SSIM_Multiscale

Inheritance Diagram

Inheritance diagram of ashpy.metrics.ssim_multiscale.SSIM_Multiscale
class ashpy.metrics.ssim_multiscale.SSIM_Multiscale(model_selection_operator=<built-in function lt>, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/v0.1.3/docs/source/log', max_val=2.0, power_factors=None, filter_size=11, filter_sigma=1.5, k1=0.01, k2=0.03)[source]

Bases: ashpy.metrics.metric.Metric

Multiscale Structural Similarity

See Multiscale structural similarity for image quality assessment 1

1

Multiscale structural similarity for image quality assessment https://ieeexplore.ieee.org/document/1292216

Methods

__init__([model_selection_operator, logdir, …])

Initialize the Metric.

split_batch(batch)

Split a batch along axis 0 into two tensors having the same size

update_state(context)

Update the internal state of the metric, using the information from the context object.

Attributes

best_folder

Retrieve the folder used to save the best model when doing model selection.

best_model_sel_file

Retrieve the path to JSON file containing the measured performance of the best model.

logdir

Retrieve the log directory.

metric

Retrieve the tf.keras.metrics.Metric object.

model_selection_operator

Retrieve the operator used for model selection.

name

Retrieve the metric name.
__init__(model_selection_operator=<built-in function lt>, logdir='/home/docs/checkouts/readthedocs.org/user_builds/ashpy/checkouts/v0.1.3/docs/source/log', max_val=2.0, power_factors=None, filter_size=11, filter_sigma=1.5, k1=0.01, k2=0.03)[source]

Initialize the Metric.

Parameters

  • model_selection_operator (typing.Callable) –

    The operation that will be used when model_selection is triggered to compare the metrics, used by the update_state. Any typing.Callable behaving like an operator is accepted.

    Note

    Model selection is done ONLY if an operator is specified here.

  • logdir (str) – Path to the log dir, defaults to a log folder in the current directory.

  • max_val (float) – The dynamic range of the images (i.e., the difference between the maximum the and minimum) (see www.tensorflow.org/versions/r2.0/api_docs/python/tf/image/ssim_multiscale)

  • power_factors (List[float]) – Iterable of weights for each of the scales. The number of scales used is the length of the list. Index 0 is the unscaled resolution’s weight and each increasing scale corresponds to the image being downsampled by 2. Defaults to (0.0448, 0.2856, 0.3001, 0.2363, 0.1333), which are the values obtained in the original paper.

  • filter_size (int) – Default value 11 (size of gaussian filter).

  • filter_sigma (int) – Default value 1.5 (width of gaussian filter).

  • k1 (int) – Default value 0.01

  • k2 (int) – Default value 0.03 (SSIM is less sensitivity to K2 for lower values, so it would be better if we taken the values in range of 0< K2 <0.4).

Return type

None

static split_batch(batch)[source]

Split a batch along axis 0 into two tensors having the same size

Parameters

batch (tf.Tensor) – A batch of images

Return type

Tuple[Tensor, Tensor]

Returns

(Tuple[tf.Tensor, tf.Tensor]) The batch split in two tensors

Raises

ValueError – if the batch has size 1

update_state(context)[source]

Update the internal state of the metric, using the information from the context object.

Parameters

context (ashpy.contexts.GANContext) – An AshPy Context Object that carries all the information the Metric needs.

Return type

None