From e69b81bb45c4472ed36f167a7133bb5d23c416c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mustafa=20=C3=87avu=C5=9Fo=C4=9Flu?= <65891055+mustafacavusoglu@users.noreply.github.com> Date: Thu, 31 Aug 2023 10:20:23 +0300 Subject: [PATCH 1/4] Typo Fix: BatchNormalisation -> BatchNormalization --- segmentation_models/models/fpn.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/segmentation_models/models/fpn.py b/segmentation_models/models/fpn.py index deab7f54..2dbd148a 100644 --- a/segmentation_models/models/fpn.py +++ b/segmentation_models/models/fpn.py @@ -204,7 +204,7 @@ def FPN( Each of these layers will be used to build features pyramid. If ``default`` is used layer names are taken from ``DEFAULT_FEATURE_PYRAMID_LAYERS``. pyramid_block_filters: a number of filters in Feature Pyramid Block of FPN_. - pyramid_use_batchnorm: if ``True``, ``BatchNormalisation`` layer between ``Conv2D`` and ``Activation`` layers + pyramid_use_batchnorm: if ``True``, ``BatchNormalization`` layer between ``Conv2D`` and ``Activation`` 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). From 5d785d3ae7b6473f27e64aa19be4ba06ba33053c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mustafa=20=C3=87avu=C5=9Fo=C4=9Flu?= <65891055+mustafacavusoglu@users.noreply.github.com> Date: Thu, 31 Aug 2023 10:21:11 +0300 Subject: [PATCH 2/4] Typo Fix: BatchNormalisation -> BatchNormalization --- segmentation_models/models/linknet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/segmentation_models/models/linknet.py b/segmentation_models/models/linknet.py index 74c533c9..29355ea5 100644 --- a/segmentation_models/models/linknet.py +++ b/segmentation_models/models/linknet.py @@ -219,7 +219,7 @@ def Linknet( 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 as ``None`` value). - decoder_use_batchnorm: if ``True``, ``BatchNormalisation`` layer between ``Conv2D`` and ``Activation`` layers + decoder_use_batchnorm: if ``True``, ``BatchNormalization`` layer between ``Conv2D`` and ``Activation`` layers is used. decoder_block_type: one of - `upsampling`: use ``UpSampling2D`` keras layer From 8863eb3a9c86f01ebd6dba411f3dc55bc7808570 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mustafa=20=C3=87avu=C5=9Fo=C4=9Flu?= <65891055+mustafacavusoglu@users.noreply.github.com> Date: Thu, 31 Aug 2023 10:21:32 +0300 Subject: [PATCH 3/4] Typo Fix: BatchNormalisation -> BatchNormalization --- segmentation_models/models/pspnet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/segmentation_models/models/pspnet.py b/segmentation_models/models/pspnet.py index 001b28c9..44bee5aa 100644 --- a/segmentation_models/models/pspnet.py +++ b/segmentation_models/models/pspnet.py @@ -184,7 +184,7 @@ def PSPNet( 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 between ``Conv2D`` and ``Activation`` layers + psp_use_batchnorm: if ``True``, ``BatchNormalization`` layer between ``Conv2D`` and ``Activation`` layers is used. psp_dropout: dropout rate between 0 and 1. From 4feec38a738315cb2de6482efe03c9da7c79c61b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mustafa=20=C3=87avu=C5=9Fo=C4=9Flu?= <65891055+mustafacavusoglu@users.noreply.github.com> Date: Thu, 31 Aug 2023 10:21:49 +0300 Subject: [PATCH 4/4] Typo Fix: BatchNormalisation -> BatchNormalization --- segmentation_models/models/unet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/segmentation_models/models/unet.py b/segmentation_models/models/unet.py index 7da2b391..0e37ffe2 100644 --- a/segmentation_models/models/unet.py +++ b/segmentation_models/models/unet.py @@ -196,7 +196,7 @@ def Unet( - `transpose`: ``Transpose2D`` -> ``Conv2D`` decoder_filters: list of numbers of ``Conv2D`` layer filters in decoder blocks - decoder_use_batchnorm: if ``True``, ``BatchNormalisation`` layer between ``Conv2D`` and ``Activation`` layers + decoder_use_batchnorm: if ``True``, ``BatchNormalization`` layer between ``Conv2D`` and ``Activation`` layers is used. Returns: