在一些特征提取实验中,我注意到'model.pop()'功能没有按预期工作。对于像vgg16这样的预训练模型,在使用'model.pop()'之后,model.summary()显示该图层已被删除(预期的4096个特征),但是在通过新模型传递图像时,它会产生相同的结果。作为原始模型的特征数(1000)。无论删除多少层(包括完全空模型),它都会生成相同的输出。寻找关于可能是什么问题的指导。
#Passing an image through the full vgg16 model
model = VGG16(weights = 'imagenet', include_top = True, input_shape = (224,224,3))
img = image.load_img( 'cat.jpg', target_size=(224,224) )
img = image.img_to_array( img )
img = np.expand_dims( img, axis=0 )
img = preprocess_input( img )
features = model.predict( img )
features = features.flatten()
print(len(features)) #Expected 1000 features corresponding to 1000 imagenet classes
1000
model.layers.pop()
img = image.load_img( 'cat.jpg', target_size=(224,224) )
img = image.img_to_array( img )
img = np.expand_dims( img, axis=0 )
img = preprocess_input( img )
features2 = model.predict( img )
features2 = features2.flatten()
print(len(features2)) #Expected 4096 features, but still getting 1000. Why?
#No matter how many layers are removed, the output is still 1000
1000
谢谢!
在这里查看完整代码:https://github.com/keras-team/keras/files/1592641/bug-feature-extraction.pdf
在这里找到答案:https://github.com/keras-team/keras/issues/2371#issuecomment-308604552
from keras.models import Model
model.layers.pop() model2 = Model(model.input, model.layers[-1].output)
model2.summary()
model2表现正常。