Skip to content

Commit

Permalink
Merge pull request #13 from ElenaRyumina/main
Browse files Browse the repository at this point in the history 
Summary
  • Loading branch information
@DmitryRyumin
DmitryRyumin authored Dec 12, 2023
2 parents fe6ecd9 + 7c3befe commit 79d78b4
Show file tree
Hide file tree
Showing 4 changed files with 16 additions and 357 deletions.
2 changes: 1 addition & 1 deletion docs/source/user_guide/notebooks/images/Pipeline_OCEANAI_ru.svg
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
290 changes: 1 addition & 289 deletions oceanai/modules/lab/keras_vggface/models.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,95 +24,11 @@
multiply,
)
from keras.models import Model
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.utils.layer_utils import get_source_inputs
from keras_applications.imagenet_utils import _obtain_input_shape

from oceanai.modules.lab.keras_vggface import utils


def VGG16(include_top=True, weights="vggface", input_tensor=None, input_shape=None, pooling=None, classes=2622):
input_shape = _obtain_input_shape(
input_shape, default_size=224, min_size=48, data_format=K.image_data_format(), require_flatten=include_top
)

if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor

x = Conv2D(64, (3, 3), activation="relu", padding="same", name="conv1_1")(img_input)
x = Conv2D(64, (3, 3), activation="relu", padding="same", name="conv1_2")(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool1")(x)

x = Conv2D(128, (3, 3), activation="relu", padding="same", name="conv2_1")(x)
x = Conv2D(128, (3, 3), activation="relu", padding="same", name="conv2_2")(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool2")(x)

x = Conv2D(256, (3, 3), activation="relu", padding="same", name="conv3_1")(x)
x = Conv2D(256, (3, 3), activation="relu", padding="same", name="conv3_2")(x)
x = Conv2D(256, (3, 3), activation="relu", padding="same", name="conv3_3")(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool3")(x)

x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv4_1")(x)
x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv4_2")(x)
x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv4_3")(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool4")(x)

x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv5_1")(x)
x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv5_2")(x)
x = Conv2D(512, (3, 3), activation="relu", padding="same", name="conv5_3")(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name="pool5")(x)

if include_top:
x = Flatten(name="flatten")(x)
x = Dense(4096, name="fc6")(x)
x = Activation("relu", name="fc6/relu")(x)
x = Dense(4096, name="fc7")(x)
x = Activation("relu", name="fc7/relu")(x)
x = Dense(classes, name="fc8")(x)
x = Activation("softmax", name="fc8/softmax")(x)
else:
if pooling == "avg":
x = GlobalAveragePooling2D()(x)
elif pooling == "max":
x = GlobalMaxPooling2D()(x)

if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input

model = Model(inputs, x, name="vggface_vgg16")
if weights == "vggface":
if include_top:
weights_path = get_file(
"rcmalli_vggface_tf_vgg16.h5", utils.VGG16_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR
)
else:
weights_path = get_file(
"rcmalli_vggface_tf_notop_vgg16.h5", utils.VGG16_WEIGHTS_PATH_NO_TOP, cache_subdir=utils.VGGFACE_DIR
)
model.load_weights(weights_path, by_name=True)
if K.backend() == "theano":
layer_utils.convert_all_kernels_in_model(model)

if K.image_data_format() == "channels_first":
if include_top:
maxpool = model.get_layer(name="pool5")
shape = maxpool.output_shape[1:]
dense = model.get_layer(name="fc6")
layer_utils.convert_dense_weights_data_format(dense, shape, "channels_first")

if K.backend() == "tensorflow":
warnings.warn("Warn")
return model


def resnet_identity_block(input_tensor, kernel_size, filters, stage, block, bias=False):
filters1, filters2, filters3 = filters
if K.image_data_format() == "channels_last":
Expand Down Expand Up @@ -234,208 +150,4 @@ def RESNET50(include_top=True, weights="vggface", input_tensor=None, input_shape

model = Model(inputs, x, name="vggface_resnet50")

if weights == "vggface":
if include_top:
weights_path = get_file(
"rcmalli_vggface_tf_resnet50.h5", utils.RESNET50_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR
)
else:
weights_path = get_file(
"rcmalli_vggface_tf_notop_resnet50.h5",
utils.RESNET50_WEIGHTS_PATH_NO_TOP,
cache_subdir=utils.VGGFACE_DIR,
)
model.load_weights(weights_path)
if K.backend() == "theano":
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name="avg_pool")
shape = maxpool.output_shape[1:]
dense = model.get_layer(name="classifier")
layer_utils.convert_dense_weights_data_format(dense, shape, "channels_first")

if K.image_data_format() == "channels_first" and K.backend() == "tensorflow":
warnings.warn("Warn")
elif weights is not None:
model.load_weights(weights)

return model


def senet_se_block(input_tensor, stage, block, compress_rate=16, bias=False):
conv1_down_name = "conv" + str(stage) + "_" + str(block) + "_1x1_down"
conv1_up_name = "conv" + str(stage) + "_" + str(block) + "_1x1_up"

num_channels = int(input_tensor.shape[-1])
bottle_neck = int(num_channels // compress_rate)

se = GlobalAveragePooling2D()(input_tensor)
se = Reshape((1, 1, num_channels))(se)
se = Conv2D(bottle_neck, (1, 1), use_bias=bias, name=conv1_down_name)(se)
se = Activation("relu")(se)
se = Conv2D(num_channels, (1, 1), use_bias=bias, name=conv1_up_name)(se)
se = Activation("sigmoid")(se)

x = input_tensor
x = multiply([x, se])
return x


def senet_conv_block(input_tensor, kernel_size, filters, stage, block, bias=False, strides=(2, 2)):
filters1, filters2, filters3 = filters
if K.image_data_format() == "channels_last":
bn_axis = 3
else:
bn_axis = 1

bn_eps = 0.0001

conv1_reduce_name = "conv" + str(stage) + "_" + str(block) + "_1x1_reduce"
conv1_increase_name = "conv" + str(stage) + "_" + str(block) + "_1x1_increase"
conv1_proj_name = "conv" + str(stage) + "_" + str(block) + "_1x1_proj"
conv3_name = "conv" + str(stage) + "_" + str(block) + "_3x3"

x = Conv2D(filters1, (1, 1), use_bias=bias, strides=strides, name=conv1_reduce_name)(input_tensor)
x = BatchNormalization(axis=bn_axis, name=conv1_reduce_name + "/bn", epsilon=bn_eps)(x)
x = Activation("relu")(x)

x = Conv2D(filters2, kernel_size, padding="same", use_bias=bias, name=conv3_name)(x)
x = BatchNormalization(axis=bn_axis, name=conv3_name + "/bn", epsilon=bn_eps)(x)
x = Activation("relu")(x)

x = Conv2D(filters3, (1, 1), name=conv1_increase_name, use_bias=bias)(x)
x = BatchNormalization(axis=bn_axis, name=conv1_increase_name + "/bn", epsilon=bn_eps)(x)

se = senet_se_block(x, stage=stage, block=block, bias=True)

shortcut = Conv2D(filters3, (1, 1), use_bias=bias, strides=strides, name=conv1_proj_name)(input_tensor)
shortcut = BatchNormalization(axis=bn_axis, name=conv1_proj_name + "/bn", epsilon=bn_eps)(shortcut)

m = layers.add([se, shortcut])
m = Activation("relu")(m)
return m


def senet_identity_block(input_tensor, kernel_size, filters, stage, block, bias=False):
filters1, filters2, filters3 = filters
if K.image_data_format() == "channels_last":
bn_axis = 3
else:
bn_axis = 1

bn_eps = 0.0001

conv1_reduce_name = "conv" + str(stage) + "_" + str(block) + "_1x1_reduce"
conv1_increase_name = "conv" + str(stage) + "_" + str(block) + "_1x1_increase"
conv3_name = "conv" + str(stage) + "_" + str(block) + "_3x3"

x = Conv2D(filters1, (1, 1), use_bias=bias, name=conv1_reduce_name)(input_tensor)
x = BatchNormalization(axis=bn_axis, name=conv1_reduce_name + "/bn", epsilon=bn_eps)(x)
x = Activation("relu")(x)

x = Conv2D(filters2, kernel_size, padding="same", use_bias=bias, name=conv3_name)(x)
x = BatchNormalization(axis=bn_axis, name=conv3_name + "/bn", epsilon=bn_eps)(x)
x = Activation("relu")(x)

x = Conv2D(filters3, (1, 1), name=conv1_increase_name, use_bias=bias)(x)
x = BatchNormalization(axis=bn_axis, name=conv1_increase_name + "/bn", epsilon=bn_eps)(x)

se = senet_se_block(x, stage=stage, block=block, bias=True)

m = layers.add([se, input_tensor])
m = Activation("relu")(m)

return m


def SENET50(include_top=True, weights="vggface", input_tensor=None, input_shape=None, pooling=None, classes=8631):
input_shape = _obtain_input_shape(
input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights,
)

if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == "channels_last":
bn_axis = 3
else:
bn_axis = 1

bn_eps = 0.0001

x = Conv2D(64, (7, 7), use_bias=False, strides=(2, 2), padding="same", name="conv1/7x7_s2")(img_input)
x = BatchNormalization(axis=bn_axis, name="conv1/7x7_s2/bn", epsilon=bn_eps)(x)
x = Activation("relu")(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)

x = senet_conv_block(x, 3, [64, 64, 256], stage=2, block=1, strides=(1, 1))
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=2)
x = senet_identity_block(x, 3, [64, 64, 256], stage=2, block=3)

x = senet_conv_block(x, 3, [128, 128, 512], stage=3, block=1)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=2)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=3)
x = senet_identity_block(x, 3, [128, 128, 512], stage=3, block=4)

x = senet_conv_block(x, 3, [256, 256, 1024], stage=4, block=1)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=2)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=3)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=4)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=5)
x = senet_identity_block(x, 3, [256, 256, 1024], stage=4, block=6)

x = senet_conv_block(x, 3, [512, 512, 2048], stage=5, block=1)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=2)
x = senet_identity_block(x, 3, [512, 512, 2048], stage=5, block=3)

x = AveragePooling2D((7, 7), name="avg_pool")(x)

if include_top:
x = Flatten()(x)
x = Dense(classes, activation="softmax", name="classifier")(x)
else:
if pooling == "avg":
x = GlobalAveragePooling2D()(x)
elif pooling == "max":
x = GlobalMaxPooling2D()(x)

if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input

model = Model(inputs, x, name="vggface_senet50")

if weights == "vggface":
if include_top:
weights_path = get_file(
"rcmalli_vggface_tf_senet50.h5", utils.SENET50_WEIGHTS_PATH, cache_subdir=utils.VGGFACE_DIR
)
else:
weights_path = get_file(
"rcmalli_vggface_tf_notop_senet50.h5", utils.SENET50_WEIGHTS_PATH_NO_TOP, cache_subdir=utils.VGGFACE_DIR
)
model.load_weights(weights_path)
if K.backend() == "theano":
layer_utils.convert_all_kernels_in_model(model)
if include_top:
maxpool = model.get_layer(name="avg_pool")
shape = maxpool.output_shape[1:]
dense = model.get_layer(name="classifier")
layer_utils.convert_dense_weights_data_format(dense, shape, "channels_first")

if K.image_data_format() == "channels_first" and K.backend() == "tensorflow":
warnings.warn("Warn")
elif weights is not None:
model.load_weights(weights)

return model
return model
20 changes: 0 additions & 20 deletions oceanai/modules/lab/keras_vggface/utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,26 +8,6 @@
import numpy as np
from keras import backend as K

V1_LABELS_PATH = "https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_labels_v1.npy"
V2_LABELS_PATH = "https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_labels_v2.npy"

VGG16_WEIGHTS_PATH = "https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_vgg16.h5"
VGG16_WEIGHTS_PATH_NO_TOP = (
"https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_notop_vgg16.h5"
)

RESNET50_WEIGHTS_PATH = "https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_resnet50.h5"
RESNET50_WEIGHTS_PATH_NO_TOP = (
"https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_notop_resnet50.h5"
)

SENET50_WEIGHTS_PATH = "https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_senet50.h5"
SENET50_WEIGHTS_PATH_NO_TOP = (
"https://github.com/rcmalli/keras-vggface/releases/download/v2.0/rcmalli_vggface_tf_notop_senet50.h5"
)

VGGFACE_DIR = "models/vggface"


def preprocess_input(x, data_format=None, version=1):
x_temp = np.copy(x)
Expand Down
Loading

0 comments on commit 79d78b4

Please sign in to comment.