Skip to content

Instantly share code, notes, and snippets.

@baraldilorenzo

baraldilorenzo/readme.md

Created January 16, 2016 12:57
Show Gist options
  • Save baraldilorenzo/8d096f48a1be4a2d660d to your computer and use it in GitHub Desktop.
Save baraldilorenzo/8d096f48a1be4a2d660d to your computer and use it in GitHub Desktop.
Download ZIP
VGG-19 pre-trained model for Keras
Raw
readme.md

##VGG19 model for Keras

This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

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

Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
arXiv:1409.1556

In the paper, the VGG-19 model is denoted as configuration E. It achieves 7.5% top-5 error on ILSVRC-2012-val, 7.3% top-5 error on ILSVRC-2012-test.

Please cite the paper if you use the models.

###Contents:

model and usage demo: see vgg-19_keras.py

weights: vgg19_weights.h5

Raw
vgg-19_keras.py
from keras.models import Sequential
from keras.layers.core import Flatten, Dense, Dropout
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD
import cv2, numpy as np
def VGG_19(weights_path=None):
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
if weights_path:
model.load_weights(weights_path)
return model
if __name__ == "__main__":
im = cv2.resize(cv2.imread('cat.jpg'), (224, 224)).astype(np.float32)
im[:,:,0] -= 103.939
im[:,:,1] -= 116.779
im[:,:,2] -= 123.68
im = im.transpose((2,0,1))
im = np.expand_dims(im, axis=0)
# Test pretrained model
model = VGG_19('vgg19_weights.h5')
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='categorical_crossentropy')
out = model.predict(im)
print np.argmax(out)
@lusiaj
Copy link

lusiaj commented Sep 25, 2025

lusia

Model Architecture: The Gist includes a Keras implementation of the VGG-19 architecture, which consists of 19 layers: 16 convolutional layers and 3 fully connected layers.

Weights: The pre-trained weights for the model are provided in the vgg19_weights.h5 file. These weights were obtained by directly converting the original Caffe model provided by the authors.

Usage: A usage demo is provided in the vgg-19_keras.py script, which demonstrates how to load the model and use it for predictions.

Citation: The original paper describing the VGG-19 architecture is:

Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556.

This indicates that the Gist is recognized as a valuable resource for obtaining a pre-trained VGG-19 model for Keras.

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