Skip to content

Instantly share code, notes, and snippets.

@EncodeTS

EncodeTS/keras VGG-Face Model.md

Last active February 19, 2024 06:56
Show Gist options
  • Save EncodeTS/6bbe8cb8bebad7a672f0d872561782d9 to your computer and use it in GitHub Desktop.
Save EncodeTS/6bbe8cb8bebad7a672f0d872561782d9 to your computer and use it in GitHub Desktop.
Download ZIP
VGG-Face model for keras
Raw
keras VGG-Face Model.md

VGG-Face model for Keras

This is the Keras model of VGG-Face.

It has been obtained through the following method:

  • vgg-face-keras:directly convert the vgg-face matconvnet model to keras model
  • vgg-face-keras-fc:first convert vgg-face caffe model to mxnet model,and then convert it to keras model

Details about the network architecture can be found in the following paper:

Deep Face Recognition
O. M. Parkhi, A. Vedaldi, A. Zisserman
British Machine Vision Conference, 2015

Please cite the paper if you use the models.

Contents:

model and usage demo: see vgg-face-keras.py or vgg-face-keras-fc.py

The only difference between them is the last few layers(see the code and you'll understand),but they produce the same result.

weights: 

Notice:

Please use this model in theano mode.

Raw
vgg-face-keras-fc.py
from keras.models import Model
from keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dense, Dropout
from PIL import Image
import numpy as np
def vgg_face(weights_path=None):
img = Input(shape=(3, 224, 224))
pad1_1 = ZeroPadding2D(padding=(1, 1))(img)
conv1_1 = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(pad1_1)
pad1_2 = ZeroPadding2D(padding=(1, 1))(conv1_1)
conv1_2 = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(pad1_2)
pool1 = MaxPooling2D((2, 2), strides=(2, 2))(conv1_2)
pad2_1 = ZeroPadding2D((1, 1))(pool1)
conv2_1 = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(pad2_1)
pad2_2 = ZeroPadding2D((1, 1))(conv2_1)
conv2_2 = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(pad2_2)
pool2 = MaxPooling2D((2, 2), strides=(2, 2))(conv2_2)
pad3_1 = ZeroPadding2D((1, 1))(pool2)
conv3_1 = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(pad3_1)
pad3_2 = ZeroPadding2D((1, 1))(conv3_1)
conv3_2 = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(pad3_2)
pad3_3 = ZeroPadding2D((1, 1))(conv3_2)
conv3_3 = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(pad3_3)
pool3 = MaxPooling2D((2, 2), strides=(2, 2))(conv3_3)
pad4_1 = ZeroPadding2D((1, 1))(pool3)
conv4_1 = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(pad4_1)
pad4_2 = ZeroPadding2D((1, 1))(conv4_1)
conv4_2 = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(pad4_2)
pad4_3 = ZeroPadding2D((1, 1))(conv4_2)
conv4_3 = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(pad4_3)
pool4 = MaxPooling2D((2, 2), strides=(2, 2))(conv4_3)
pad5_1 = ZeroPadding2D((1, 1))(pool4)
conv5_1 = Convolution2D(512, 3, 3, activation='relu', name='conv5_1')(pad5_1)
pad5_2 = ZeroPadding2D((1, 1))(conv5_1)
conv5_2 = Convolution2D(512, 3, 3, activation='relu', name='conv5_2')(pad5_2)
pad5_3 = ZeroPadding2D((1, 1))(conv5_2)
conv5_3 = Convolution2D(512, 3, 3, activation='relu', name='conv5_3')(pad5_3)
pool5 = MaxPooling2D((2, 2), strides=(2, 2))(conv5_3)
flat = Flatten()(pool5)
fc6 = Dense(4096, activation='relu', name='fc6')(flat)
fc6_drop = Dropout(0.5)(fc6)
fc7 = Dense(4096, activation='relu', name='fc7')(fc6_drop)
fc7_drop = Dropout(0.5)(fc7)
out = Dense(2622, activation='softmax', name='fc8')(fc7_drop)
model = Model(input=img, output=out)
if weights_path:
model.load_weights(weights_path)
return model
if __name__ == "__main__":
im = Image.open('A.J._Buckley.jpg')
im = im.resize((224,224))
im = np.array(im).astype(np.float32)
# im[:,:,0] -= 129.1863
# im[:,:,1] -= 104.7624
# im[:,:,2] -= 93.5940
im = im.transpose((2,0,1))
im = np.expand_dims(im, axis=0)
# Test pretrained model
model = vgg_face('vgg-face-keras-fc.h5')
out = model.predict(im)
print(out[0][0])
Raw
vgg-face-keras.py
from keras.models import Model
from keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dropout, Activation
from PIL import Image
import numpy as np
def vgg_face(weights_path=None):
img = Input(shape=(3, 224, 224))
pad1_1 = ZeroPadding2D(padding=(1, 1))(img)
conv1_1 = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(pad1_1)
pad1_2 = ZeroPadding2D(padding=(1, 1))(conv1_1)
conv1_2 = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(pad1_2)
pool1 = MaxPooling2D((2, 2), strides=(2, 2))(conv1_2)
pad2_1 = ZeroPadding2D((1, 1))(pool1)
conv2_1 = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(pad2_1)
pad2_2 = ZeroPadding2D((1, 1))(conv2_1)
conv2_2 = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(pad2_2)
pool2 = MaxPooling2D((2, 2), strides=(2, 2))(conv2_2)
pad3_1 = ZeroPadding2D((1, 1))(pool2)
conv3_1 = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(pad3_1)
pad3_2 = ZeroPadding2D((1, 1))(conv3_1)
conv3_2 = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(pad3_2)
pad3_3 = ZeroPadding2D((1, 1))(conv3_2)
conv3_3 = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(pad3_3)
pool3 = MaxPooling2D((2, 2), strides=(2, 2))(conv3_3)
pad4_1 = ZeroPadding2D((1, 1))(pool3)
conv4_1 = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(pad4_1)
pad4_2 = ZeroPadding2D((1, 1))(conv4_1)
conv4_2 = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(pad4_2)
pad4_3 = ZeroPadding2D((1, 1))(conv4_2)
conv4_3 = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(pad4_3)
pool4 = MaxPooling2D((2, 2), strides=(2, 2))(conv4_3)
pad5_1 = ZeroPadding2D((1, 1))(pool4)
conv5_1 = Convolution2D(512, 3, 3, activation='relu', name='conv5_1')(pad5_1)
pad5_2 = ZeroPadding2D((1, 1))(conv5_1)
conv5_2 = Convolution2D(512, 3, 3, activation='relu', name='conv5_2')(pad5_2)
pad5_3 = ZeroPadding2D((1, 1))(conv5_2)
conv5_3 = Convolution2D(512, 3, 3, activation='relu', name='conv5_3')(pad5_3)
pool5 = MaxPooling2D((2, 2), strides=(2, 2))(conv5_3)
fc6 = Convolution2D(4096, 7, 7, activation='relu', name='fc6')(pool5)
fc6_drop = Dropout(0.5)(fc6)
fc7 = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(fc6_drop)
fc7_drop = Dropout(0.5)(fc7)
fc8 = Convolution2D(2622, 1, 1, name='fc8')(fc7_drop)
flat = Flatten()(fc8)
out = Activation('softmax')(flat)
model = Model(input=img, output=out)
if weights_path:
model.load_weights(weights_path)
return model
if __name__ == "__main__":
im = Image.open('A.J._Buckley.jpg')
im = im.resize((224,224))
im = np.array(im).astype(np.float32)
# im[:,:,0] -= 129.1863
# im[:,:,1] -= 104.7624
# im[:,:,2] -= 93.5940
im = im.transpose((2,0,1))
im = np.expand_dims(im, axis=0)
# Test pretrained model
model = vgg_face('vgg-face-keras.h5')
out = model.predict(im)
print(out[0][0])
@mzaradzki
Copy link

Hi @slashstar, @EncodeTS,

To convert the weights from MatConvNet I wrote this code :
https://github.com/mzaradzki/neuralnets/blob/master/vgg_faces_keras/vgg_faces_demo.ipynb

The weights are translated using the scipy.io.loadmat function

Hope this helps.

@oxydron
Copy link

oxydron commented Apr 4, 2017

@EncodeTS This model run on which python, tensorflow and keras versions?

@bogdan-kulynych
Copy link

https://github.com/rcmalli/keras-vggface

@monktastic
Copy link

I'm running this with tensorflow as the backend (but with channels_first). The test picture gives me the wrong result. Did anyone else get it working?

@kushal-vangara
Copy link

@monktastic This works with tensorflow as backend when you change the configuration. Could you specify the error message that you are getting?

@jugatsingh
Copy link

@monktastic I have the exact same issue. Were you able to solve it?

@rkaushik97
Copy link

what is the dataset used for this model?

@wen-fei
Copy link

wen-fei commented Mar 14, 2018

Thanks, is anybody know the pytorch version?

@kristianSN
Copy link

Question: The mean subtraction done in

im[:,:,0] -= 129.1863

im[:,:,1] -= 104.7624

im[:,:,2] -= 93.5940

1: Are these the channel means obtained by the people who trained the VGG face?
2: If so, why are they commented?

@shahryarabaki
Copy link

I got this error when I ran the code:

VGG_Tensorflow_V2.py:15: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:17: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:21: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:23: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu'))
Traceback (most recent call last):
  File "/home/mshafaei/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1576, in _create_c_op
    c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

@afruzan
Copy link

afruzan commented Nov 24, 2018 •
edited
Loading

I also got this error when I ran vgg-face-keras.py:
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

@finger2vec
Copy link

I also got this error when I ran vgg-face-keras.py:
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

You could add channels_first as follow like this

from keras import backend as K
K.set_image_data_format('channels_first')

@finger2vec
Copy link

I got this error when I ran the code:

VGG_Tensorflow_V2.py:15: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:17: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:21: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu'))
VGG_Tensorflow_V2.py:23: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu'))
Traceback (most recent call last):
  File "/home/mshafaei/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1576, in _create_c_op
    c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

You could add channels_first as follow like this

from keras import backend as K
K.set_image_data_format('channels_first')

@wgsjack199213
Copy link

00000001
Here is a test picture,the probability of the picture belonging to the first class should be 0.99953598.

Sorry but I ran the vgg-face-keras.py program using theano backend and the maximum probability is only 0.207927 (class 36, not class 1). Did I make any mistake?

Thanks!

@afruzan
Copy link

afruzan commented Feb 17, 2019 •
edited
Loading

Question: The mean subtraction done in
im[:,:,0] -= 129.1863
im[:,:,1] -= 104.7624
im[:,:,2] -= 93.5940
1: Are these the channel means obtained by the people who trained the VGG face?
2: If so, why are they commented?

these are my questions too... any one can answer how these means are computed? is it means we should also subtract these means from train images?

@aco92
Copy link

aco92 commented Apr 4, 2019

00000001
Here is a test picture,the probability of the picture belonging to the first class should be 0.99953598.

Sorry but I ran the vgg-face-keras.py program using theano backend and the maximum probability is only 0.207927 (class 36, not class 1). Did I make any mistake?

Thanks!

I run it with tf backend and max probability for that test image is 0.20376973. Does anybody know why we are not getting expected result?

Regards,
Aleksandar

@rhlshah
Copy link

rhlshah commented Jun 11, 2019

@EncodeTS,
I run it with tf backend but I am getting system error :" Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2".Pls help me out.

@moe-assal
Copy link

@rhlshah
don't worry about this problem. any program you run will work as usual. the reason this happening is that you are using a CPU that supports AVX2, which is a set of instructions that your CPU can do. it will accelerate some vector operations. you can install another binary of TensorFlow but i don't recommend that since it's a hard thing to do.

@wayne841213
Copy link

Try this https://github.com/wayne841213/VGGFace/blob/master/vgg-face-keras.py
My result is 0.99910444

@sohaibwaheedgithub
Copy link

I am getting this error while using "vgg-face-keras.h5"
Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling2d_2/MaxPool}} = MaxPoolT=DT_FLOAT, data_format="NCHW", explicit_paddings=[], ksize=[1, 1, 2, 2], padding="VALID", strides=[1, 1, 2, 2]' with input shapes: [?,256,1,1].

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment