Add convnext, inception models
This commit is contained in:
parent
61e94375b0
commit
785c83b25a
@ -4,15 +4,19 @@ from absl.testing import parameterized
|
||||
|
||||
from keras_core import backend
|
||||
from keras_core import testing
|
||||
from keras_core.applications import convnext
|
||||
from keras_core.applications import densenet
|
||||
from keras_core.applications import efficientnet
|
||||
from keras_core.applications import efficientnet_v2
|
||||
from keras_core.applications import inception_resnet_v2
|
||||
from keras_core.applications import inception_v3
|
||||
from keras_core.applications import mobilenet
|
||||
from keras_core.applications import mobilenet_v2
|
||||
from keras_core.applications import mobilenet_v3
|
||||
from keras_core.applications import vgg16
|
||||
from keras_core.applications import vgg19
|
||||
from keras_core.applications import xception
|
||||
from keras_core.saving import serialization_lib
|
||||
from keras_core.utils import file_utils
|
||||
from keras_core.utils import image_utils
|
||||
|
||||
@ -27,7 +31,10 @@ MODEL_LIST = [
|
||||
(vgg19.VGG19, 512, vgg19),
|
||||
# xception
|
||||
(xception.Xception, 2048, xception),
|
||||
# mobilnet
|
||||
# inception
|
||||
(inception_v3.InceptionV3, 2048, inception_v3),
|
||||
(inception_resnet_v2.InceptionResNetV2, 1536, inception_resnet_v2),
|
||||
# mobilenet
|
||||
(mobilenet.MobileNet, 1024, mobilenet),
|
||||
(mobilenet_v2.MobileNetV2, 1280, mobilenet_v2),
|
||||
(mobilenet_v3.MobileNetV3Small, 576, mobilenet_v3),
|
||||
@ -52,6 +59,12 @@ MODEL_LIST = [
|
||||
(densenet.DenseNet121, 1024, densenet),
|
||||
(densenet.DenseNet169, 1664, densenet),
|
||||
(densenet.DenseNet201, 1920, densenet),
|
||||
# convnext
|
||||
(convnext.ConvNeXtTiny, 768, convnext),
|
||||
(convnext.ConvNeXtSmall, 768, convnext),
|
||||
(convnext.ConvNeXtBase, 1024, convnext),
|
||||
(convnext.ConvNeXtLarge, 1536, convnext),
|
||||
(convnext.ConvNeXtXLarge, 2048, convnext),
|
||||
]
|
||||
# Add names for `named_parameters`.
|
||||
MODEL_LIST = [(e[0].__name__, *e) for e in MODEL_LIST]
|
||||
@ -111,8 +124,8 @@ class ApplicationsTest(testing.TestCase, parameterized.TestCase):
|
||||
self.assertIn("African_elephant", names[:3])
|
||||
|
||||
# Can be serialized and deserialized
|
||||
config = model.get_config()
|
||||
reconstructed_model = model.__class__.from_config(config)
|
||||
config = serialization_lib.serialize_keras_object(model)
|
||||
reconstructed_model = serialization_lib.deserialize_keras_object(config)
|
||||
self.assertEqual(len(model.weights), len(reconstructed_model.weights))
|
||||
|
||||
@parameterized.named_parameters(MODEL_LIST)
|
||||
|
752
keras_core/applications/convnext.py
Normal file
752
keras_core/applications/convnext.py
Normal file
@ -0,0 +1,752 @@
|
||||
import numpy as np
|
||||
from tensorflow.io import gfile
|
||||
|
||||
from keras_core import backend
|
||||
from keras_core import initializers
|
||||
from keras_core import layers
|
||||
from keras_core import operations as ops
|
||||
from keras_core import random
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.applications import imagenet_utils
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.models import Functional
|
||||
from keras_core.models import Sequential
|
||||
from keras_core.operations import operation_utils
|
||||
from keras_core.utils import file_utils
|
||||
|
||||
BASE_WEIGHTS_PATH = (
|
||||
"https://storage.googleapis.com/tensorflow/keras-applications/convnext/"
|
||||
)
|
||||
|
||||
WEIGHTS_HASHES = {
|
||||
"convnext_tiny": (
|
||||
"8ae6e78ce2933352b1ef4008e6dd2f17bc40771563877d156bc6426c7cf503ff",
|
||||
"d547c096cabd03329d7be5562c5e14798aa39ed24b474157cef5e85ab9e49ef1",
|
||||
),
|
||||
"convnext_small": (
|
||||
"ce1277d8f1ee5a0ef0e171469089c18f5233860ceaf9b168049cb9263fd7483c",
|
||||
"6fc8009faa2f00c1c1dfce59feea9b0745eb260a7dd11bee65c8e20843da6eab",
|
||||
),
|
||||
"convnext_base": (
|
||||
"52cbb006d3dadd03f6e095a8ca1aca47aecdd75acb4bc74bce1f5c695d0086e6",
|
||||
"40a20c5548a5e9202f69735ecc06c990e6b7c9d2de39f0361e27baeb24cb7c45",
|
||||
),
|
||||
"convnext_large": (
|
||||
"070c5ed9ed289581e477741d3b34beffa920db8cf590899d6d2c67fba2a198a6",
|
||||
"96f02b6f0753d4f543261bc9d09bed650f24dd6bc02ddde3066135b63d23a1cd",
|
||||
),
|
||||
"convnext_xlarge": (
|
||||
"c1f5ccab661354fc3a79a10fa99af82f0fbf10ec65cb894a3ae0815f17a889ee",
|
||||
"de3f8a54174130e0cecdc71583354753d557fcf1f4487331558e2a16ba0cfe05",
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
MODEL_CONFIGS = {
|
||||
"tiny": {
|
||||
"depths": [3, 3, 9, 3],
|
||||
"projection_dims": [96, 192, 384, 768],
|
||||
"default_size": 224,
|
||||
},
|
||||
"small": {
|
||||
"depths": [3, 3, 27, 3],
|
||||
"projection_dims": [96, 192, 384, 768],
|
||||
"default_size": 224,
|
||||
},
|
||||
"base": {
|
||||
"depths": [3, 3, 27, 3],
|
||||
"projection_dims": [128, 256, 512, 1024],
|
||||
"default_size": 224,
|
||||
},
|
||||
"large": {
|
||||
"depths": [3, 3, 27, 3],
|
||||
"projection_dims": [192, 384, 768, 1536],
|
||||
"default_size": 224,
|
||||
},
|
||||
"xlarge": {
|
||||
"depths": [3, 3, 27, 3],
|
||||
"projection_dims": [256, 512, 1024, 2048],
|
||||
"default_size": 224,
|
||||
},
|
||||
}
|
||||
|
||||
BASE_DOCSTRING = """Instantiates the {name} architecture.
|
||||
|
||||
References:
|
||||
- [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
|
||||
(CVPR 2022)
|
||||
|
||||
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/).
|
||||
|
||||
The `base`, `large`, and `xlarge` models were first pre-trained on the
|
||||
ImageNet-21k dataset and then fine-tuned on the ImageNet-1k dataset. The
|
||||
pre-trained parameters of the models were assembled from the
|
||||
[official repository](https://github.com/facebookresearch/ConvNeXt). To get a
|
||||
sense of how these parameters were converted to Keras compatible parameters,
|
||||
please refer to
|
||||
[this repository](https://github.com/sayakpaul/keras-convnext-conversion).
|
||||
|
||||
Note: Each Keras Application expects a specific kind of input preprocessing.
|
||||
For ConvNeXt, preprocessing is included in the model using a `Normalization`
|
||||
layer. ConvNeXt models expect their inputs to be float or uint8 tensors of
|
||||
pixels with values in the [0-255] range.
|
||||
|
||||
When calling the `summary()` method after instantiating a ConvNeXt model,
|
||||
prefer setting the `expand_nested` argument `summary()` to `True` to better
|
||||
investigate the instantiated model.
|
||||
|
||||
Args:
|
||||
include_top: Whether to include the fully-connected
|
||||
layer at the top of the network. Defaults to `True`.
|
||||
weights: One of `None` (random initialization),
|
||||
`"imagenet"` (pre-training on ImageNet-1k), or the path to the weights
|
||||
file to be loaded. Defaults to `"imagenet"`.
|
||||
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`.
|
||||
It should have exactly 3 inputs channels.
|
||||
pooling: Optional pooling mode for feature extraction
|
||||
when `include_top` is `False`. Defaults to None.
|
||||
- `None` means that the output of the model will be
|
||||
the 4D tensor output of the last convolutional layer.
|
||||
- `avg` means that global average pooling
|
||||
will be applied to the output of the
|
||||
last convolutional layer, 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. Defaults to 1000 (number of
|
||||
ImageNet classes).
|
||||
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.
|
||||
Defaults to `"softmax"`.
|
||||
When loading pretrained weights, `classifier_activation` can only
|
||||
be `None` or `"softmax"`.
|
||||
|
||||
Returns:
|
||||
A model instance.
|
||||
"""
|
||||
|
||||
|
||||
class StochasticDepth(Layer):
|
||||
"""Stochastic Depth module.
|
||||
|
||||
It performs batch-wise dropping rather than sample-wise. In libraries like
|
||||
`timm`, it's similar to `DropPath` layers that drops residual paths
|
||||
sample-wise.
|
||||
|
||||
References:
|
||||
- https://github.com/rwightman/pytorch-image-models
|
||||
|
||||
Args:
|
||||
drop_path_rate (float): Probability of dropping paths. Should be within
|
||||
[0, 1].
|
||||
|
||||
Returns:
|
||||
Tensor either with the residual path dropped or kept.
|
||||
"""
|
||||
|
||||
def __init__(self, drop_path_rate, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.drop_path_rate = drop_path_rate
|
||||
|
||||
def call(self, x, training=None):
|
||||
if training:
|
||||
keep_prob = 1 - self.drop_path_rate
|
||||
shape = (ops.shape(x)[0],) + (1,) * (len(ops.shape(x)) - 1)
|
||||
random_tensor = keep_prob + random.uniform(shape, 0, 1)
|
||||
random_tensor = ops.floor(random_tensor)
|
||||
return (x / keep_prob) * random_tensor
|
||||
return x
|
||||
|
||||
def get_config(self):
|
||||
config = super().get_config()
|
||||
config.update({"drop_path_rate": self.drop_path_rate})
|
||||
return config
|
||||
|
||||
|
||||
class LayerScale(Layer):
|
||||
"""Layer scale module.
|
||||
|
||||
References:
|
||||
|
||||
- https://arxiv.org/abs/2103.17239
|
||||
|
||||
Args:
|
||||
init_values (float): Initial value for layer scale. Should be within
|
||||
[0, 1].
|
||||
projection_dim (int): Projection dimensionality.
|
||||
|
||||
Returns:
|
||||
Tensor multiplied to the scale.
|
||||
"""
|
||||
|
||||
def __init__(self, init_values, projection_dim, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.init_values = init_values
|
||||
self.projection_dim = projection_dim
|
||||
|
||||
def build(self, _):
|
||||
self.gamma = self.add_weight(
|
||||
shape=(self.projection_dim,),
|
||||
initializer=initializers.Constant(self.init_values),
|
||||
trainable=True,
|
||||
)
|
||||
|
||||
def call(self, x):
|
||||
return x * self.gamma
|
||||
|
||||
def get_config(self):
|
||||
config = super().get_config()
|
||||
config.update(
|
||||
{
|
||||
"init_values": self.init_values,
|
||||
"projection_dim": self.projection_dim,
|
||||
}
|
||||
)
|
||||
return config
|
||||
|
||||
|
||||
def ConvNeXtBlock(
|
||||
projection_dim, drop_path_rate=0.0, layer_scale_init_value=1e-6, name=None
|
||||
):
|
||||
"""ConvNeXt block.
|
||||
|
||||
References:
|
||||
- https://arxiv.org/abs/2201.03545
|
||||
- https://github.com/facebookresearch/ConvNeXt/blob/main/models/convnext.py
|
||||
|
||||
Notes:
|
||||
In the original ConvNeXt implementation (linked above), the authors use
|
||||
`Dense` layers for pointwise convolutions for increased efficiency.
|
||||
Following that, this implementation also uses the same.
|
||||
|
||||
Args:
|
||||
projection_dim (int): Number of filters for convolution layers. In the
|
||||
ConvNeXt paper, this is referred to as projection dimension.
|
||||
drop_path_rate (float): Probability of dropping paths. Should be within
|
||||
[0, 1].
|
||||
layer_scale_init_value (float): Layer scale value.
|
||||
Should be a small float number.
|
||||
name: name to path to the keras layer.
|
||||
|
||||
Returns:
|
||||
A function representing a ConvNeXtBlock block.
|
||||
"""
|
||||
if name is None:
|
||||
name = "prestem" + str(backend.get_uid("prestem"))
|
||||
|
||||
def apply(inputs):
|
||||
x = inputs
|
||||
|
||||
x = layers.Conv2D(
|
||||
filters=projection_dim,
|
||||
kernel_size=7,
|
||||
padding="same",
|
||||
groups=projection_dim,
|
||||
name=name + "_depthwise_conv",
|
||||
)(x)
|
||||
x = layers.LayerNormalization(epsilon=1e-6, name=name + "_layernorm")(x)
|
||||
x = layers.Dense(4 * projection_dim, name=name + "_pointwise_conv_1")(x)
|
||||
x = layers.Activation("gelu", name=name + "_gelu")(x)
|
||||
x = layers.Dense(projection_dim, name=name + "_pointwise_conv_2")(x)
|
||||
|
||||
if layer_scale_init_value is not None:
|
||||
x = LayerScale(
|
||||
layer_scale_init_value,
|
||||
projection_dim,
|
||||
name=name + "_layer_scale",
|
||||
)(x)
|
||||
if drop_path_rate:
|
||||
layer = StochasticDepth(
|
||||
drop_path_rate, name=name + "_stochastic_depth"
|
||||
)
|
||||
else:
|
||||
layer = layers.Activation("linear", name=name + "_identity")
|
||||
|
||||
return inputs + layer(x)
|
||||
|
||||
return apply
|
||||
|
||||
|
||||
def PreStem(name=None):
|
||||
"""Normalizes inputs with ImageNet-1k mean and std."""
|
||||
if name is None:
|
||||
name = "prestem" + str(backend.get_uid("prestem"))
|
||||
|
||||
def apply(x):
|
||||
x = layers.Normalization(
|
||||
mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
|
||||
variance=[
|
||||
(0.229 * 255) ** 2,
|
||||
(0.224 * 255) ** 2,
|
||||
(0.225 * 255) ** 2,
|
||||
],
|
||||
name=name + "_prestem_normalization",
|
||||
)(x)
|
||||
return x
|
||||
|
||||
return apply
|
||||
|
||||
|
||||
def Head(num_classes=1000, classifier_activation=None, name=None):
|
||||
"""Implementation of classification head of ConvNeXt.
|
||||
|
||||
Args:
|
||||
num_classes: number of classes for Dense layer
|
||||
classifier_activation: activation function for the Dense layer
|
||||
name: name prefix
|
||||
|
||||
Returns:
|
||||
Classification head function.
|
||||
"""
|
||||
if name is None:
|
||||
name = str(backend.get_uid("head"))
|
||||
|
||||
def apply(x):
|
||||
x = layers.GlobalAveragePooling2D(name=name + "_head_gap")(x)
|
||||
x = layers.LayerNormalization(
|
||||
epsilon=1e-6, name=name + "_head_layernorm"
|
||||
)(x)
|
||||
x = layers.Dense(
|
||||
num_classes,
|
||||
activation=classifier_activation,
|
||||
name=name + "_head_dense",
|
||||
)(x)
|
||||
return x
|
||||
|
||||
return apply
|
||||
|
||||
|
||||
def ConvNeXt(
|
||||
depths,
|
||||
projection_dims,
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=224,
|
||||
model_name="convnext",
|
||||
include_preprocessing=True,
|
||||
include_top=True,
|
||||
weights=None,
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
"""Instantiates ConvNeXt architecture given specific configuration.
|
||||
|
||||
Args:
|
||||
depths: An iterable containing depths for each individual stages.
|
||||
projection_dims: An iterable containing output number of channels of
|
||||
each individual stages.
|
||||
drop_path_rate: Stochastic depth probability. If 0.0, then stochastic
|
||||
depth won't be used.
|
||||
layer_scale_init_value: Layer scale coefficient. If 0.0, layer scaling
|
||||
won't be used.
|
||||
default_size: Default input image size.
|
||||
model_name: An optional name for the model.
|
||||
include_preprocessing: boolean denoting whther to
|
||||
include preprocessing in the model.
|
||||
When `weights="imagenet"` this should always be `True`.
|
||||
But for other models (e.g., randomly initialized) you should set it
|
||||
to `False` and apply preprocessing to data accordingly.
|
||||
include_top: Boolean denoting whether to include classification
|
||||
head to the model.
|
||||
weights: one of `None` (random initialization), `"imagenet"`
|
||||
(pre-training on ImageNet-1k),
|
||||
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`. It should have exactly 3 inputs channels.
|
||||
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 layer.
|
||||
- `avg` means that global average pooling will be applied
|
||||
to the output of the last convolutional layer,
|
||||
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.
|
||||
|
||||
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="imagenet"` with `include_top=True`, '
|
||||
"`classes` should be 1000. "
|
||||
f"Received classes={classes}"
|
||||
)
|
||||
|
||||
# Determine proper input shape.
|
||||
input_shape = imagenet_utils.obtain_input_shape(
|
||||
input_shape,
|
||||
default_size=default_size,
|
||||
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
|
||||
|
||||
if input_tensor is not None:
|
||||
inputs = operation_utils.get_source_inputs(input_tensor)[0]
|
||||
else:
|
||||
inputs = img_input
|
||||
|
||||
x = inputs
|
||||
if include_preprocessing:
|
||||
channel_axis = (
|
||||
3 if backend.image_data_format() == "channels_last" else 1
|
||||
)
|
||||
num_channels = input_shape[channel_axis - 1]
|
||||
if num_channels == 3:
|
||||
x = PreStem(name=model_name)(x)
|
||||
|
||||
# Stem block.
|
||||
stem = Sequential(
|
||||
[
|
||||
layers.Conv2D(
|
||||
projection_dims[0],
|
||||
kernel_size=4,
|
||||
strides=4,
|
||||
name=model_name + "_stem_conv",
|
||||
),
|
||||
layers.LayerNormalization(
|
||||
epsilon=1e-6, name=model_name + "_stem_layernorm"
|
||||
),
|
||||
],
|
||||
name=model_name + "_stem",
|
||||
)
|
||||
|
||||
# Downsampling blocks.
|
||||
downsample_layers = []
|
||||
downsample_layers.append(stem)
|
||||
|
||||
num_downsample_layers = 3
|
||||
for i in range(num_downsample_layers):
|
||||
downsample_layer = Sequential(
|
||||
[
|
||||
layers.LayerNormalization(
|
||||
epsilon=1e-6,
|
||||
name=model_name + "_downsampling_layernorm_" + str(i),
|
||||
),
|
||||
layers.Conv2D(
|
||||
projection_dims[i + 1],
|
||||
kernel_size=2,
|
||||
strides=2,
|
||||
name=model_name + "_downsampling_conv_" + str(i),
|
||||
),
|
||||
],
|
||||
name=model_name + "_downsampling_block_" + str(i),
|
||||
)
|
||||
downsample_layers.append(downsample_layer)
|
||||
|
||||
# Stochastic depth schedule.
|
||||
# This is referred from the original ConvNeXt codebase:
|
||||
# https://github.com/facebookresearch/ConvNeXt/blob/main/models/convnext.py#L86
|
||||
depth_drop_rates = [
|
||||
float(x) for x in np.linspace(0.0, drop_path_rate, sum(depths))
|
||||
]
|
||||
|
||||
# First apply downsampling blocks and then apply ConvNeXt stages.
|
||||
cur = 0
|
||||
|
||||
num_convnext_blocks = 4
|
||||
for i in range(num_convnext_blocks):
|
||||
x = downsample_layers[i](x)
|
||||
for j in range(depths[i]):
|
||||
x = ConvNeXtBlock(
|
||||
projection_dim=projection_dims[i],
|
||||
drop_path_rate=depth_drop_rates[cur + j],
|
||||
layer_scale_init_value=layer_scale_init_value,
|
||||
name=model_name + f"_stage_{i}_block_{j}",
|
||||
)(x)
|
||||
cur += depths[i]
|
||||
|
||||
if include_top:
|
||||
imagenet_utils.validate_activation(classifier_activation, weights)
|
||||
x = Head(
|
||||
num_classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
name=model_name,
|
||||
)(x)
|
||||
|
||||
else:
|
||||
if pooling == "avg":
|
||||
x = layers.GlobalAveragePooling2D()(x)
|
||||
elif pooling == "max":
|
||||
x = layers.GlobalMaxPooling2D()(x)
|
||||
x = layers.LayerNormalization(epsilon=1e-6)(x)
|
||||
|
||||
model = Functional(inputs=inputs, outputs=x, name=model_name)
|
||||
|
||||
# Load weights.
|
||||
if weights == "imagenet":
|
||||
if include_top:
|
||||
file_suffix = ".h5"
|
||||
file_hash = WEIGHTS_HASHES[model_name][0]
|
||||
else:
|
||||
file_suffix = "_notop.h5"
|
||||
file_hash = WEIGHTS_HASHES[model_name][1]
|
||||
file_name = model_name + file_suffix
|
||||
weights_path = file_utils.get_file(
|
||||
file_name,
|
||||
BASE_WEIGHTS_PATH + file_name,
|
||||
cache_subdir="models",
|
||||
file_hash=file_hash,
|
||||
)
|
||||
model.load_weights(weights_path)
|
||||
elif weights is not None:
|
||||
model.load_weights(weights)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
## Instantiating variants ##
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.convnext.ConvNeXtTiny",
|
||||
"keras_core.applications.ConvNeXtTiny",
|
||||
]
|
||||
)
|
||||
def ConvNeXtTiny(
|
||||
model_name="convnext_tiny",
|
||||
include_top=True,
|
||||
include_preprocessing=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
return ConvNeXt(
|
||||
depths=MODEL_CONFIGS["tiny"]["depths"],
|
||||
projection_dims=MODEL_CONFIGS["tiny"]["projection_dims"],
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=MODEL_CONFIGS["tiny"]["default_size"],
|
||||
model_name=model_name,
|
||||
include_top=include_top,
|
||||
include_preprocessing=include_preprocessing,
|
||||
weights=weights,
|
||||
input_tensor=input_tensor,
|
||||
input_shape=input_shape,
|
||||
pooling=pooling,
|
||||
classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.convnext.ConvNeXtSmall",
|
||||
"keras_core.applications.ConvNeXtSmall",
|
||||
]
|
||||
)
|
||||
def ConvNeXtSmall(
|
||||
model_name="convnext_small",
|
||||
include_top=True,
|
||||
include_preprocessing=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
return ConvNeXt(
|
||||
depths=MODEL_CONFIGS["small"]["depths"],
|
||||
projection_dims=MODEL_CONFIGS["small"]["projection_dims"],
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=MODEL_CONFIGS["small"]["default_size"],
|
||||
model_name=model_name,
|
||||
include_top=include_top,
|
||||
include_preprocessing=include_preprocessing,
|
||||
weights=weights,
|
||||
input_tensor=input_tensor,
|
||||
input_shape=input_shape,
|
||||
pooling=pooling,
|
||||
classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.convnext.ConvNeXtBase",
|
||||
"keras_core.applications.ConvNeXtBase",
|
||||
]
|
||||
)
|
||||
def ConvNeXtBase(
|
||||
model_name="convnext_base",
|
||||
include_top=True,
|
||||
include_preprocessing=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
return ConvNeXt(
|
||||
depths=MODEL_CONFIGS["base"]["depths"],
|
||||
projection_dims=MODEL_CONFIGS["base"]["projection_dims"],
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=MODEL_CONFIGS["base"]["default_size"],
|
||||
model_name=model_name,
|
||||
include_top=include_top,
|
||||
include_preprocessing=include_preprocessing,
|
||||
weights=weights,
|
||||
input_tensor=input_tensor,
|
||||
input_shape=input_shape,
|
||||
pooling=pooling,
|
||||
classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.convnext.ConvNeXtLarge",
|
||||
"keras_core.applications.ConvNeXtLarge",
|
||||
]
|
||||
)
|
||||
def ConvNeXtLarge(
|
||||
model_name="convnext_large",
|
||||
include_top=True,
|
||||
include_preprocessing=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
return ConvNeXt(
|
||||
depths=MODEL_CONFIGS["large"]["depths"],
|
||||
projection_dims=MODEL_CONFIGS["large"]["projection_dims"],
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=MODEL_CONFIGS["large"]["default_size"],
|
||||
model_name=model_name,
|
||||
include_top=include_top,
|
||||
include_preprocessing=include_preprocessing,
|
||||
weights=weights,
|
||||
input_tensor=input_tensor,
|
||||
input_shape=input_shape,
|
||||
pooling=pooling,
|
||||
classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.convnext.ConvNeXtXLarge",
|
||||
"keras_core.applications.ConvNeXtXLarge",
|
||||
]
|
||||
)
|
||||
def ConvNeXtXLarge(
|
||||
model_name="convnext_xlarge",
|
||||
include_top=True,
|
||||
include_preprocessing=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
return ConvNeXt(
|
||||
depths=MODEL_CONFIGS["xlarge"]["depths"],
|
||||
projection_dims=MODEL_CONFIGS["xlarge"]["projection_dims"],
|
||||
drop_path_rate=0.0,
|
||||
layer_scale_init_value=1e-6,
|
||||
default_size=MODEL_CONFIGS["xlarge"]["default_size"],
|
||||
model_name=model_name,
|
||||
include_top=include_top,
|
||||
include_preprocessing=include_preprocessing,
|
||||
weights=weights,
|
||||
input_tensor=input_tensor,
|
||||
input_shape=input_shape,
|
||||
pooling=pooling,
|
||||
classes=classes,
|
||||
classifier_activation=classifier_activation,
|
||||
)
|
||||
|
||||
|
||||
ConvNeXtTiny.__doc__ = BASE_DOCSTRING.format(name="ConvNeXtTiny")
|
||||
ConvNeXtSmall.__doc__ = BASE_DOCSTRING.format(name="ConvNeXtSmall")
|
||||
ConvNeXtBase.__doc__ = BASE_DOCSTRING.format(name="ConvNeXtBase")
|
||||
ConvNeXtLarge.__doc__ = BASE_DOCSTRING.format(name="ConvNeXtLarge")
|
||||
ConvNeXtXLarge.__doc__ = BASE_DOCSTRING.format(name="ConvNeXtXLarge")
|
||||
|
||||
|
||||
@keras_core_export("keras_core.applications.convnext.preprocess_input")
|
||||
def preprocess_input(x, data_format=None):
|
||||
"""A placeholder method for backward compatibility.
|
||||
|
||||
The preprocessing logic has been included in the convnext model
|
||||
implementation. Users are no longer required to call this method to
|
||||
normalize the input data. This method does nothing and only kept as a
|
||||
placeholder to align the API surface between old and new version of model.
|
||||
|
||||
Args:
|
||||
x: A floating point `numpy.array` or a tensor.
|
||||
data_format: Optional data format of the image tensor/array. Defaults to
|
||||
None, in which case the global setting
|
||||
`keras_core.backend.image_data_format()` is used
|
||||
(unless you changed it, it defaults to `"channels_last"`).{mode}
|
||||
|
||||
Returns:
|
||||
Unchanged `numpy.array` or tensor.
|
||||
"""
|
||||
return x
|
||||
|
||||
|
||||
@keras_core_export("keras_core.applications.convnext.decode_predictions")
|
||||
def decode_predictions(preds, top=5):
|
||||
return imagenet_utils.decode_predictions(preds, top=top)
|
||||
|
||||
|
||||
decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__
|
400
keras_core/applications/inception_resnet_v2.py
Normal file
400
keras_core/applications/inception_resnet_v2.py
Normal file
@ -0,0 +1,400 @@
|
||||
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.layers.layer import Layer
|
||||
from keras_core.models import Functional
|
||||
from keras_core.operations import operation_utils
|
||||
from keras_core.utils import file_utils
|
||||
|
||||
BASE_WEIGHT_URL = (
|
||||
"https://storage.googleapis.com/tensorflow/"
|
||||
"keras-applications/inception_resnet_v2/"
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.inception_resnet_v2.InceptionResNetV2",
|
||||
"keras_core.applications.InceptionResNetV2",
|
||||
]
|
||||
)
|
||||
def InceptionResNetV2(
|
||||
include_top=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
"""Instantiates the Inception-ResNet v2 architecture.
|
||||
|
||||
Reference:
|
||||
- [Inception-v4, Inception-ResNet and the Impact of
|
||||
Residual Connections on Learning](https://arxiv.org/abs/1602.07261)
|
||||
(AAAI 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 InceptionResNetV2, call
|
||||
`keras_core.applications.inception_resnet_v2.preprocess_input`
|
||||
on your inputs before passing them to the model.
|
||||
`inception_resnet_v2.preprocess_input`
|
||||
will scale input pixels between -1 and 1.
|
||||
|
||||
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 `(299, 299, 3)`
|
||||
(with `'channels_last'` data format)
|
||||
or `(3, 299, 299)` (with `'channels_first'` data format).
|
||||
It should have exactly 3 inputs channels,
|
||||
and width and height should be no smaller than 75.
|
||||
E.g. `(150, 150, 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="imagenet"` with `include_top=True`, '
|
||||
"`classes` should be 1000. "
|
||||
f"Received classes={classes}"
|
||||
)
|
||||
|
||||
# Determine proper input shape
|
||||
input_shape = imagenet_utils.obtain_input_shape(
|
||||
input_shape,
|
||||
default_size=299,
|
||||
min_size=75,
|
||||
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
|
||||
|
||||
# Stem block: 35 x 35 x 192
|
||||
x = conv2d_bn(img_input, 32, 3, strides=2, padding="valid")
|
||||
x = conv2d_bn(x, 32, 3, padding="valid")
|
||||
x = conv2d_bn(x, 64, 3)
|
||||
x = layers.MaxPooling2D(3, strides=2)(x)
|
||||
x = conv2d_bn(x, 80, 1, padding="valid")
|
||||
x = conv2d_bn(x, 192, 3, padding="valid")
|
||||
x = layers.MaxPooling2D(3, strides=2)(x)
|
||||
|
||||
# Mixed 5b (Inception-A block): 35 x 35 x 320
|
||||
branch_0 = conv2d_bn(x, 96, 1)
|
||||
branch_1 = conv2d_bn(x, 48, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 64, 5)
|
||||
branch_2 = conv2d_bn(x, 64, 1)
|
||||
branch_2 = conv2d_bn(branch_2, 96, 3)
|
||||
branch_2 = conv2d_bn(branch_2, 96, 3)
|
||||
branch_pool = layers.AveragePooling2D(3, strides=1, padding="same")(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 64, 1)
|
||||
branches = [branch_0, branch_1, branch_2, branch_pool]
|
||||
channel_axis = 1 if backend.image_data_format() == "channels_first" else 3
|
||||
x = layers.Concatenate(axis=channel_axis, name="mixed_5b")(branches)
|
||||
|
||||
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
|
||||
for block_idx in range(1, 11):
|
||||
x = inception_resnet_block(
|
||||
x, scale=0.17, block_type="block35", block_idx=block_idx
|
||||
)
|
||||
|
||||
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
|
||||
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding="valid")
|
||||
branch_1 = conv2d_bn(x, 256, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 256, 3)
|
||||
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding="valid")
|
||||
branch_pool = layers.MaxPooling2D(3, strides=2, padding="valid")(x)
|
||||
branches = [branch_0, branch_1, branch_pool]
|
||||
x = layers.Concatenate(axis=channel_axis, name="mixed_6a")(branches)
|
||||
|
||||
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
|
||||
for block_idx in range(1, 21):
|
||||
x = inception_resnet_block(
|
||||
x, scale=0.1, block_type="block17", block_idx=block_idx
|
||||
)
|
||||
|
||||
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
|
||||
branch_0 = conv2d_bn(x, 256, 1)
|
||||
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding="valid")
|
||||
branch_1 = conv2d_bn(x, 256, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding="valid")
|
||||
branch_2 = conv2d_bn(x, 256, 1)
|
||||
branch_2 = conv2d_bn(branch_2, 288, 3)
|
||||
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding="valid")
|
||||
branch_pool = layers.MaxPooling2D(3, strides=2, padding="valid")(x)
|
||||
branches = [branch_0, branch_1, branch_2, branch_pool]
|
||||
x = layers.Concatenate(axis=channel_axis, name="mixed_7a")(branches)
|
||||
|
||||
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
|
||||
for block_idx in range(1, 10):
|
||||
x = inception_resnet_block(
|
||||
x, scale=0.2, block_type="block8", block_idx=block_idx
|
||||
)
|
||||
x = inception_resnet_block(
|
||||
x, scale=1.0, activation=None, block_type="block8", block_idx=10
|
||||
)
|
||||
|
||||
# Final convolution block: 8 x 8 x 1536
|
||||
x = conv2d_bn(x, 1536, 1, name="conv_7b")
|
||||
|
||||
if include_top:
|
||||
# Classification block
|
||||
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()(x)
|
||||
elif pooling == "max":
|
||||
x = layers.GlobalMaxPooling2D()(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.
|
||||
model = Functional(inputs, x, name="inception_resnet_v2")
|
||||
|
||||
# Load weights.
|
||||
if weights == "imagenet":
|
||||
if include_top:
|
||||
fname = "inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5"
|
||||
weights_path = file_utils.get_file(
|
||||
fname,
|
||||
BASE_WEIGHT_URL + fname,
|
||||
cache_subdir="models",
|
||||
file_hash="e693bd0210a403b3192acc6073ad2e96",
|
||||
)
|
||||
else:
|
||||
fname = (
|
||||
"inception_resnet_v2_weights_"
|
||||
"tf_dim_ordering_tf_kernels_notop.h5"
|
||||
)
|
||||
weights_path = file_utils.get_file(
|
||||
fname,
|
||||
BASE_WEIGHT_URL + fname,
|
||||
cache_subdir="models",
|
||||
file_hash="d19885ff4a710c122648d3b5c3b684e4",
|
||||
)
|
||||
model.load_weights(weights_path)
|
||||
elif weights is not None:
|
||||
model.load_weights(weights)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
def conv2d_bn(
|
||||
x,
|
||||
filters,
|
||||
kernel_size,
|
||||
strides=1,
|
||||
padding="same",
|
||||
activation="relu",
|
||||
use_bias=False,
|
||||
name=None,
|
||||
):
|
||||
"""Utility function to apply conv + BN.
|
||||
|
||||
Args:
|
||||
x: input tensor.
|
||||
filters: filters in `Conv2D`.
|
||||
kernel_size: kernel size as in `Conv2D`.
|
||||
strides: strides in `Conv2D`.
|
||||
padding: padding mode in `Conv2D`.
|
||||
activation: activation in `Conv2D`.
|
||||
use_bias: whether to use a bias in `Conv2D`.
|
||||
name: name of the ops; will become `name + '_ac'`
|
||||
for the activation and `name + '_bn'` for the batch norm layer.
|
||||
|
||||
Returns:
|
||||
Output tensor after applying `Conv2D` and `BatchNormalization`.
|
||||
"""
|
||||
x = layers.Conv2D(
|
||||
filters,
|
||||
kernel_size,
|
||||
strides=strides,
|
||||
padding=padding,
|
||||
use_bias=use_bias,
|
||||
name=name,
|
||||
)(x)
|
||||
if not use_bias:
|
||||
bn_axis = 1 if backend.image_data_format() == "channels_first" else 3
|
||||
bn_name = None if name is None else name + "_bn"
|
||||
x = layers.BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(
|
||||
x
|
||||
)
|
||||
if activation is not None:
|
||||
ac_name = None if name is None else name + "_ac"
|
||||
x = layers.Activation(activation, name=ac_name)(x)
|
||||
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 an Inception-ResNet block.
|
||||
|
||||
Args:
|
||||
x: input tensor.
|
||||
scale: scaling factor to scale the residuals
|
||||
(i.e., the output of passing `x` through an inception module)
|
||||
before adding them to the shortcut
|
||||
branch. Let `r` be the output from the residual branch,
|
||||
the output of this block will be `x + scale * r`.
|
||||
block_type: `'block35'`, `'block17'` or `'block8'`,
|
||||
determines the network structure in the residual branch.
|
||||
block_idx: an `int` used for generating layer names.
|
||||
The Inception-ResNet blocks are repeated many times
|
||||
in this network. We use `block_idx` to identify each
|
||||
of the repetitions. For example, the first
|
||||
Inception-ResNet-A block will have
|
||||
`block_type='block35', block_idx=0`, and the layer names
|
||||
will have a common prefix `'block35_0'`.
|
||||
activation: activation function to use at the end of the block.
|
||||
|
||||
Returns:
|
||||
Output tensor for the block.
|
||||
"""
|
||||
if block_type == "block35":
|
||||
branch_0 = conv2d_bn(x, 32, 1)
|
||||
branch_1 = conv2d_bn(x, 32, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 32, 3)
|
||||
branch_2 = conv2d_bn(x, 32, 1)
|
||||
branch_2 = conv2d_bn(branch_2, 48, 3)
|
||||
branch_2 = conv2d_bn(branch_2, 64, 3)
|
||||
branches = [branch_0, branch_1, branch_2]
|
||||
elif block_type == "block17":
|
||||
branch_0 = conv2d_bn(x, 192, 1)
|
||||
branch_1 = conv2d_bn(x, 128, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 160, [1, 7])
|
||||
branch_1 = conv2d_bn(branch_1, 192, [7, 1])
|
||||
branches = [branch_0, branch_1]
|
||||
elif block_type == "block8":
|
||||
branch_0 = conv2d_bn(x, 192, 1)
|
||||
branch_1 = conv2d_bn(x, 192, 1)
|
||||
branch_1 = conv2d_bn(branch_1, 224, [1, 3])
|
||||
branch_1 = conv2d_bn(branch_1, 256, [3, 1])
|
||||
branches = [branch_0, branch_1]
|
||||
else:
|
||||
raise ValueError(
|
||||
"Unknown Inception-ResNet block type. "
|
||||
'Expects "block35", "block17" or "block8", '
|
||||
"but got: " + str(block_type)
|
||||
)
|
||||
|
||||
block_name = block_type + "_" + str(block_idx)
|
||||
channel_axis = 1 if backend.image_data_format() == "channels_first" else 3
|
||||
mixed = layers.Concatenate(axis=channel_axis, name=block_name + "_mixed")(
|
||||
branches
|
||||
)
|
||||
up = conv2d_bn(
|
||||
mixed,
|
||||
x.shape[channel_axis],
|
||||
1,
|
||||
activation=None,
|
||||
use_bias=True,
|
||||
name=block_name + "_conv",
|
||||
)
|
||||
|
||||
x = CustomScaleLayer(scale)([x, up])
|
||||
if activation is not None:
|
||||
x = layers.Activation(activation, name=block_name + "_ac")(x)
|
||||
return x
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
"keras_core.applications.inception_resnet_v2.preprocess_input"
|
||||
)
|
||||
def preprocess_input(x, data_format=None):
|
||||
return imagenet_utils.preprocess_input(
|
||||
x, data_format=data_format, mode="tf"
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
"keras_core.applications.inception_resnet_v2.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_TF,
|
||||
error=imagenet_utils.PREPROCESS_INPUT_ERROR_DOC,
|
||||
)
|
||||
decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__
|
442
keras_core/applications/inception_v3.py
Normal file
442
keras_core/applications/inception_v3.py
Normal file
@ -0,0 +1,442 @@
|
||||
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
|
||||
|
||||
WEIGHTS_PATH = (
|
||||
"https://storage.googleapis.com/tensorflow/keras-applications/"
|
||||
"inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels.h5"
|
||||
)
|
||||
WEIGHTS_PATH_NO_TOP = (
|
||||
"https://storage.googleapis.com/tensorflow/keras-applications/"
|
||||
"inception_v3/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5"
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export(
|
||||
[
|
||||
"keras_core.applications.inception_v3.InceptionV3",
|
||||
"keras_core.applications.InceptionV3",
|
||||
]
|
||||
)
|
||||
def InceptionV3(
|
||||
include_top=True,
|
||||
weights="imagenet",
|
||||
input_tensor=None,
|
||||
input_shape=None,
|
||||
pooling=None,
|
||||
classes=1000,
|
||||
classifier_activation="softmax",
|
||||
):
|
||||
"""Instantiates the Inception v3 architecture.
|
||||
|
||||
Reference:
|
||||
- [Rethinking the Inception Architecture for Computer Vision](
|
||||
http://arxiv.org/abs/1512.00567) (CVPR 2016)
|
||||
|
||||
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 `InceptionV3`, call
|
||||
`keras_core.applications.inception_v3.preprocess_input` on your inputs
|
||||
before passing them to the model.
|
||||
`inception_v3.preprocess_input` will scale input pixels between -1 and 1.
|
||||
|
||||
Args:
|
||||
include_top: Boolean, whether to include the fully-connected
|
||||
layer at the top, as the last layer of the network.
|
||||
Defaults to `True`.
|
||||
weights: One of `None` (random initialization),
|
||||
`imagenet` (pre-training on ImageNet),
|
||||
or the path to the weights file to be loaded.
|
||||
Defaults to `"imagenet"`.
|
||||
input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`)
|
||||
to use as image input for the model. `input_tensor` is useful for
|
||||
sharing inputs between multiple different networks.
|
||||
Defaults to `None`.
|
||||
input_shape: Optional shape tuple, only to be specified
|
||||
if `include_top` is False (otherwise the input shape
|
||||
has to be `(299, 299, 3)` (with `channels_last` data format)
|
||||
or `(3, 299, 299)` (with `channels_first` data format).
|
||||
It should have exactly 3 inputs channels,
|
||||
and width and height should be no smaller than 75.
|
||||
E.g. `(150, 150, 3)` would be one valid value.
|
||||
`input_shape` will be ignored if the `input_tensor` is provided.
|
||||
pooling: Optional pooling mode for feature extraction
|
||||
when `include_top` is `False`.
|
||||
- `None` (default) 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. Defaults to 1000.
|
||||
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; "
|
||||
f"Received: weights={weights}"
|
||||
)
|
||||
|
||||
if weights == "imagenet" and include_top and classes != 1000:
|
||||
raise ValueError(
|
||||
'If using `weights="imagenet"` with `include_top=True`, '
|
||||
"`classes` should be 1000. "
|
||||
f"Received classes={classes}"
|
||||
)
|
||||
|
||||
# Determine proper input shape
|
||||
input_shape = imagenet_utils.obtain_input_shape(
|
||||
input_shape,
|
||||
default_size=299,
|
||||
min_size=75,
|
||||
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
|
||||
|
||||
if backend.image_data_format() == "channels_first":
|
||||
channel_axis = 1
|
||||
else:
|
||||
channel_axis = 3
|
||||
|
||||
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding="valid")
|
||||
x = conv2d_bn(x, 32, 3, 3, padding="valid")
|
||||
x = conv2d_bn(x, 64, 3, 3)
|
||||
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
|
||||
x = conv2d_bn(x, 80, 1, 1, padding="valid")
|
||||
x = conv2d_bn(x, 192, 3, 3, padding="valid")
|
||||
x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
|
||||
# mixed 0: 35 x 35 x 256
|
||||
branch1x1 = conv2d_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2d_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed0",
|
||||
)
|
||||
|
||||
# mixed 1: 35 x 35 x 288
|
||||
branch1x1 = conv2d_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2d_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed1",
|
||||
)
|
||||
|
||||
# mixed 2: 35 x 35 x 288
|
||||
branch1x1 = conv2d_bn(x, 64, 1, 1)
|
||||
|
||||
branch5x5 = conv2d_bn(x, 48, 1, 1)
|
||||
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed2",
|
||||
)
|
||||
|
||||
# mixed 3: 17 x 17 x 768
|
||||
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding="valid")
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
|
||||
branch3x3dbl = conv2d_bn(
|
||||
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding="valid"
|
||||
)
|
||||
|
||||
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
x = layers.concatenate(
|
||||
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name="mixed3"
|
||||
)
|
||||
|
||||
# mixed 4: 17 x 17 x 768
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 128, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed4",
|
||||
)
|
||||
|
||||
# mixed 5, 6: 17 x 17 x 768
|
||||
for i in range(2):
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 160, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed" + str(5 + i),
|
||||
)
|
||||
|
||||
# mixed 7: 17 x 17 x 768
|
||||
branch1x1 = conv2d_bn(x, 192, 1, 1)
|
||||
|
||||
branch7x7 = conv2d_bn(x, 192, 1, 1)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
|
||||
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
|
||||
|
||||
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
|
||||
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed7",
|
||||
)
|
||||
|
||||
# mixed 8: 8 x 8 x 1280
|
||||
branch3x3 = conv2d_bn(x, 192, 1, 1)
|
||||
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding="valid")
|
||||
|
||||
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
|
||||
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
|
||||
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
|
||||
branch7x7x3 = conv2d_bn(
|
||||
branch7x7x3, 192, 3, 3, strides=(2, 2), padding="valid"
|
||||
)
|
||||
|
||||
branch_pool = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)
|
||||
x = layers.concatenate(
|
||||
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name="mixed8"
|
||||
)
|
||||
|
||||
# mixed 9: 8 x 8 x 2048
|
||||
for i in range(2):
|
||||
branch1x1 = conv2d_bn(x, 320, 1, 1)
|
||||
|
||||
branch3x3 = conv2d_bn(x, 384, 1, 1)
|
||||
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
|
||||
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
|
||||
branch3x3 = layers.concatenate(
|
||||
[branch3x3_1, branch3x3_2],
|
||||
axis=channel_axis,
|
||||
name="mixed9_" + str(i),
|
||||
)
|
||||
|
||||
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
|
||||
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
|
||||
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
|
||||
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
|
||||
branch3x3dbl = layers.concatenate(
|
||||
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis
|
||||
)
|
||||
|
||||
branch_pool = layers.AveragePooling2D(
|
||||
(3, 3), strides=(1, 1), padding="same"
|
||||
)(x)
|
||||
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
|
||||
x = layers.concatenate(
|
||||
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
|
||||
axis=channel_axis,
|
||||
name="mixed" + str(9 + i),
|
||||
)
|
||||
if include_top:
|
||||
# Classification block
|
||||
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()(x)
|
||||
elif pooling == "max":
|
||||
x = layers.GlobalMaxPooling2D()(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.
|
||||
model = Functional(inputs, x, name="inception_v3")
|
||||
|
||||
# Load weights.
|
||||
if weights == "imagenet":
|
||||
if include_top:
|
||||
weights_path = file_utils.get_file(
|
||||
"inception_v3_weights_tf_dim_ordering_tf_kernels.h5",
|
||||
WEIGHTS_PATH,
|
||||
cache_subdir="models",
|
||||
file_hash="9a0d58056eeedaa3f26cb7ebd46da564",
|
||||
)
|
||||
else:
|
||||
weights_path = file_utils.get_file(
|
||||
"inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5",
|
||||
WEIGHTS_PATH_NO_TOP,
|
||||
cache_subdir="models",
|
||||
file_hash="bcbd6486424b2319ff4ef7d526e38f63",
|
||||
)
|
||||
model.load_weights(weights_path)
|
||||
elif weights is not None:
|
||||
model.load_weights(weights)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
def conv2d_bn(
|
||||
x, filters, num_row, num_col, padding="same", strides=(1, 1), name=None
|
||||
):
|
||||
"""Utility function to apply conv + BN.
|
||||
|
||||
Args:
|
||||
x: input tensor.
|
||||
filters: filters in `Conv2D`.
|
||||
num_row: height of the convolution kernel.
|
||||
num_col: width of the convolution kernel.
|
||||
padding: padding mode in `Conv2D`.
|
||||
strides: strides in `Conv2D`.
|
||||
name: name of the ops; will become `name + '_conv'`
|
||||
for the convolution and `name + '_bn'` for the
|
||||
batch norm layer.
|
||||
|
||||
Returns:
|
||||
Output tensor after applying `Conv2D` and `BatchNormalization`.
|
||||
"""
|
||||
if name is not None:
|
||||
bn_name = name + "_bn"
|
||||
conv_name = name + "_conv"
|
||||
else:
|
||||
bn_name = None
|
||||
conv_name = None
|
||||
if backend.image_data_format() == "channels_first":
|
||||
bn_axis = 1
|
||||
else:
|
||||
bn_axis = 3
|
||||
x = layers.Conv2D(
|
||||
filters,
|
||||
(num_row, num_col),
|
||||
strides=strides,
|
||||
padding=padding,
|
||||
use_bias=False,
|
||||
name=conv_name,
|
||||
)(x)
|
||||
x = layers.BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
|
||||
x = layers.Activation("relu", name=name)(x)
|
||||
return x
|
||||
|
||||
|
||||
@keras_core_export("keras_core.applications.inception_v3.preprocess_input")
|
||||
def preprocess_input(x, data_format=None):
|
||||
return imagenet_utils.preprocess_input(
|
||||
x, data_format=data_format, mode="tf"
|
||||
)
|
||||
|
||||
|
||||
@keras_core_export("keras_core.applications.inception_v3.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_TF,
|
||||
error=imagenet_utils.PREPROCESS_INPUT_ERROR_DOC,
|
||||
)
|
||||
decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__
|
@ -1,7 +1,6 @@
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.Cropping1D")
|
||||
@ -43,9 +42,9 @@ class Cropping1D(Layer):
|
||||
|
||||
def __init__(self, cropping=(1, 1), name=None, dtype=None):
|
||||
super().__init__(name=name, dtype=dtype)
|
||||
self.cropping = argument_validation.standardize_tuple(
|
||||
cropping, 2, "cropping", allow_zero=True
|
||||
)
|
||||
if isinstance(cropping, int):
|
||||
cropping = (cropping, cropping)
|
||||
self.cropping = cropping
|
||||
self.input_spec = InputSpec(ndim=3)
|
||||
|
||||
def compute_output_shape(self, input_shape):
|
||||
|
@ -56,14 +56,6 @@ class Cropping1DTest(testing.TestCase):
|
||||
cropped = layers.Cropping1D((1, 2))(input_layer)
|
||||
self.assertEqual(cropped.shape, (1, None, 7))
|
||||
|
||||
def test_cropping_1d_errors_if_cropping_argument_invalid(self):
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping1D(cropping=(1,))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping1D(cropping=(1, 2, 3))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping1D(cropping="1")
|
||||
|
||||
def test_cropping_1d_errors_if_cropping_more_than_available(self):
|
||||
with self.assertRaises(ValueError):
|
||||
input_layer = layers.Input(batch_shape=(3, 5, 7))
|
||||
|
@ -2,7 +2,6 @@ from keras_core import backend
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.Cropping2D")
|
||||
@ -66,12 +65,12 @@ class Cropping2D(Layer):
|
||||
"`cropping` should have two elements. "
|
||||
f"Received: cropping={cropping}."
|
||||
)
|
||||
height_cropping = argument_validation.standardize_tuple(
|
||||
cropping[0], 2, "1st entry of cropping", allow_zero=True
|
||||
)
|
||||
width_cropping = argument_validation.standardize_tuple(
|
||||
cropping[1], 2, "2nd entry of cropping", allow_zero=True
|
||||
)
|
||||
height_cropping = cropping[0]
|
||||
if isinstance(height_cropping, int):
|
||||
height_cropping = (height_cropping, height_cropping)
|
||||
width_cropping = cropping[1]
|
||||
if isinstance(width_cropping, int):
|
||||
width_cropping = (width_cropping, width_cropping)
|
||||
self.cropping = (height_cropping, width_cropping)
|
||||
else:
|
||||
raise ValueError(
|
||||
|
@ -97,9 +97,3 @@ class Cropping2DTest(testing.TestCase, parameterized.TestCase):
|
||||
layers.Cropping2D(cropping=(1, 2, 3))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping2D(cropping="1")
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping2D(cropping=((1, 2), (3, 4, 5)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping2D(cropping=((1, 2), (3, -4)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping2D(cropping=((1, 2), "3"))
|
||||
|
@ -2,7 +2,6 @@ from keras_core import backend
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.Cropping3D")
|
||||
@ -76,15 +75,15 @@ class Cropping3D(Layer):
|
||||
raise ValueError(
|
||||
f"`cropping` should have 3 elements. Received: {cropping}."
|
||||
)
|
||||
dim1_cropping = argument_validation.standardize_tuple(
|
||||
cropping[0], 2, "1st entry of cropping", allow_zero=True
|
||||
)
|
||||
dim2_cropping = argument_validation.standardize_tuple(
|
||||
cropping[1], 2, "2nd entry of cropping", allow_zero=True
|
||||
)
|
||||
dim3_cropping = argument_validation.standardize_tuple(
|
||||
cropping[2], 2, "3rd entry of cropping", allow_zero=True
|
||||
)
|
||||
dim1_cropping = cropping[0]
|
||||
if isinstance(dim1_cropping, int):
|
||||
dim1_cropping = (dim1_cropping, dim1_cropping)
|
||||
dim2_cropping = cropping[1]
|
||||
if isinstance(dim2_cropping, int):
|
||||
dim2_cropping = (dim2_cropping, dim2_cropping)
|
||||
dim3_cropping = cropping[2]
|
||||
if isinstance(dim3_cropping, int):
|
||||
dim3_cropping = (dim3_cropping, dim3_cropping)
|
||||
self.cropping = (dim1_cropping, dim2_cropping, dim3_cropping)
|
||||
else:
|
||||
raise ValueError(
|
||||
|
@ -159,9 +159,3 @@ class Cropping3DTest(testing.TestCase, parameterized.TestCase):
|
||||
layers.Cropping3D(cropping=(1, 2, 3, 4))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping3D(cropping="1")
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping3D(cropping=((1, 2), (3, 4), (5, 6, 7)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping3D(cropping=((1, 2), (3, 4), (5, -6)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.Cropping3D(cropping=((1, 2), (3, 4), "5"))
|
||||
|
@ -2,7 +2,6 @@ from keras_core import operations as ops
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.ZeroPadding1D")
|
||||
@ -49,9 +48,9 @@ class ZeroPadding1D(Layer):
|
||||
|
||||
def __init__(self, padding=1, name=None, dtype=None):
|
||||
super().__init__(name=name, dtype=dtype)
|
||||
self.padding = argument_validation.standardize_tuple(
|
||||
padding, 2, "padding", allow_zero=True
|
||||
)
|
||||
if isinstance(padding, int):
|
||||
padding = (padding, padding)
|
||||
self.padding = padding
|
||||
self.input_spec = InputSpec(ndim=3)
|
||||
|
||||
def compute_output_shape(self, input_shape):
|
||||
|
@ -33,11 +33,3 @@ class ZeroPadding1DTest(testing.TestCase, parameterized.TestCase):
|
||||
input_layer = layers.Input(batch_shape=(1, None, 3))
|
||||
padded = layers.ZeroPadding1D((1, 2))(input_layer)
|
||||
self.assertEqual(padded.shape, (1, None, 3))
|
||||
|
||||
def test_zero_padding_1d_errors_if_padding_argument_invalid(self):
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding1D(padding=(1,))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding1D(padding=(1, 2, 3))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding1D(padding="1")
|
||||
|
@ -3,7 +3,6 @@ from keras_core import operations as ops
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.ZeroPadding2D")
|
||||
@ -79,12 +78,12 @@ class ZeroPadding2D(Layer):
|
||||
"`padding` should have two elements. "
|
||||
f"Received: padding={padding}."
|
||||
)
|
||||
height_padding = argument_validation.standardize_tuple(
|
||||
padding[0], 2, "1st entry of padding", allow_zero=True
|
||||
)
|
||||
width_padding = argument_validation.standardize_tuple(
|
||||
padding[1], 2, "2nd entry of padding", allow_zero=True
|
||||
)
|
||||
height_padding = padding[0]
|
||||
if isinstance(height_padding, int):
|
||||
height_padding = (height_padding, height_padding)
|
||||
width_padding = padding[1]
|
||||
if isinstance(width_padding, int):
|
||||
width_padding = (width_padding, width_padding)
|
||||
self.padding = (height_padding, width_padding)
|
||||
else:
|
||||
raise ValueError(
|
||||
|
@ -74,9 +74,3 @@ class ZeroPadding2DTest(testing.TestCase, parameterized.TestCase):
|
||||
layers.ZeroPadding2D(padding=(1, 2, 3))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding2D(padding="1")
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding2D(padding=((1, 2), (3, 4, 5)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding2D(padding=((1, 2), (3, -4)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding2D(padding=((1, 2), "3"))
|
||||
|
@ -3,7 +3,6 @@ from keras_core import operations as ops
|
||||
from keras_core.api_export import keras_core_export
|
||||
from keras_core.layers.input_spec import InputSpec
|
||||
from keras_core.layers.layer import Layer
|
||||
from keras_core.utils import argument_validation
|
||||
|
||||
|
||||
@keras_core_export("keras_core.layers.ZeroPadding3D")
|
||||
@ -77,15 +76,16 @@ class ZeroPadding3D(Layer):
|
||||
raise ValueError(
|
||||
f"`padding` should have 3 elements. Received: {padding}."
|
||||
)
|
||||
dim1_padding = argument_validation.standardize_tuple(
|
||||
padding[0], 2, "1st entry of padding", allow_zero=True
|
||||
)
|
||||
dim2_padding = argument_validation.standardize_tuple(
|
||||
padding[1], 2, "2nd entry of padding", allow_zero=True
|
||||
)
|
||||
dim3_padding = argument_validation.standardize_tuple(
|
||||
padding[2], 2, "3rd entry of padding", allow_zero=True
|
||||
)
|
||||
dim1_padding = padding[0]
|
||||
if isinstance(dim1_padding, int):
|
||||
dim1_padding = (dim1_padding, dim1_padding)
|
||||
dim2_padding = padding[1]
|
||||
if isinstance(dim2_padding, int):
|
||||
dim2_padding = (dim2_padding, dim2_padding)
|
||||
dim3_padding = padding[2]
|
||||
if isinstance(dim3_padding, int):
|
||||
dim3_padding = (dim3_padding, dim3_padding)
|
||||
self.padding = (dim1_padding, dim2_padding, dim3_padding)
|
||||
self.padding = (dim1_padding, dim2_padding, dim3_padding)
|
||||
else:
|
||||
raise ValueError(
|
||||
|
@ -82,9 +82,3 @@ class ZeroPadding3DTest(testing.TestCase, parameterized.TestCase):
|
||||
layers.ZeroPadding3D(padding=(1, 2, 3, 4))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding3D(padding="1")
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding3D(padding=((1, 2), (3, 4), (5, 6, 7)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding3D(padding=((1, 2), (3, 4), (5, -6)))
|
||||
with self.assertRaises(ValueError):
|
||||
layers.ZeroPadding3D(padding=((1, 2), (3, 4), "5"))
|
||||
|
@ -540,7 +540,7 @@ def deserialize_node(node_data, created_layers):
|
||||
if layer is None:
|
||||
raise ValueError(f"Unknown layer: {history[0]}")
|
||||
inbound_node_index = history[1]
|
||||
inbound_tensor_index = history[1]
|
||||
inbound_tensor_index = history[2]
|
||||
if len(layer._inbound_nodes) <= inbound_node_index:
|
||||
raise ValueError(
|
||||
"Layer node index out of bounds.\n"
|
||||
|
@ -112,11 +112,6 @@ class Sequential(Model):
|
||||
self._functional = Functional(inputs=inputs, outputs=outputs)
|
||||
self.built = True
|
||||
|
||||
def __call__(self, inputs, training=None, mask=None):
|
||||
if self._functional:
|
||||
return self._functional(inputs, training=training, mask=mask)
|
||||
return super().__call__(inputs, training=training, mask=mask)
|
||||
|
||||
def call(self, inputs, training=None, mask=None):
|
||||
if self._functional:
|
||||
return self._functional.call(inputs, training=training, mask=mask)
|
||||
|
Loading…
Reference in New Issue
Block a user