pystiche_papers.gatys_et_al_2017
.. seealso::
:ref:`Paper implementations <impl_params>`
The following parts are affected:
Parameter
impl_params
True
False
layer
"relu4_2"
"conv4_2"
score_weight
1e0
Parameter
impl_params
True
False
layers
("relu1_1", "relu2_1", "relu3_1", "relu4_1", "relu5_1")
("conv1_1", "conv2_1", "conv3_1", "conv4_1", "conv5_1")
layer_weights
(2.4e-04, 6.1e-05, 1.5e-05, 3.8e-06, 3.8e-06)
[1]
score_weight
1e3
[1]
Parameter
impl_params
True
False
layers
("relu1_1", "relu2_1", "relu3_1", "relu4_1", "relu5_1")
("conv1_1", "conv2_1", "conv3_1", "conv4_1", "conv5_1")
layer_weights
(2.4e-04, 6.1e-05, 1.5e-05, 3.8e-06, 3.8e-06)
[1] [2]
region_weights
"sum"
score_weight
1e3
[1]
Parameter
impl_params
True
False
edge_sizes
(500, 1024)
[3]
(512, 1024)
num_steps
[4]
(500, 200)
[1] (1 , 2 , 3 , 4 ) The values are reported in the
supplementary material .
[2] The layer_weights
are computed by 1 / n^2 where n denotes the
number of channels of a feature map from the corresponding layer in the
:func:`~pystiche_papers.gatys_et_al_2017.multi_layer_encoder` .
[3] The paper only reports the edge_size
for the low resolution.
[4] The paper only reports the ratio. i.e. 500 / 200 = 2.5 of num_steps
.
.. automodule:: pystiche_papers.gatys_et_al_2017
.. autofunction:: images
.. autofunction:: content_loss
.. autoclass:: MultiLayerEncodingLoss
.. autofunction:: style_loss
.. autofunction:: guided_style_loss
.. autofunction:: perceptual_loss
.. autofunction:: guided_perceptual_loss
.. autofunction:: nst
.. autofunction:: guided_nst
.. autofunction:: image_pyramid
.. autofunction:: preprocessor
.. autofunction:: postprocessor
.. autofunction:: multi_layer_encoder
.. autofunction:: optimizer
.. autofunction:: compute_layer_weights
.. autofunction:: hyper_parameters