6bi|8SrSSKJr SSKJr SSKJr SSKrSSKJr SSK J r SSK J r \ "S /S 9"S S \R\ R55r \ "S /S 9S(Sj5r\ "S/S 9"SS\R \ R55r\ "S/S 9S(Sj5r\ "S/S 9"SS\R$\ R55r\ "S/S 9S(Sj5r\ "S/S 9"SS\R(\ R55r\ "S/S 9S(Sj5r\ "S/S 9"SS \R,\ R55r\ "S!/S 9S(S"j5r\ "S#/S 9"S$S%\R0\ R55r\ "S&/S 9S(S'j5r\r\r\r\rg))z@Contains the pooling layer classes and their functional aliases.)absolute_import)division)print_functionN)layers)base) keras_exportz1keras.__internal__.legacy.layers.AveragePooling1D)v1c6^\rSrSrSrSU4SjjrSrU=r$)AveragePooling1DaAverage Pooling layer for 1D inputs. Args: pool_size: An integer or tuple/list of a single integer, representing the size of the pooling window. strides: An integer or tuple/list of a single integer, specifying the strides of the pooling operation. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling1D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.AveragePooling1D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.AveragePooling1D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 gNz$Argument `strides` must not be None. pool_sizestridespadding data_formatname ValueErrorsuper__init__selfrrrrrkwargs __class__s _/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/legacy_tf_layers/pooling.pyrAveragePooling1D.__init__PA ?CD D  #    rvalid channels_lastN__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__ __classcell__rs@rr r .h#    r!r z2keras.__internal__.legacy.layers.average_pooling1dcV[R"SSS9 [UUUUUS9nU"U5$)aAverage Pooling layer for 1D inputs. Args: inputs: The tensor over which to pool. Must have rank 3. pool_size: An integer or tuple/list of a single integer, representing the size of the pooling window. strides: An integer or tuple/list of a single integer, specifying the strides of the pooling operation. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. name: A string, the name of the layer. Returns: The output tensor, of rank 3. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling1D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.average_pooling1d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.AveragePooling1D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.average_pooling1d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.AveragePooling1D` instead. stacklevelr)warningswarnr inputsrrrrrlayers raverage_pooling1dr8esCH MM A     E =r!z-keras.__internal__.legacy.layers.MaxPooling1Dc6^\rSrSrSrSU4SjjrSrU=r$) MaxPooling1DaMax Pooling layer for 1D inputs. Args: pool_size: An integer or tuple/list of a single integer, representing the size of the pooling window. strides: An integer or tuple/list of a single integer, specifying the strides of the pooling operation. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling1D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.MaxPooling1D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.MaxPooling1D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 grrrs rrMaxPooling1D.__init__r r!rr"r%r-s@rr:r:r.r!r:z.keras.__internal__.legacy.layers.max_pooling1dcV[R"SSS9 [UUUUUS9nU"U5$)aMax Pooling layer for 1D inputs. Args: inputs: The tensor over which to pool. Must have rank 3. pool_size: An integer or tuple/list of a single integer, representing the size of the pooling window. strides: An integer or tuple/list of a single integer, specifying the strides of the pooling operation. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch, length, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, length)`. name: A string, the name of the layer. Returns: The output tensor, of rank 3. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling1D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.max_pooling1d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.MaxPooling1D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.max_pooling1d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.MaxPooling1D` instead.r0r1r)r3r4r:r5s r max_pooling1dr?sBH MM =     E =r!z1keras.__internal__.legacy.layers.AveragePooling2Dc6^\rSrSrSrSU4SjjrSrU=r$)AveragePooling2DiTaAverage pooling layer for 2D inputs (e.g. images). Args: pool_size: An integer or tuple/list of 2 integers: (pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling2D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.AveragePooling2D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.AveragePooling2D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 grrrs rrAveragePooling2D.__init__r r!rr"r%r-s@rrArAT2p#    r!rAz2keras.__internal__.legacy.layers.average_pooling2dcV[R"SSS9 [UUUUUS9nU"U5$)aAverage pooling layer for 2D inputs (e.g. images). Args: inputs: The tensor over which to pool. Must have rank 4. pool_size: An integer or tuple/list of 2 integers: (pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. name: A string, the name of the layer. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling2D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.average_pooling2d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.AveragePooling2D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.average_pooling2d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.AveragePooling2D` instead.r0r1r)r3r4rAr5s raverage_pooling2drFsCP MM A     E =r!z-keras.__internal__.legacy.layers.MaxPooling2Dc6^\rSrSrSrSU4SjjrSrU=r$) MaxPooling2Dia{Max pooling layer for 2D inputs (e.g. images). Args: pool_size: An integer or tuple/list of 2 integers: (pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling2D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.MaxPooling2D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.MaxPooling2D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 grrrs rrMaxPooling2D.__init__-r r!rr"r%r-s@rrHrHrDr!rHz.keras.__internal__.legacy.layers.max_pooling2dcV[R"SSS9 [UUUUUS9nU"U5$)aMax pooling layer for 2D inputs (e.g. images). Args: inputs: The tensor over which to pool. Must have rank 4. pool_size: An integer or tuple/list of 2 integers: (pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 2 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, height, width)`. name: A string, the name of the layer. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling2D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.max_pooling2d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.MaxPooling2D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.max_pooling2d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.MaxPooling2D` instead.r0r1r)r3r4rHr5s r max_pooling2drLBsBP MM =     E =r!z1keras.__internal__.legacy.layers.AveragePooling3Dc6^\rSrSrSrSU4SjjrSrU=r$)AveragePooling3DiaAverage pooling layer for 3D inputs (e.g. volumes). Args: pool_size: An integer or tuple/list of 3 integers: (pool_depth, pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling3D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.AveragePooling3D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.AveragePooling3D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 grrrs rrAveragePooling3D.__init__r r!rr"r%r-s@rrNrN4t#    r!rNz2keras.__internal__.legacy.layers.average_pooling3dcV[R"SSS9 [UUUUUS9nU"U5$)aAverage pooling layer for 3D inputs (e.g. volumes). Args: inputs: The tensor over which to pool. Must have rank 5. pool_size: An integer or tuple/list of 3 integers: (pool_depth, pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. name: A string, the name of the layer. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.AveragePooling3D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.average_pooling3d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.AveragePooling3D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.average_pooling3d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.AveragePooling3D` instead.r0r1r)r3r4rNr5s raverage_pooling3drSsCT MM A     E =r!z-keras.__internal__.legacy.layers.MaxPooling3Dc6^\rSrSrSrSU4SjjrSrU=r$) MaxPooling3DiAaMax pooling layer for 3D inputs (e.g. volumes). Args: pool_size: An integer or tuple/list of 3 integers: (pool_depth, pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. name: A string, the name of the layer. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling3D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python pooling = tf.compat.v1.layers.MaxPooling3D(pool_size=2, strides=2) ``` After: ```python pooling = tf.keras.layers.MaxPooling3D(pool_size=2, strides=2) ``` @end_compatibility c N>Uc [S5e[TU]"SUUUUUS.UD6 grrrs rrMaxPooling3D.__init__yr r!rr"r%r-s@rrUrUArQr!rUz.keras.__internal__.legacy.layers.max_pooling3dcV[R"SSS9 [UUUUUS9nU"U5$)aMax pooling layer for 3D inputs (e.g. volumes). Args: inputs: The tensor over which to pool. Must have rank 5. pool_size: An integer or tuple/list of 3 integers: (pool_depth, pool_height, pool_width) specifying the size of the pooling window. Can be a single integer to specify the same value for all spatial dimensions. strides: An integer or tuple/list of 3 integers, specifying the strides of the pooling operation. Can be a single integer to specify the same value for all spatial dimensions. padding: A string. The padding method, either 'valid' or 'same'. Case-insensitive. data_format: A string. The ordering of the dimensions in the inputs. `channels_last` (default) and `channels_first` are supported. `channels_last` corresponds to inputs with shape `(batch, depth, height, width, channels)` while `channels_first` corresponds to inputs with shape `(batch, channels, depth, height, width)`. name: A string, the name of the layer. Returns: Output tensor. Raises: ValueError: if eager execution is enabled. @compatibility(TF2) This API is a legacy api that is only compatible with eager execution and `tf.function` if you combine it with `tf.compat.v1.keras.utils.track_tf1_style_variables` Please refer to [tf.layers model mapping section of the migration guide] (https://www.tensorflow.org/guide/migrate/model_mapping) to learn how to use your TensorFlow v1 model in TF2 with TF-Keras. The corresponding TensorFlow v2 layer is `tf.keras.layers.MaxPooling3D`. #### Structural Mapping to Native TF2 None of the supported arguments have changed name. Before: ```python y = tf.compat.v1.layers.max_pooling3d(x, pool_size=2, strides=2) ``` After: To migrate code using TF1 functional layers use the [Keras Functional API] (https://www.tensorflow.org/guide/tf_keras/functional): ```python x = tf.keras.Input((28, 28, 1)) y = tf.keras.layers.MaxPooling3D(pool_size=2, strides=2)(x) model = tf.keras.Model(x, y) ``` @end_compatibility z`tf.layers.max_pooling3d` is deprecated and will be removed in a future version. Please use `tf.keras.layers.MaxPooling3D` instead.r0r1r)r3r4rUr5s r max_pooling3drYsBR MM =     E =r!r")r* __future__rrrr3 tf_keras.srcr keras_layerstf_keras.src.legacy_tf_layersr tensorflow.python.util.tf_exportrr Layerr8r:r?rArFrHrLrNrSrUrY AvgPool2D MaxPool2D max_pool2d avg_pool2drr!rrds~ G&%/.:EFGC |44djjC HC LFGH  PIPfABCC <,,djjC DC LBCD  PEPfEFGG |44djjG HG TFGH  TITnABCG <,,djjG DG TBCD  TETnEFGI |44djjI HI XFGH  VIVrABCI <,,djjI DI XBCD  UEUt     r!