Keras的名字重量

时间:2016-11-05 22:51:32

标签: keras

使用Keras训练模型后,我可以使用以下方法获得权重数组列表:

myModel.get_weights() 

myLayer.get_weights()

我想知道每个重量阵列对应的名字。我知道如何通过保存模型和解析HDF5文件来间接地做到这一点,但肯定必须有直接的方法来实现这一目标吗?

1 个答案:

答案 0 :(得分:9)

函数get_weights返回一个numpy数组列表,其中没有名称信息。

至于Model.get_weights(),它只是每个[展平]图层Layer.get_weights()的串联。

但是,Layer.weights可以直接访问后端变量,这些,是的,可能有一个名称。然后解决方案是遍历每个图层的每个权重,检索其name属性。

VGG16的一个例子:

from keras.applications.vgg16 import VGG16


model = VGG16()

names = [weight.name for layer in model.layers for weight in layer.weights]
weights = model.get_weights()

for name, weight in zip(names, weights):
    print(name, weight.shape)

输出:

block1_conv1_W_6:0 (3, 3, 3, 64)
block1_conv1_b_6:0 (64,)
block1_conv2_W_6:0 (3, 3, 64, 64)
block1_conv2_b_6:0 (64,)
block2_conv1_W_6:0 (3, 3, 64, 128)
block2_conv1_b_6:0 (128,)
block2_conv2_W_6:0 (3, 3, 128, 128)
block2_conv2_b_6:0 (128,)
block3_conv1_W_6:0 (3, 3, 128, 256)
block3_conv1_b_6:0 (256,)
block3_conv2_W_6:0 (3, 3, 256, 256)
block3_conv2_b_6:0 (256,)
block3_conv3_W_6:0 (3, 3, 256, 256)
block3_conv3_b_6:0 (256,)
block4_conv1_W_6:0 (3, 3, 256, 512)
block4_conv1_b_6:0 (512,)
block4_conv2_W_6:0 (3, 3, 512, 512)
block4_conv2_b_6:0 (512,)
block4_conv3_W_6:0 (3, 3, 512, 512)
block4_conv3_b_6:0 (512,)
block5_conv1_W_6:0 (3, 3, 512, 512)
block5_conv1_b_6:0 (512,)
block5_conv2_W_6:0 (3, 3, 512, 512)
block5_conv2_b_6:0 (512,)
block5_conv3_W_6:0 (3, 3, 512, 512)
block5_conv3_b_6:0 (512,)
fc1_W_6:0 (25088, 4096)
fc1_b_6:0 (4096,)
fc2_W_6:0 (4096, 4096)
fc2_b_6:0 (4096,)
predictions_W_6:0 (4096, 1000)
predictions_b_6:0 (1000,)