VGG Model is introduced

VGG(Oxford Visual Geometry Group) The model is 2014 year ILSVRC Second place in the competition ,, from Karen Simonyan and Andrew Zisserman Realization .VGG It's a convolutional neural network model , Is in AlexNet Improvements based on .

TensorFLow Of keras Integrated in the library VGG16、VGG19 Model , You can print the structure of the model , Let's say VGG16 Take as an example to illustrate the model structure ：

from tensorflow.python.keras.applications.vgg16 import VGG16

model = VGG16()
print(model.summary())

VGG Model print results

Model: "vgg16"
_________________________________________________________________
Layer (type)                 Output Shape              Param # 
=================================================================
input_1 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
_________________________________________________________________
flatten (Flatten)            (None, 25088)             0         
_________________________________________________________________
fc1 (Dense)                  (None, 4096)              102764544 
_________________________________________________________________
fc2 (Dense)                  (None, 4096)              16781312  
_________________________________________________________________
predictions (Dense)          (None, 1000)              4097000   
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0

be based on VGG Image recognition

This article found two pictures of animals from the Internet , One is husky , Always a Jaguar , adopt VGG Model the image
Class identification .
Siberian Husky ：

jaguar ：

Code implementation

because VGG The model is integrated , So just call the corresponding API Can realize the task of image recognition .

Husky identifies

from tensorflow.python.keras.applications.vgg16 import VGG16,decode_predictions,preprocess_input
from tensorflow.python.keras.preprocessing.image import load_img,img_to_array

model = VGG16()
#  Change the input picture to (224,224) Fixed size of 
image = load_img("./dog.jpeg",target_size=(224,224))

#  Convert the picture to 3 Dimension group 
image = img_to_array(image)

#  The picture becomes 4 dimension , Satisfy VGG Input requirements of the model 
image = image.reshape(1,image.shape[0],image.shape[1],image.shape[2])

#  Preprocess the input picture 
image = preprocess_input(image)

#  Predict the categories of pictures 
y_predict = model.predict(image)

#  Decode the prediction results 
label = decode_predictions(y_predict)
res = label[0][0]
print(" The forecast category is :%s, The probability of :(%.2f%%)",(res[1],res[2]*100))

Running results

 The forecast category is :Siberian_husky, The probability of :(51.18%)

Jaguar recognition

from tensorflow.python.keras.applications.vgg16 import VGG16,decode_predictions,preprocess_input
from tensorflow.python.keras.preprocessing.image import load_img,img_to_array

model = VGG16()
#  Change the input picture to (224,224) Fixed size of 
image = load_img("./leopard.jpg",target_size=(224,224))

#  Convert the picture to 3 Dimension group 
image = img_to_array(image)

#  The picture becomes 4 dimension , Satisfy VGG Input requirements of the model 
image = image.reshape(1,image.shape[0],image.shape[1],image.shape[2])

#  Preprocess the input picture 
image = preprocess_input(image)

#  Predict the categories of pictures 
y_predict = model.predict(image)

#  Decode the prediction results 
label = decode_predictions(y_predict)
res = label[0][0]
print(" The forecast category is :%s, The probability of :(%.2f%%)",(res[1],res[2]*100))

Running results

 The forecast category is :leopard, The probability of :(62.83%)

summary

This paper introduces VGG Model , And based on TensorFlow.Keras Integrated in API Set the VGG Model . The accuracy of the model in the image recognition task is verified by two animal images .