github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 12:05:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

google drive to github release

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2021-07-03 00:27:35 +03:00
parent c21b1f7287
commit a904d9007c
9 changed files with 120 additions and 104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
deepface/basemodels/ArcFace.py
View File

@ -10,7 +10,9 @@ import os
from pathlib import Path from pathlib import Path
import gdown import gdown
def loadModel(): #url = "https://drive.google.com/uc?id=1LVB3CdVejpmGHM28BpqqkbZP5hDEcdZY"
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/arcface_weights.h5'):
base_model = ResNet34() base_model = ResNet34()
inputs = base_model.inputs[0] inputs = base_model.inputs[0]
arcface_model = base_model.outputs[0] arcface_model = base_model.outputs[0]
@ -20,41 +22,36 @@ def loadModel():
arcface_model = keras.layers.Dense(512, activation=None, use_bias=True, kernel_initializer="glorot_normal")(arcface_model) arcface_model = keras.layers.Dense(512, activation=None, use_bias=True, kernel_initializer="glorot_normal")(arcface_model)
embedding = keras.layers.BatchNormalization(momentum=0.9, epsilon=2e-5, name="embedding", scale=True)(arcface_model) embedding = keras.layers.BatchNormalization(momentum=0.9, epsilon=2e-5, name="embedding", scale=True)(arcface_model)
model = keras.models.Model(inputs, embedding, name=base_model.name) model = keras.models.Model(inputs, embedding, name=base_model.name)
#--------------------------------------- #---------------------------------------
#check the availability of pre-trained weights #check the availability of pre-trained weights
home = str(Path.home()) home = str(Path.home())
url = "https://drive.google.com/uc?id=1LVB3CdVejpmGHM28BpqqkbZP5hDEcdZY"
file_name = "arcface_weights.h5" file_name = "arcface_weights.h5"
output = home+'/.deepface/weights/'+file_name output = home+'/.deepface/weights/'+file_name
if os.path.isfile(output) != True: if os.path.isfile(output) != True:
print(file_name," will be downloaded to ",output) print(file_name," will be downloaded to ",output)
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#--------------------------------------- #---------------------------------------
try: model.load_weights(output)
model.load_weights(output)
except:
print("pre-trained weights could not be loaded.")
print("You might try to download it from the url ", url," and copy to ",output," manually")
return model return model
def ResNet34(): def ResNet34():
img_input = tensorflow.keras.layers.Input(shape=(112, 112, 3)) img_input = tensorflow.keras.layers.Input(shape=(112, 112, 3))
x = tensorflow.keras.layers.ZeroPadding2D(padding=1, name='conv1_pad')(img_input) x = tensorflow.keras.layers.ZeroPadding2D(padding=1, name='conv1_pad')(img_input)
x = tensorflow.keras.layers.Conv2D(64, 3, strides=1, use_bias=False, kernel_initializer='glorot_normal', name='conv1_conv')(x) x = tensorflow.keras.layers.Conv2D(64, 3, strides=1, use_bias=False, kernel_initializer='glorot_normal', name='conv1_conv')(x)
x = tensorflow.keras.layers.BatchNormalization(axis=3, epsilon=2e-5, momentum=0.9, name='conv1_bn')(x) x = tensorflow.keras.layers.BatchNormalization(axis=3, epsilon=2e-5, momentum=0.9, name='conv1_bn')(x)
x = tensorflow.keras.layers.PReLU(shared_axes=[1, 2], name='conv1_prelu')(x) x = tensorflow.keras.layers.PReLU(shared_axes=[1, 2], name='conv1_prelu')(x)
x = stack_fn(x) x = stack_fn(x)
model = training.Model(img_input, x, name='ResNet34') model = training.Model(img_input, x, name='ResNet34')
return model return model
@ -91,4 +88,4 @@ def stack_fn(x):
x = stack1(x, 64, 3, name='conv2') x = stack1(x, 64, 3, name='conv2')
x = stack1(x, 128, 4, name='conv3') x = stack1(x, 128, 4, name='conv3')
x = stack1(x, 256, 6, name='conv4') x = stack1(x, 256, 6, name='conv4')
return stack1(x, 512, 3, name='conv5') return stack1(x, 512, 3, name='conv5')

34
deepface/basemodels/DeepID.py
View File

@ -9,44 +9,46 @@ from tensorflow.keras.layers import Conv2D, Activation, Input, Add, MaxPooling2D
#------------------------------------- #-------------------------------------
def loadModel(url = 'https://drive.google.com/uc?id=1uRLtBCTQQAvHJ_KVrdbRJiCKxU8m5q2J'): #url = 'https://drive.google.com/uc?id=1uRLtBCTQQAvHJ_KVrdbRJiCKxU8m5q2J'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/deepid_keras_weights.h5'):
myInput = Input(shape=(55, 47, 3)) myInput = Input(shape=(55, 47, 3))
x = Conv2D(20, (4, 4), name='Conv1', activation='relu', input_shape=(55, 47, 3))(myInput) x = Conv2D(20, (4, 4), name='Conv1', activation='relu', input_shape=(55, 47, 3))(myInput)
x = MaxPooling2D(pool_size=2, strides=2, name='Pool1')(x) x = MaxPooling2D(pool_size=2, strides=2, name='Pool1')(x)
x = Dropout(rate=0.99, name='D1')(x) x = Dropout(rate=0.99, name='D1')(x)
x = Conv2D(40, (3, 3), name='Conv2', activation='relu')(x) x = Conv2D(40, (3, 3), name='Conv2', activation='relu')(x)
x = MaxPooling2D(pool_size=2, strides=2, name='Pool2')(x) x = MaxPooling2D(pool_size=2, strides=2, name='Pool2')(x)
x = Dropout(rate=0.99, name='D2')(x) x = Dropout(rate=0.99, name='D2')(x)
x = Conv2D(60, (3, 3), name='Conv3', activation='relu')(x) x = Conv2D(60, (3, 3), name='Conv3', activation='relu')(x)
x = MaxPooling2D(pool_size=2, strides=2, name='Pool3')(x) x = MaxPooling2D(pool_size=2, strides=2, name='Pool3')(x)
x = Dropout(rate=0.99, name='D3')(x) x = Dropout(rate=0.99, name='D3')(x)
x1 = Flatten()(x) x1 = Flatten()(x)
fc11 = Dense(160, name = 'fc11')(x1) fc11 = Dense(160, name = 'fc11')(x1)
x2 = Conv2D(80, (2, 2), name='Conv4', activation='relu')(x) x2 = Conv2D(80, (2, 2), name='Conv4', activation='relu')(x)
x2 = Flatten()(x2) x2 = Flatten()(x2)
fc12 = Dense(160, name = 'fc12')(x2) fc12 = Dense(160, name = 'fc12')(x2)
y = Add()([fc11, fc12]) y = Add()([fc11, fc12])
y = Activation('relu', name = 'deepid')(y) y = Activation('relu', name = 'deepid')(y)
model = Model(inputs=[myInput], outputs=y) model = Model(inputs=[myInput], outputs=y)
#--------------------------------- #---------------------------------
home = str(Path.home()) home = str(Path.home())
if os.path.isfile(home+'/.deepface/weights/deepid_keras_weights.h5') != True: if os.path.isfile(home+'/.deepface/weights/deepid_keras_weights.h5') != True:
print("deepid_keras_weights.h5 will be downloaded...") print("deepid_keras_weights.h5 will be downloaded...")
output = home+'/.deepface/weights/deepid_keras_weights.h5' output = home+'/.deepface/weights/deepid_keras_weights.h5'
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
model.load_weights(home+'/.deepface/weights/deepid_keras_weights.h5') model.load_weights(home+'/.deepface/weights/deepid_keras_weights.h5')
return model return model

70
deepface/basemodels/Facenet.py
View File

@ -21,7 +21,7 @@ def scaling(x, scale):
return x * scale return x * scale
def InceptionResNetV2(): def InceptionResNetV2():
inputs = Input(shape=(160, 160, 3)) inputs = Input(shape=(160, 160, 3))
x = Conv2D(32, 3, strides=2, padding='valid', use_bias=False, name= 'Conv2d_1a_3x3') (inputs) x = Conv2D(32, 3, strides=2, padding='valid', use_bias=False, name= 'Conv2d_1a_3x3') (inputs)
x = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Conv2d_1a_3x3_BatchNorm')(x) x = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Conv2d_1a_3x3_BatchNorm')(x)
@ -42,7 +42,7 @@ def InceptionResNetV2():
x = Conv2D(256, 3, strides=2, padding='valid', use_bias=False, name= 'Conv2d_4b_3x3') (x) x = Conv2D(256, 3, strides=2, padding='valid', use_bias=False, name= 'Conv2d_4b_3x3') (x)
x = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Conv2d_4b_3x3_BatchNorm')(x) x = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Conv2d_4b_3x3_BatchNorm')(x)
x = Activation('relu', name='Conv2d_4b_3x3_Activation')(x) x = Activation('relu', name='Conv2d_4b_3x3_Activation')(x)
# 5x Block35 (Inception-ResNet-A block): # 5x Block35 (Inception-ResNet-A block):
branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_1_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_1_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_1_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_1_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
@ -68,7 +68,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block35_1_Activation')(x) x = Activation('relu', name='Block35_1_Activation')(x)
branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_2_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_2_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block35_2_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block35_2_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -93,7 +93,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block35_2_Activation')(x) x = Activation('relu', name='Block35_2_Activation')(x)
branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_3_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_3_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block35_3_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block35_3_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -118,7 +118,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block35_3_Activation')(x) x = Activation('relu', name='Block35_3_Activation')(x)
branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_4_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_4_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block35_4_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block35_4_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -143,7 +143,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.17})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block35_4_Activation')(x) x = Activation('relu', name='Block35_4_Activation')(x)
branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_5_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(32, 1, strides=1, padding='same', use_bias=False, name= 'Block35_5_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block35_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block35_5_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block35_5_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -205,7 +205,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_1_Activation')(x) x = Activation('relu', name='Block17_1_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_2_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_2_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_2_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_2_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -224,7 +224,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_2_Activation')(x) x = Activation('relu', name='Block17_2_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_3_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_3_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_3_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_3_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -243,7 +243,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_3_Activation')(x) x = Activation('relu', name='Block17_3_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_4_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_4_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_4_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_4_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -262,7 +262,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_4_Activation')(x) x = Activation('relu', name='Block17_4_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_5_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_5_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_5_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_5_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -281,7 +281,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_5_Activation')(x) x = Activation('relu', name='Block17_5_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_6_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_6_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_6_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_6_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_6_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_6_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -299,8 +299,8 @@ def InceptionResNetV2():
up = Conv2D(896, 1, strides=1, padding='same', use_bias=True, name= 'Block17_6_Conv2d_1x1') (mixed) up = Conv2D(896, 1, strides=1, padding='same', use_bias=True, name= 'Block17_6_Conv2d_1x1') (mixed)
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_6_Activation')(x) x = Activation('relu', name='Block17_6_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_7_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_7_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_7_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_7_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_7_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_7_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -319,7 +319,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_7_Activation')(x) x = Activation('relu', name='Block17_7_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_8_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_8_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_8_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_8_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_8_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_8_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -338,7 +338,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_8_Activation')(x) x = Activation('relu', name='Block17_8_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_9_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_9_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_9_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_9_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_9_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_9_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -357,7 +357,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.1})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_9_Activation')(x) x = Activation('relu', name='Block17_9_Activation')(x)
branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_10_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(128, 1, strides=1, padding='same', use_bias=False, name= 'Block17_10_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_10_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block17_10_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block17_10_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block17_10_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -377,7 +377,7 @@ def InceptionResNetV2():
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block17_10_Activation')(x) x = Activation('relu', name='Block17_10_Activation')(x)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080 # Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = Conv2D(256, 1, strides=1, padding='same', use_bias=False, name= 'Mixed_7a_Branch_0_Conv2d_0a_1x1') (x) branch_0 = Conv2D(256, 1, strides=1, padding='same', use_bias=False, name= 'Mixed_7a_Branch_0_Conv2d_0a_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Mixed_7a_Branch_0_Conv2d_0a_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Mixed_7a_Branch_0_Conv2d_0a_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Mixed_7a_Branch_0_Conv2d_0a_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Mixed_7a_Branch_0_Conv2d_0a_1x1_Activation')(branch_0)
@ -404,7 +404,7 @@ def InceptionResNetV2():
x = Concatenate(axis=3, name='Mixed_7a')(branches) x = Concatenate(axis=3, name='Mixed_7a')(branches)
# 5x Block8 (Inception-ResNet-C block): # 5x Block8 (Inception-ResNet-C block):
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_1_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_1_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_1_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_1_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_1_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_1_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -423,7 +423,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block8_1_Activation')(x) x = Activation('relu', name='Block8_1_Activation')(x)
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_2_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_2_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_2_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_2_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_2_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -442,7 +442,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block8_2_Activation')(x) x = Activation('relu', name='Block8_2_Activation')(x)
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_3_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_3_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_3_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_3_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_3_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -461,7 +461,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block8_3_Activation')(x) x = Activation('relu', name='Block8_3_Activation')(x)
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_4_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_4_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_4_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_4_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_4_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -480,7 +480,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block8_4_Activation')(x) x = Activation('relu', name='Block8_4_Activation')(x)
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_5_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_5_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_5_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_5_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_5_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -499,7 +499,7 @@ def InceptionResNetV2():
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 0.2})(up)
x = add([x, up]) x = add([x, up])
x = Activation('relu', name='Block8_5_Activation')(x) x = Activation('relu', name='Block8_5_Activation')(x)
branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_6_Branch_0_Conv2d_1x1') (x) branch_0 = Conv2D(192, 1, strides=1, padding='same', use_bias=False, name= 'Block8_6_Branch_0_Conv2d_1x1') (x)
branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_6_Branch_0_Conv2d_1x1_BatchNorm')(branch_0) branch_0 = BatchNormalization(axis=3, momentum=0.995, epsilon=0.001, scale=False, name='Block8_6_Branch_0_Conv2d_1x1_BatchNorm')(branch_0)
branch_0 = Activation('relu', name='Block8_6_Branch_0_Conv2d_1x1_Activation')(branch_0) branch_0 = Activation('relu', name='Block8_6_Branch_0_Conv2d_1x1_Activation')(branch_0)
@ -517,7 +517,7 @@ def InceptionResNetV2():
up = Conv2D(1792, 1, strides=1, padding='same', use_bias=True, name= 'Block8_6_Conv2d_1x1') (mixed) up = Conv2D(1792, 1, strides=1, padding='same', use_bias=True, name= 'Block8_6_Conv2d_1x1') (mixed)
up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 1})(up) up = Lambda(scaling, output_shape=K.int_shape(up)[1:], arguments={'scale': 1})(up)
x = add([x, up]) x = add([x, up])
# Classification block # Classification block
x = GlobalAveragePooling2D(name='AvgPool')(x) x = GlobalAveragePooling2D(name='AvgPool')(x)
x = Dropout(1.0 - 0.8, name='Dropout')(x) x = Dropout(1.0 - 0.8, name='Dropout')(x)
@ -530,23 +530,25 @@ def InceptionResNetV2():
return model return model
def loadModel(url = 'https://drive.google.com/uc?id=1971Xk5RwedbudGgTIrGAL4F7Aifu7id1'): #url = 'https://drive.google.com/uc?id=1971Xk5RwedbudGgTIrGAL4F7Aifu7id1'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/facenet_weights.h5'):
model = InceptionResNetV2() model = InceptionResNetV2()
#----------------------------------- #-----------------------------------
home = str(Path.home()) home = str(Path.home())
if os.path.isfile(home+'/.deepface/weights/facenet_weights.h5') != True: if os.path.isfile(home+'/.deepface/weights/facenet_weights.h5') != True:
print("facenet_weights.h5 will be downloaded...") print("facenet_weights.h5 will be downloaded...")
output = home+'/.deepface/weights/facenet_weights.h5' output = home+'/.deepface/weights/facenet_weights.h5'
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#----------------------------------- #-----------------------------------
model.load_weights(home+'/.deepface/weights/facenet_weights.h5') model.load_weights(home+'/.deepface/weights/facenet_weights.h5')
#----------------------------------- #-----------------------------------
return model return model

20
deepface/basemodels/OpenFace.py
View File

@ -13,7 +13,9 @@ from tensorflow.keras import backend as K
#--------------------------------------- #---------------------------------------
def loadModel(url = 'https://drive.google.com/uc?id=1LSe1YCV1x-BfNnfb7DFZTNpv_Q9jITxn'): #url = 'https://drive.google.com/uc?id=1LSe1YCV1x-BfNnfb7DFZTNpv_Q9jITxn'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/openface_weights.h5'):
myInput = Input(shape=(96, 96, 3)) myInput = Input(shape=(96, 96, 3))
x = ZeroPadding2D(padding=(3, 3), input_shape=(96, 96, 3))(myInput) x = ZeroPadding2D(padding=(3, 3), input_shape=(96, 96, 3))(myInput)
@ -229,19 +231,19 @@ def loadModel(url = 'https://drive.google.com/uc?id=1LSe1YCV1x-BfNnfb7DFZTNpv_Q9
model = Model(inputs=[myInput], outputs=norm_layer) model = Model(inputs=[myInput], outputs=norm_layer)
#----------------------------------- #-----------------------------------
home = str(Path.home()) home = str(Path.home())
if os.path.isfile(home+'/.deepface/weights/openface_weights.h5') != True: if os.path.isfile(home+'/.deepface/weights/openface_weights.h5') != True:
print("openface_weights.h5 will be downloaded...") print("openface_weights.h5 will be downloaded...")
output = home+'/.deepface/weights/openface_weights.h5' output = home+'/.deepface/weights/openface_weights.h5'
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#----------------------------------- #-----------------------------------
model.load_weights(home+'/.deepface/weights/openface_weights.h5') model.load_weights(home+'/.deepface/weights/openface_weights.h5')
#----------------------------------- #-----------------------------------
return model return model

35
deepface/basemodels/VGGFace.py
View File

@ -12,7 +12,7 @@ else:
from tensorflow import keras from tensorflow import keras
from tensorflow.keras.models import Model, Sequential from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dense, Dropout, Activation from tensorflow.keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dense, Dropout, Activation
#--------------------------------------- #---------------------------------------
def baseModel(): def baseModel():
@ -60,34 +60,31 @@ def baseModel():
model.add(Convolution2D(2622, (1, 1))) model.add(Convolution2D(2622, (1, 1)))
model.add(Flatten()) model.add(Flatten())
model.add(Activation('softmax')) model.add(Activation('softmax'))
return model return model
def loadModel(url = 'https://drive.google.com/uc?id=1CPSeum3HpopfomUEK1gybeuIVoeJT_Eo'): #url = 'https://drive.google.com/uc?id=1CPSeum3HpopfomUEK1gybeuIVoeJT_Eo'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/vgg_face_weights.h5'):
model = baseModel() model = baseModel()
#----------------------------------- #-----------------------------------
home = str(Path.home()) home = str(Path.home())
output = home+'/.deepface/weights/vgg_face_weights.h5' output = home+'/.deepface/weights/vgg_face_weights.h5'
if os.path.isfile(output) != True: if os.path.isfile(output) != True:
print("vgg_face_weights.h5 will be downloaded...") print("vgg_face_weights.h5 will be downloaded...")
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#----------------------------------- #-----------------------------------
try: model.load_weights(output)
model.load_weights(output)
except Exception as err:
print(str(err))
print("Pre-trained weight could not be loaded.")
print("You might try to download the pre-trained weights from the url ", url, " and copy it to the ", output)
#----------------------------------- #-----------------------------------
#TO-DO: why? #TO-DO: why?
vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output) vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)
return vgg_face_descriptor return vgg_face_descriptor

4
deepface/extendedmodels/Age.py
View File

@ -16,7 +16,9 @@ elif tf_version == 2:
from tensorflow.keras.models import Model, Sequential from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Convolution2D, Flatten, Activation from tensorflow.keras.layers import Convolution2D, Flatten, Activation
def loadModel(url = 'https://drive.google.com/uc?id=1YCox_4kJ-BYeXq27uUbasu--yz28zUMV'): #url = 'https://drive.google.com/uc?id=1YCox_4kJ-BYeXq27uUbasu--yz28zUMV'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/age_model_weights.h5'):
model = VGGFace.baseModel() model = VGGFace.baseModel()

11
deepface/extendedmodels/Emotion.py
View File

@ -15,7 +15,9 @@ elif tf_version == 2:
from tensorflow.keras.models import Model, Sequential from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D, Flatten, Dense, Dropout from tensorflow.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D, Flatten, Dense, Dropout
def loadModel(url = 'https://drive.google.com/uc?id=13iUHHP3SlNg53qSuQZDdHDSDNdBP9nwy'): #url = 'https://drive.google.com/uc?id=13iUHHP3SlNg53qSuQZDdHDSDNdBP9nwy'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/facial_expression_model_weights.h5'):
num_classes = 7 num_classes = 7
@ -52,15 +54,18 @@ def loadModel(url = 'https://drive.google.com/uc?id=13iUHHP3SlNg53qSuQZDdHDSDNdB
if os.path.isfile(home+'/.deepface/weights/facial_expression_model_weights.h5') != True: if os.path.isfile(home+'/.deepface/weights/facial_expression_model_weights.h5') != True:
print("facial_expression_model_weights.h5 will be downloaded...") print("facial_expression_model_weights.h5 will be downloaded...")
#TO-DO: upload weights to google drive output = home+'/.deepface/weights/facial_expression_model_weights.h5'
gdown.download(url, output, quiet=False)
#zip """
#google drive source downloads zip
output = home+'/.deepface/weights/facial_expression_model_weights.zip' output = home+'/.deepface/weights/facial_expression_model_weights.zip'
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#unzip facial_expression_model_weights.zip #unzip facial_expression_model_weights.zip
with zipfile.ZipFile(output, 'r') as zip_ref: with zipfile.ZipFile(output, 'r') as zip_ref:
zip_ref.extractall(home+'/.deepface/weights/') zip_ref.extractall(home+'/.deepface/weights/')
"""
model.load_weights(home+'/.deepface/weights/facial_expression_model_weights.h5') model.load_weights(home+'/.deepface/weights/facial_expression_model_weights.h5')

4
deepface/extendedmodels/Gender.py
View File

@ -14,7 +14,9 @@ elif tf_version == 2:
from tensorflow.keras.models import Model, Sequential from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Convolution2D, Flatten, Activation from tensorflow.keras.layers import Convolution2D, Flatten, Activation
def loadModel(url = 'https://drive.google.com/uc?id=1wUXRVlbsni2FN9-jkS_f4UTUrm1bRLyk'): #url = 'https://drive.google.com/uc?id=1wUXRVlbsni2FN9-jkS_f4UTUrm1bRLyk'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/gender_model_weights.h5'):
model = VGGFace.baseModel() model = VGGFace.baseModel()

11
deepface/extendedmodels/Race.py
View File

@ -16,7 +16,9 @@ elif tf_version == 2:
from tensorflow.keras.models import Model, Sequential from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Convolution2D, Flatten, Activation from tensorflow.keras.layers import Convolution2D, Flatten, Activation
def loadModel(url = 'https://drive.google.com/uc?id=1nz-WDhghGQBC4biwShQ9kYjvQMpO6smj'): #url = 'https://drive.google.com/uc?id=1nz-WDhghGQBC4biwShQ9kYjvQMpO6smj'
def loadModel(url = 'https://github.com/serengil/deepface_models/releases/download/v1.0/race_model_single_batch.h5'):
model = VGGFace.baseModel() model = VGGFace.baseModel()
@ -41,13 +43,18 @@ def loadModel(url = 'https://drive.google.com/uc?id=1nz-WDhghGQBC4biwShQ9kYjvQMp
if os.path.isfile(home+'/.deepface/weights/race_model_single_batch.h5') != True: if os.path.isfile(home+'/.deepface/weights/race_model_single_batch.h5') != True:
print("race_model_single_batch.h5 will be downloaded...") print("race_model_single_batch.h5 will be downloaded...")
#zip output = home+'/.deepface/weights/race_model_single_batch.h5'
gdown.download(url, output, quiet=False)
"""
#google drive source downloads zip
output = home+'/.deepface/weights/race_model_single_batch.zip' output = home+'/.deepface/weights/race_model_single_batch.zip'
gdown.download(url, output, quiet=False) gdown.download(url, output, quiet=False)
#unzip race_model_single_batch.zip #unzip race_model_single_batch.zip
with zipfile.ZipFile(output, 'r') as zip_ref: with zipfile.ZipFile(output, 'r') as zip_ref:
zip_ref.extractall(home+'/.deepface/weights/') zip_ref.extractall(home+'/.deepface/weights/')
"""
race_model.load_weights(home+'/.deepface/weights/race_model_single_batch.h5') race_model.load_weights(home+'/.deepface/weights/race_model_single_batch.h5')