tensorflow提取VGG特征

我们知道，再网络训练好之后，只需要forward过程就能做预测，当然，我们也可以直接把这个网络当成一个feature extractor来用，可以直接用任何一层的输出作为特征，根据R-CNN论文对Alexnet的实验结果，如果不做fine-tuning，pool5和fc6和fc7的特征效果并没有很强的提升，所以，如果直接用作feature extractor，直接用pool的最后一层输出就OK.

这里是一个简单的演示，提取VGG的pool5层特征，存储为.mat文件；

    import scipy.io as sio
   from scipy.misc import imread, imresize

   sess = tf.Session()
    imgs = tf.placeholder(tf.float32, [None, 224, 224, 3])
    vgg = vgg16(imgs, '/aa/data/vgg16_weights.npz', sess)

    img1 = imread('/aa/data/laska.png', mode='RGB')
    img1 = imresize(img1, (224, 224))
    path = '/aa/data/AllSample/'

    for i in range(1,211):
        img = imread(path+str(i)+'.jpg',mode='RGB')
        print(path+str(i)+'.jpg')
        img = imresize(img, (224, 224))
    
        feature = sess.run(vgg.pool5, feed_dict={vgg.imgs: [img]})
        feature = np.reshape(feature,[7,7,512])
        dic = {'features':feature}
        sio.savemat('/aa/data/features/'+str(i)+'.mat',dic)
    
#     features = feature.eval(session=sess)
#     features = np.reshape(features,[7,7,512])