segmodels-keras 0.1.0.dev1__tar.gz → 0.1.0.dev3__tar.gz

{segmodels_keras-0.1.0.dev1 → segmodels_keras-0.1.0.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: segmodels_keras
-Version: 0.1.0.dev1
+Version: 0.1.0.dev3
 Summary: Image segmentation models with pre-trained backbones with Keras.
 Home-page: https://github.com/orthoseg/segmodels_keras
 Author: Pieter Roggemans

{segmodels_keras-0.1.0.dev1 → segmodels_keras-0.1.0.dev3}/segmodels_keras/_version.py

@@ -1,2 +1,2 @@
-__versioninfo__ = (0, 1, 0, "dev1")
+__versioninfo__ = (0, 1, 0, "dev3")
 __version__ = ".".join(map(str, __versioninfo__))

{segmodels_keras-0.1.0.dev1 → segmodels_keras-0.1.0.dev3}/segmodels_keras/backbones/backbones_factory.py

@@ -125,14 +125,16 @@ class BackbonesFactory:
         "inceptionresnetv2": (
             irv2.InceptionResNetV2,
             irv2.preprocess_input,
-            (
-                "activation_161",
-                "activation_74",
-                "activation_3",
-                "activation",
-                # "input_1",
-            ),
-            # (594, 260, 16, 9),
+            # Use the layer indexes instead of names because otherwise loading weights
+            # saved with keras 2 cannot be loaded with keras 3.
+            # (
+            #     "activation_161",
+            #     "activation_74",
+            #     "activation_3",
+            #     "activation",
+            #     # "input_1",
+            # ),
+            (594, 260, 16, 9),
         ),
         "inceptionv3": (iv3.InceptionV3, iv3.preprocess_input, (228, 86, 16, 9)),
         # MobileNet

{segmodels_keras-0.1.0.dev1 → segmodels_keras-0.1.0.dev3}/segmodels_keras/backbones/inception_resnet_v2.py

@@ -13,7 +13,11 @@ https://github.com/tensorflow/models/tree/master/research/slim#pre-trained-model
 - [Inception-v4, Inception-ResNet and the Impact of
    Residual Connections on Learning](https://arxiv.org/abs/1602.07261) (AAAI 2017)
 
-Differences with the original implementation in keras.applications:
+The differences retained from the segmentation_models version
+(https://github.com/qubvel/segmentation_models/blob/master/segmentation_models/backbones/inception_resnet_v2.py)
+compared to the most recent version in keras.applications
+(https://github.com/keras-team/keras/blob/86d7deacb0ac2baa3e41db4bcd61775065b5a301/keras/src/applications/inception_resnet_v2.py)
+are the following:
 - For e.g. in the `conv2d_bn` blocks, padding="same" is used instead of "valid". This is
   to make the sizes of the outputs of the layers the correct size for the skip
   connections for the decoders in the segmentation models. It does not affect the
@@ -24,8 +28,10 @@ Differences with the original implementation in keras.applications:
   also give issues when loading weights that were saved with an older version. An
   example where this solution is used/shown can be found here:
   https://github.com/ayushdabra/dubai-satellite-imagery-segmentation/blob/9446e16134e752dda080ba9d65be18ea47fa26a9/get_activations.py#L40
-- The original implementation uses different imports as it is internal in keras, and
-  here we need to use the public API of keras.
+- The keras.applications implementation uses different imports as it is internal in
+  keras, and here we need to use the public API of keras.
+- Keep using the Lambda layer instead of CustomScaleLayer to avoid having to pass it in
+  with `custom_objects` when loading the model.
 """
 
 import warnings
@@ -308,20 +314,6 @@ def conv2d_bn(
     return x
 
 
-class CustomScaleLayer(Layer):
-    def __init__(self, scale, **kwargs):
-        super().__init__(**kwargs)
-        self.scale = scale
-
-    def get_config(self):
-        config = super().get_config()
-        config.update({"scale": self.scale})
-        return config
-
-    def call(self, inputs):
-        return inputs[0] + inputs[1] * self.scale
-
-
 def inception_resnet_block(x, scale, block_type, block_idx, activation="relu"):
     """Adds a Inception-ResNet block.
 
@@ -398,9 +390,16 @@ def inception_resnet_block(x, scale, block_type, block_idx, activation="relu"):
         name=f"{block_name}_conv",
     )
 
-    x = CustomScaleLayer(scale)([x, up])
+    x = layers.Lambda(
+        lambda inputs, scale: inputs[0] + inputs[1] * scale,
+        output_shape=x.shape[1:],
+        arguments={"scale": scale},
+        name=block_name,
+    )([x, up])
+
     if activation is not None:
         x = layers.Activation(activation, name=f"{block_name}_ac")(x)
+
     return x
 
 
@@ -502,17 +501,15 @@ def _obtain_input_shape(
         if data_format == "channels_first":
             if input_shape is not None:
                 if len(input_shape) != 3:
-                    raise ValueError(
-                        "`input_shape` must be a tuple of three integers."
-                    )
+                    raise ValueError("`input_shape` must be a tuple of three integers.")
                 if input_shape[0] != 3 and weights == "imagenet":
                     raise ValueError(
                         "The input must have 3 channels; Received "
                         f"`input_shape={input_shape}`"
                     )
-                if (
-                    input_shape[1] is not None and input_shape[1] < min_size
-                ) or (input_shape[2] is not None and input_shape[2] < min_size):
+                if (input_shape[1] is not None and input_shape[1] < min_size) or (
+                    input_shape[2] is not None and input_shape[2] < min_size
+                ):
                     raise ValueError(
                         f"Input size must be at least {min_size}"
                         f"x{min_size}; Received: "
@@ -521,17 +518,15 @@ def _obtain_input_shape(
         else:
             if input_shape is not None:
                 if len(input_shape) != 3:
-                    raise ValueError(
-                        "`input_shape` must be a tuple of three integers."
-                    )
+                    raise ValueError("`input_shape` must be a tuple of three integers.")
                 if input_shape[-1] != 3 and weights == "imagenet":
                     raise ValueError(
                         "The input must have 3 channels; Received "
                         f"`input_shape={input_shape}`"
                     )
-                if (
-                    input_shape[0] is not None and input_shape[0] < min_size
-                ) or (input_shape[1] is not None and input_shape[1] < min_size):
+                if (input_shape[0] is not None and input_shape[0] < min_size) or (
+                    input_shape[1] is not None and input_shape[1] < min_size
+                ):
                     raise ValueError(
                         "Input size must be at least "
                         f"{min_size}x{min_size}; Received: "

{segmodels_keras-0.1.0.dev1 → segmodels_keras-0.1.0.dev3}/segmodels_keras.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: segmodels_keras
-Version: 0.1.0.dev1
+Version: 0.1.0.dev3
 Summary: Image segmentation models with pre-trained backbones with Keras.
 Home-page: https://github.com/orthoseg/segmodels_keras
 Author: Pieter Roggemans