoid
,softmax
,linear
). - encoder_weights – one of
None
(random initialization),imagenet
(pre-training on ImageNet). - encoder_freeze – if
True
set all layers of encoder (backbone model) as non-trainable. - encoder_features – a list of layer numbers or names starting from top of the model.
Each of these layers will be used to build features pyramid. If
default
is used layer names are taken fromDEFAULT_FEATURE_PYRAMID_LAYERS
. - pyramid_block_filters – a number of filters in Feature Pyramid Block of FPN.
- pyramid_use_batchnorm – if
True
,BatchNormalisation
layer betweenConv2D
andActivation
layers is used. - pyramid_aggregation – one of ‘sum’ or ‘concat’. The way to aggregate pyramid blocks.
- pyramid_dropout – spatial dropout rate for feature pyramid in range (0, 1).
Returns: FPN
Return type: keras.models.Model
PSPNet¶
-
segmentation_models.
PSPNet
(backbone_name='vgg16', input_shape=(384, 384, 3), classes=21, activation='softmax', weights=None, encoder_weights='imagenet', encoder_freeze=False, downsample_factor=8, psp_conv_filters=512, psp_pooling_type='avg', psp_use_batchnorm=True, psp_dropout=None, **kwargs)¶ PSPNet is a fully convolution neural network for image semantic segmentation
Parameters: - backbone_name – name of classification model used as feature extractor to build segmentation model.
- input_shape – shape of input data/image
(H, W, C)
.H
andW
should be divisible by6 * downsample_factor
and NOTNone
! - classes – a number of classes for output (output shape -
(h, w, classes)
). - activation – name of one of
keras.activations
for last model layer (e.g.sigmoid
,softmax
,linear
). - weights – optional, path to model weights.
- encoder_weights – one of
None
(random initialization),imagenet
(pre-training on ImageNet). - encoder_freeze – if
True
set all layers of encoder (backbone model) as non-trainable. - downsample_factor – one of 4, 8 and 16. Downsampling rate or in other words backbone depth to construct PSP module on it.
- psp_conv_filters – number of filters in
Conv2D
layer in each PSP block. - psp_pooling_type – one of ‘avg’, ‘max’. PSP block pooling type (maximum or average).
- psp_use_batchnorm – if
True
,BatchNormalisation
layer betweenConv2D
andActivation
layers is used. - psp_dropout – dropout rate between 0 and 1.
Returns: PSPNet
Return type: keras.models.Model
metrics¶
-
segmentation_models.metrics.
IOUScore
(class_weights=None, threshold=None, per_image=True, smooth=1e-05)¶ The Jaccard index, also known as Intersection over Union and the Jaccard similarity coefficient (originally coined coefficient de communauté by Paul Jaccard), is a statistic used for comparing the similarity and diversity of sample sets. The Jaccard coefficient measures similarity between finite sample sets, and is defined as the size of the intersection divided by the size of the union of the sample sets:
\[J(A, B) = \frac{A \cap B}{A \cup B}\]Parameters: - class_weights –
- or list of class weights, len(weights) = C
- smooth – value to avoid division by zero
- per_image – if
True
, metric is calculated as mean over images in batch (B), else over whole batch - threshold – value to round predictions (use
>
comparison), ifNone
prediction will not be round
Returns: A callable
iou_score
instance. Can be used inmodel.compile(...)
function.Example:
metric = IOUScore() model.compile('SGD', loss=loss, metrics=[metric])
- class_weights –
-
segmentation_models.metrics.
FScore
(beta=1, class_weights=None, threshold=None, per_image=True, smooth=1e-05)¶ The F-score (Dice coefficient) can be interpreted as a weighted average of the precision and recall, where an F-score reaches its best value at 1 and worst score at 0. The relative contribution of
precision
andrecall
to the F1-score are equal. The formula for the F score is:\[F_\beta(precision, recall) = (1 + \beta^2) \frac{precision \cdot recall} {\beta^2 \cdot precision + recall}\]The formula in terms of Type I and Type II errors:
\[L(tp, fp, fn) = \frac{(1 + \beta^2) \cdot tp} {(1 + \beta^2) \cdot fp + \beta^2 \cdot fn + fp}\]- where:
- tp - true positives;
- fp - false positives;
- fn - false negatives;
Parameters: - beta – f-score coefficient
- class_weights –
- or
np.array
of class weights (len(weights) = num_classes
)
- or
- smooth – value to avoid division by zero
- per_image – if
True
, metric is calculated as mean over images in batch (B), else over whole batch - threshold – value to round predictions (use
>
comparison), ifNone
prediction will not be round
Returns: A callable
f_score
instance. Can be used inmodel.compile(...)
function.Example:
metric = FScore() model.compile('SGD', loss=loss, metrics=[metric])
losses¶
-
segmentation_models.losses.
JaccardLoss
(class_weights=None, per_image=True, smooth=1e-05)¶ Creates a criterion to measure Jaccard loss:
\[L(A, B) = 1 - \frac{A \cap B}{A \cup B}\]Parameters: - class_weights – Array (
np.array
) of class weights (len(weights) = num_classes
). - per_image – If
True
loss is calculated for each image in batch and then averaged, else loss is calculated for the whole batch. - smooth – Value to avoid division by zero.
Returns: A callable
jaccard_loss
instance. Can be used inmodel.compile(...)
function or combined with other losses.Example:
loss = JaccardLoss() model.compile('SGD', loss=loss)
- class_weights – Array (
-
segmentation_models.losses.
DiceLoss
(beta=1, class_weights=None, per_image=True, smooth=1e-05)¶ Creates a criterion to measure Dice loss:
\[L(precision, recall) = 1 - (1 + \beta^2) \frac{precision \cdot recall} {\beta^2 \cdot precision + recall}\]The formula in terms of Type I and Type II errors:
\[L(tp, fp, fn) = \frac{(1 + \beta^2) \cdot tp} {(1 + \beta^2) \cdot fp + \beta^2 \cdot fn + fp}\]- where:
- tp - true positives;
- fp - false positives;
- fn - false negatives;
Parameters: - beta – Float or integer coefficient for precision and recall balance.
- class_weights – Array (
np.array
) of class weights (len(weights) = num_classes
). - per_image – If
True
loss is calculated for each image in batch and then averaged, - loss is calculated for the whole batch. (else) –
- smooth – Value to avoid division by zero.
Returns: A callable
dice_loss
instance. Can be used inmodel.compile(...)
function` or combined with other losses.Example:
loss = DiceLoss() model.compile('SGD', loss=loss)
-
segmentation_models.losses.
BinaryCELoss
()¶ Creates a criterion that measures the Binary Cross Entropy between the ground truth (gt) and the prediction (pr).
\[L(gt, pr) = - gt \cdot \log(pr) - (1 - gt) \cdot \log(1 - pr)\]Returns: A callable binary_crossentropy
instance. Can be used inmodel.compile(...)
function or combined with other losses.Example:
loss = BinaryCELoss() model.compile('SGD', loss=loss)
-
segmentation_models.losses.
CategoricalCELoss
(class_weights=None)¶ Creates a criterion that measures the Categorical Cross Entropy between the ground truth (gt) and the prediction (pr).
\[L(gt, pr) = - gt \cdot \log(pr)\]Returns: A callable categorical_crossentropy
instance. Can be used inmodel.compile(...)
function or combined with other losses.Example:
loss = CategoricalCELoss() model.compile('SGD', loss=loss)
-
segmentation_models.losses.
BinaryFocalLoss
(alpha=0.25, gamma=2.0)¶ Creates a criterion that measures the Binary Focal Loss between the ground truth (gt) and the prediction (pr).
\[L(gt, pr) = - gt \alpha (1 - pr)^\gamma \log(pr) - (1 - gt) \alpha pr^\gamma \log(1 - pr)\]Parameters: - alpha – Float or integer, the same as weighting factor in balanced cross entropy, default 0.25.
- gamma – Float or integer, focusing parameter for modulating factor (1 - p), default 2.0.
Returns: A callable
binary_focal_loss
instance. Can be used inmodel.compile(...)
function or combined with other losses.Example:
loss = BinaryFocalLoss() model.compile('SGD', loss=loss)
-
segmentation_models.losses.
CategoricalFocalLoss
(alpha=0.25, gamma=2.0)¶ Creates a criterion that measures the Categorical Focal Loss between the ground truth (gt) and the prediction (pr).
\[L(gt, pr) = - gt \cdot \alpha \cdot (1 - pr)^\gamma \cdot \log(pr)\]Parameters: - alpha – Float or integer, the same as weighting factor in balanced cross entropy, default 0.25.
- gamma – Float or integer, focusing parameter for modulating factor (1 - p), default 2.0.
Returns: A callable
categorical_focal_loss
instance. Can be used inmodel.compile(...)
function or combined with other losses.Example
loss = CategoricalFocalLoss() model.compile('SGD', loss=loss)
utils¶
-
segmentation_models.utils.
set_trainable
(model, recompile=True, **kwargs)¶ Set all layers of model trainable and recompile it
Note
Model is recompiled using same optimizer, loss and metrics:
model.compile( model.optimizer, loss=model.loss, metrics=model.metrics, loss_weights=model.loss_weights, sample_weight_mode=model.sample_weight_mode, weighted_metrics=model.weighted_metrics, )
Parameters: model ( keras.models.Model
) – instance of keras model