swayson · January 16, 2016 13:12 · Jan 16, 2016
diff --git a/readme.md b/readme.md
@@ -0,0 +1,22 @@
+##VGG19 model for Keras
+
+This is the [Keras](http://keras.io/) 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](https://gist.github.com/ksimonyan/3785162f95cd2d5fee77#file-readme-md) 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](https://drive.google.com/file/d/0Bz7KyqmuGsilZ2RVeVhKY0FyRmc/view?usp=sharing)
diff --git a/vgg-19_keras.py b/vgg-19_keras.py
@@ -0,0 +1,76 @@
+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)