在 Keras 中修改图层参数 [英] Modify layer parameters in Keras

问题描述

我对更新 Keras 中现有的图层参数感兴趣(不是删除图层并插入一个新图层，而是修改现有参数).

I am interested in updating existing layer parameters in Keras (not removing a layer and inserting a new one instead, rather just modifying existing parameters).

我将举一个我正在编写的函数的例子:

I will give an example of a function I'm writing:

def add_filters(self, model):
    conv_indices = [i for i, layer in enumerate(model.layers) if 'convolution' in layer.get_config()['name']]
    random_conv_index = random.randint(0, len(conv_indices)-1)
    factor = 2
    conv_layer = model.layers[random_conv_index]
    conv_layer.filters = conv_layer.filters * factor
    print('new conv layer filters after transform is:', conv_layer.filters)
    print('just to make sure, its:', model.layers[random_conv_index].filters)
    return model

所以这里基本上发生的事情是我从我的网络中随机抽取一个卷积层(我所有的卷积层的名称中都有卷积")并尝试将过滤器加倍.据我所知，这在任何情况下都不会导致输入/输出大小兼容性的任何编译问题".

so what's basically happening here is me taking a random convolutional layer from my network (all my conv layers have 'convolution' in their name) and trying to double the filters. As far as I know this shouldn't cause any 'compilation issues' with input/output size compatibility in any case.

问题是，我的模型根本没有改变.我最后添加的 2 个打印输出打印了正确的数字(是之前过滤器数量的两倍).但是当我编译模型并打印model.summary()时，还是看到了之前的过滤量.

The thing is, my model doesn't change at all. The 2 print-outs I added in the end print the correct number (double the previous amount of filters). But when I compile the model and print model.summary(), I still see the previous filter amount.

顺便说一句，我并不局限于 Keras.例如，如果有人知道如何使用 PyTorch 实现这一点，我也会购买它:D

BTW, I'm not constricted to Keras. If anyone has an idea how to pull this off with PyTorch for example I'll also buy it :D

推荐答案

好吧，如果您想基于现有模型创建新模型的架构，尽管进行一些修改，您可以使用 to_json 和 model_from_json() 函数.下面是一个例子:

Well, if you would like to create the architecture of a new model based on an existing model, though with some modifications, you can use to_json and model_from_json() functions. Here is an example:

model = Sequential()
model.add(Conv2D(10, (3,3), input_shape=(100,100,3)))
model.add(Conv2D(40, (3,3)))

model.summary()

模型摘要:

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_12 (Conv2D)           (None, 98, 98, 10)        280       
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 96, 96, 40)        3640      
=================================================================
Total params: 3,920
Trainable params: 3,920
Non-trainable params: 0
_________________________________________________________________

现在我们修改第一层的过滤器数量，并基于修改后的架构创建一个新模型:

Now we modify the number of filters of the first layer and create a new model based on the modified architecture:

from keras.models import model_from_json

model.layers[0].filters *= 2
new_model = model_from_json(model.to_json())
new_model.summary()

新模型摘要:

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_12 (Conv2D)           (None, 98, 98, 20)        560       
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 96, 96, 40)        7240      
=================================================================
Total params: 7,800
Trainable params: 7,800
Non-trainable params: 0
_________________________________________________________________

也可以直接修改model.to_json()的输出，无需修改模型实例.

You can also modify the output of model.to_json() directly without modifying the model instance.

您可以轻松地使用 get_weights() 方法来获取卷积层的当前权重.它将返回两个 numpy 数组的列表.第一个对应于过滤器权重，第二个对应于偏置参数.然后你可以使用 set_weights() 方法来设置新的权重:

You can easily use get_weights() method to get the current weights of the convolution layer. It would return a list of two numpy arrays. The first one corresponds to filter weights and the second one corresponds to bias parameters. Then you can use set_weights() method to set the new weights:

conv_layer = model.layers[random_conv_index]
weights = conv_layer.get_weights()
weights[0] *= factor  # multiply filter weights by `factor`
conv_layer.set_weights(weights)

作为旁注，您在代码中使用的卷积层的 filters 属性对应于该层中过滤器的数量，而不是它们的权重.

As a side note, the filters attribute of a convolution layer which you have used in your code corresponds to the number of filters in this layer and not their weights.

这篇关于在 Keras 中修改图层参数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！