diff --git a/keras_core/applications/applications_test.py b/keras_core/applications/applications_test.py index 4c7176990..c083ee660 100644 --- a/keras_core/applications/applications_test.py +++ b/keras_core/applications/applications_test.py @@ -4,6 +4,7 @@ from absl.testing import parameterized from keras_core import backend from keras_core import testing +from keras_core.applications import densenet from keras_core.applications import efficientnet from keras_core.applications import efficientnet_v2 from keras_core.applications import mobilenet @@ -47,6 +48,10 @@ MODEL_LIST = [ (efficientnet_v2.EfficientNetV2S, 1280, efficientnet_v2), (efficientnet_v2.EfficientNetV2M, 1280, efficientnet_v2), (efficientnet_v2.EfficientNetV2L, 1280, efficientnet_v2), + # densenet + (densenet.DenseNet121, 1024, densenet), + (densenet.DenseNet169, 1664, densenet), + (densenet.DenseNet201, 1920, densenet), ] # Add names for `named_parameters`. MODEL_LIST = [(e[0].__name__, *e) for e in MODEL_LIST] diff --git a/keras_core/applications/densenet.py b/keras_core/applications/densenet.py new file mode 100644 index 000000000..9f0d8163b --- /dev/null +++ b/keras_core/applications/densenet.py @@ -0,0 +1,482 @@ +from tensorflow.io import gfile + +from keras_core import backend +from keras_core import layers +from keras_core.api_export import keras_core_export +from keras_core.applications import imagenet_utils +from keras_core.models import Functional +from keras_core.operations import operation_utils +from keras_core.utils import file_utils + +BASE_WEIGHTS_PATH = ( + "https://storage.googleapis.com/tensorflow/keras-applications/densenet/" +) +DENSENET121_WEIGHT_PATH = ( + BASE_WEIGHTS_PATH + "densenet121_weights_tf_dim_ordering_tf_kernels.h5" +) +DENSENET121_WEIGHT_PATH_NO_TOP = ( + BASE_WEIGHTS_PATH + + "densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5" +) +DENSENET169_WEIGHT_PATH = ( + BASE_WEIGHTS_PATH + "densenet169_weights_tf_dim_ordering_tf_kernels.h5" +) +DENSENET169_WEIGHT_PATH_NO_TOP = ( + BASE_WEIGHTS_PATH + + "densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5" +) +DENSENET201_WEIGHT_PATH = ( + BASE_WEIGHTS_PATH + "densenet201_weights_tf_dim_ordering_tf_kernels.h5" +) +DENSENET201_WEIGHT_PATH_NO_TOP = ( + BASE_WEIGHTS_PATH + + "densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5" +) + + +def dense_block(x, blocks, name): + """A dense block. + + Args: + x: input tensor. + blocks: integer, the number of building blocks. + name: string, block label. + + Returns: + Output tensor for the block. + """ + for i in range(blocks): + x = conv_block(x, 32, name=name + "_block" + str(i + 1)) + return x + + +def transition_block(x, reduction, name): + """A transition block. + + Args: + x: input tensor. + reduction: float, compression rate at transition layers. + name: string, block label. + + Returns: + Output tensor for the block. + """ + bn_axis = 3 if backend.image_data_format() == "channels_last" else 1 + x = layers.BatchNormalization( + axis=bn_axis, epsilon=1.001e-5, name=name + "_bn" + )(x) + x = layers.Activation("relu", name=name + "_relu")(x) + x = layers.Conv2D( + int(x.shape[bn_axis] * reduction), + 1, + use_bias=False, + name=name + "_conv", + )(x) + x = layers.AveragePooling2D(2, strides=2, name=name + "_pool")(x) + return x + + +def conv_block(x, growth_rate, name): + """A building block for a dense block. + + Args: + x: input tensor. + growth_rate: float, growth rate at dense layers. + name: string, block label. + + Returns: + Output tensor for the block. + """ + bn_axis = 3 if backend.image_data_format() == "channels_last" else 1 + x1 = layers.BatchNormalization( + axis=bn_axis, epsilon=1.001e-5, name=name + "_0_bn" + )(x) + x1 = layers.Activation("relu", name=name + "_0_relu")(x1) + x1 = layers.Conv2D( + 4 * growth_rate, 1, use_bias=False, name=name + "_1_conv" + )(x1) + x1 = layers.BatchNormalization( + axis=bn_axis, epsilon=1.001e-5, name=name + "_1_bn" + )(x1) + x1 = layers.Activation("relu", name=name + "_1_relu")(x1) + x1 = layers.Conv2D( + growth_rate, 3, padding="same", use_bias=False, name=name + "_2_conv" + )(x1) + x = layers.Concatenate(axis=bn_axis, name=name + "_concat")([x, x1]) + return x + + +def DenseNet( + blocks, + include_top=True, + weights="imagenet", + input_tensor=None, + input_shape=None, + pooling=None, + classes=1000, + classifier_activation="softmax", +): + """Instantiates the DenseNet architecture. + + Reference: + - [Densely Connected Convolutional Networks]( + https://arxiv.org/abs/1608.06993) (CVPR 2017) + + This function returns a Keras image classification model, + optionally loaded with weights pre-trained on ImageNet. + + For image classification use cases, see + [this page for detailed examples]( + https://keras.io/api/applications/#usage-examples-for-image-classification-models). + + For transfer learning use cases, make sure to read the + [guide to transfer learning & fine-tuning]( + https://keras.io/guides/transfer_learning/). + + Note: each Keras Application expects a specific kind of input preprocessing. + For DenseNet, call `keras_core.applications.densenet.preprocess_input` + on your inputs before passing them to the model. + `densenet.preprocess_input` will scale pixels between 0 and 1 and then + will normalize each channel with respect to the ImageNet + dataset statistics. + + Args: + blocks: numbers of building blocks for the four dense layers. + include_top: whether to include the fully-connected + layer at the top of the network. + weights: one of `None` (random initialization), + `"imagenet"` (pre-training on ImageNet), + or the path to the weights file to be loaded. + input_tensor: optional Keras tensor + (i.e. output of `layers.Input()`) + to use as image input for the model. + input_shape: optional shape tuple, only to be specified + if `include_top` is False (otherwise the input shape + has to be `(224, 224, 3)` + (with `'channels_last'` data format) + or `(3, 224, 224)` (with `'channels_first'` data format). + It should have exactly 3 inputs channels, + and width and height should be no smaller than 32. + E.g. `(200, 200, 3)` would be one valid value. + pooling: optional pooling mode for feature extraction + when `include_top` is `False`. + - `None` means that the output of the model will be + the 4D tensor output of the + last convolutional block. + - `avg` means that global average pooling + will be applied to the output of the + last convolutional block, and thus + the output of the model will be a 2D tensor. + - `max` means that global max pooling will + be applied. + classes: optional number of classes to classify images + into, only to be specified if `include_top` is `True`, and + if no `weights` argument is specified. + classifier_activation: A `str` or callable. + The activation function to use + on the "top" layer. Ignored unless `include_top=True`. Set + `classifier_activation=None` to return the logits of the "top" + layer. When loading pretrained weights, `classifier_activation` + can only be `None` or `"softmax"`. + + Returns: + A model instance. + """ + if not (weights in {"imagenet", None} or gfile.exists(weights)): + raise ValueError( + "The `weights` argument should be either " + "`None` (random initialization), `imagenet` " + "(pre-training on ImageNet), " + "or the path to the weights file to be loaded." + ) + + if weights == "imagenet" and include_top and classes != 1000: + raise ValueError( + 'If using `weights` as `"imagenet"` with `include_top`' + " as true, `classes` should be 1000" + ) + + # Determine proper input shape + input_shape = imagenet_utils.obtain_input_shape( + input_shape, + default_size=224, + min_size=32, + data_format=backend.image_data_format(), + require_flatten=include_top, + weights=weights, + ) + + if input_tensor is None: + img_input = layers.Input(shape=input_shape) + else: + if not backend.is_keras_tensor(input_tensor): + img_input = layers.Input(tensor=input_tensor, shape=input_shape) + else: + img_input = input_tensor + + bn_axis = 3 if backend.image_data_format() == "channels_last" else 1 + + x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input) + x = layers.Conv2D(64, 7, strides=2, use_bias=False, name="conv1/conv")(x) + x = layers.BatchNormalization( + axis=bn_axis, epsilon=1.001e-5, name="conv1/bn" + )(x) + x = layers.Activation("relu", name="conv1/relu")(x) + x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x) + x = layers.MaxPooling2D(3, strides=2, name="pool1")(x) + + x = dense_block(x, blocks[0], name="conv2") + x = transition_block(x, 0.5, name="pool2") + x = dense_block(x, blocks[1], name="conv3") + x = transition_block(x, 0.5, name="pool3") + x = dense_block(x, blocks[2], name="conv4") + x = transition_block(x, 0.5, name="pool4") + x = dense_block(x, blocks[3], name="conv5") + + x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name="bn")(x) + x = layers.Activation("relu", name="relu")(x) + + if include_top: + x = layers.GlobalAveragePooling2D(name="avg_pool")(x) + + imagenet_utils.validate_activation(classifier_activation, weights) + x = layers.Dense( + classes, activation=classifier_activation, name="predictions" + )(x) + else: + if pooling == "avg": + x = layers.GlobalAveragePooling2D(name="avg_pool")(x) + elif pooling == "max": + x = layers.GlobalMaxPooling2D(name="max_pool")(x) + + # Ensure that the model takes into account + # any potential predecessors of `input_tensor`. + if input_tensor is not None: + inputs = operation_utils.get_source_inputs(input_tensor) + else: + inputs = img_input + + # Create model. + if blocks == [6, 12, 24, 16]: + model = Functional(inputs, x, name="densenet121") + elif blocks == [6, 12, 32, 32]: + model = Functional(inputs, x, name="densenet169") + elif blocks == [6, 12, 48, 32]: + model = Functional(inputs, x, name="densenet201") + else: + model = Functional(inputs, x, name="densenet") + + # Load weights. + if weights == "imagenet": + if include_top: + if blocks == [6, 12, 24, 16]: + weights_path = file_utils.get_file( + "densenet121_weights_tf_dim_ordering_tf_kernels.h5", + DENSENET121_WEIGHT_PATH, + cache_subdir="models", + file_hash="9d60b8095a5708f2dcce2bca79d332c7", + ) + elif blocks == [6, 12, 32, 32]: + weights_path = file_utils.get_file( + "densenet169_weights_tf_dim_ordering_tf_kernels.h5", + DENSENET169_WEIGHT_PATH, + cache_subdir="models", + file_hash="d699b8f76981ab1b30698df4c175e90b", + ) + elif blocks == [6, 12, 48, 32]: + weights_path = file_utils.get_file( + "densenet201_weights_tf_dim_ordering_tf_kernels.h5", + DENSENET201_WEIGHT_PATH, + cache_subdir="models", + file_hash="1ceb130c1ea1b78c3bf6114dbdfd8807", + ) + else: + if blocks == [6, 12, 24, 16]: + weights_path = file_utils.get_file( + "densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5", + DENSENET121_WEIGHT_PATH_NO_TOP, + cache_subdir="models", + file_hash="30ee3e1110167f948a6b9946edeeb738", + ) + elif blocks == [6, 12, 32, 32]: + weights_path = file_utils.get_file( + "densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5", + DENSENET169_WEIGHT_PATH_NO_TOP, + cache_subdir="models", + file_hash="b8c4d4c20dd625c148057b9ff1c1176b", + ) + elif blocks == [6, 12, 48, 32]: + weights_path = file_utils.get_file( + "densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5", + DENSENET201_WEIGHT_PATH_NO_TOP, + cache_subdir="models", + file_hash="c13680b51ded0fb44dff2d8f86ac8bb1", + ) + model.load_weights(weights_path) + elif weights is not None: + model.load_weights(weights) + + return model + + +@keras_core_export( + [ + "keras_core.applications.densenet.DenseNet121", + "keras_core.applications.DenseNet121", + ] +) +def DenseNet121( + include_top=True, + weights="imagenet", + input_tensor=None, + input_shape=None, + pooling=None, + classes=1000, + classifier_activation="softmax", +): + """Instantiates the Densenet121 architecture.""" + return DenseNet( + [6, 12, 24, 16], + include_top, + weights, + input_tensor, + input_shape, + pooling, + classes, + classifier_activation, + ) + + +@keras_core_export( + [ + "keras_core.applications.densenet.DenseNet169", + "keras_core.applications.DenseNet169", + ] +) +def DenseNet169( + include_top=True, + weights="imagenet", + input_tensor=None, + input_shape=None, + pooling=None, + classes=1000, + classifier_activation="softmax", +): + """Instantiates the Densenet169 architecture.""" + return DenseNet( + [6, 12, 32, 32], + include_top, + weights, + input_tensor, + input_shape, + pooling, + classes, + classifier_activation, + ) + + +@keras_core_export( + [ + "keras_core.applications.densenet.DenseNet201", + "keras_core.applications.DenseNet201", + ] +) +def DenseNet201( + include_top=True, + weights="imagenet", + input_tensor=None, + input_shape=None, + pooling=None, + classes=1000, + classifier_activation="softmax", +): + """Instantiates the Densenet201 architecture.""" + return DenseNet( + [6, 12, 48, 32], + include_top, + weights, + input_tensor, + input_shape, + pooling, + classes, + classifier_activation, + ) + + +@keras_core_export("keras_core.applications.densenet.preprocess_input") +def preprocess_input(x, data_format=None): + return imagenet_utils.preprocess_input( + x, data_format=data_format, mode="torch" + ) + + +@keras_core_export("keras_core.applications.densenet.decode_predictions") +def decode_predictions(preds, top=5): + return imagenet_utils.decode_predictions(preds, top=top) + + +preprocess_input.__doc__ = imagenet_utils.PREPROCESS_INPUT_DOC.format( + mode="", + ret=imagenet_utils.PREPROCESS_INPUT_RET_DOC_TORCH, + error=imagenet_utils.PREPROCESS_INPUT_ERROR_DOC, +) +decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__ + +DOC = """ + +Reference: +- [Densely Connected Convolutional Networks]( + https://arxiv.org/abs/1608.06993) (CVPR 2017) + +Optionally loads weights pre-trained on ImageNet. +Note that the data format convention used by the model is +the one specified in your Keras config at `~/.keras/keras.json`. + +Note: each Keras Application expects a specific kind of input preprocessing. +For DenseNet, call `keras_core.applications.densenet.preprocess_input` +on your inputs before passing them to the model. + +Args: + include_top: whether to include the fully-connected + layer at the top of the network. + weights: one of `None` (random initialization), + `"imagenet"` (pre-training on ImageNet), + or the path to the weights file to be loaded. + input_tensor: optional Keras tensor + (i.e. output of `layers.Input()`) + to use as image input for the model. + input_shape: optional shape tuple, only to be specified + if `include_top` is False (otherwise the input shape + has to be `(224, 224, 3)` (with `'channels_last'` data format) + or `(3, 224, 224)` (with `'channels_first'` data format). + It should have exactly 3 inputs channels, + and width and height should be no smaller than 32. + E.g. `(200, 200, 3)` would be one valid value. + pooling: Optional pooling mode for feature extraction + when `include_top` is `False`. + - `None` means that the output of the model will be + the 4D tensor output of the + last convolutional block. + - `avg` means that global average pooling + will be applied to the output of the + last convolutional block, and thus + the output of the model will be a 2D tensor. + - `max` means that global max pooling will + be applied. + classes: optional number of classes to classify images + into, only to be specified if `include_top` is `True`, and + if no `weights` argument is specified. + classifier_activation: A `str` or callable. + The activation function to use + on the "top" layer. Ignored unless `include_top=True`. Set + `classifier_activation=None` to return the logits + of the "top" layer. When loading pretrained weights, + `classifier_activation` can only be `None` or `"softmax"`. + +Returns: + A Keras model instance. +""" + +setattr(DenseNet121, "__doc__", DenseNet121.__doc__ + DOC) +setattr(DenseNet169, "__doc__", DenseNet169.__doc__ + DOC) +setattr(DenseNet201, "__doc__", DenseNet201.__doc__ + DOC) diff --git a/keras_core/layers/merging/concatenate.py b/keras_core/layers/merging/concatenate.py index d686a7bd2..ad71e2905 100644 --- a/keras_core/layers/merging/concatenate.py +++ b/keras_core/layers/merging/concatenate.py @@ -38,7 +38,6 @@ class Concatenate(Merge): self._reshape_required = False def build(self, input_shape): - super().build(input_shape) # Used purely for shape validation. if len(input_shape) < 1 or not isinstance(input_shape[0], tuple): raise ValueError( @@ -77,6 +76,7 @@ class Concatenate(Merge): ) if len(unique_dims) > 1: raise ValueError(err_msg) + self.built = True def _merge_function(self, inputs): return ops.concatenate(inputs, axis=self.axis) diff --git a/keras_core/layers/merging/dot.py b/keras_core/layers/merging/dot.py index 1db48d787..79e54fd0b 100644 --- a/keras_core/layers/merging/dot.py +++ b/keras_core/layers/merging/dot.py @@ -263,7 +263,6 @@ class Dot(Merge): self._reshape_required = False def build(self, input_shape): - super().build(input_shape) # Used purely for shape validation. if not isinstance(input_shape[0], tuple) or len(input_shape) != 2: raise ValueError( @@ -288,6 +287,7 @@ class Dot(Merge): f"{shape2[axes[1]]} (at axis {axes[1]}). " f"Full input shapes: {shape1}, {shape2}" ) + self.built = True def _merge_function(self, inputs): if len(inputs) != 2: