How to change in keras Conv2D (2d convolutional layer) kernel_initializer config parameters?

Question

I am trying to build a model similirar to ResNet, just for understan every detail in the layers, but when I use get_config for the conv2D layers, the scale, mode and distribution in kernel_initializer are different to the default congiguration. How can I change this parameters?. See lines 14-18 first for the resnet Conv2D and second the regular Conv2D

1  #resnet Conv2D   
2  resnet_model.layers[2].get_weights()
3
4  {'name': 'conv1',
5  'trainable': True,
6  'filters': 64,
7  'kernel_size': (7, 7),
8  'strides': (2, 2),
9  'padding': 'valid',
10 'data_format': 'channels_last',
11 'dilation_rate': (1, 1),
12 'activation': 'linear',
13 'use_bias': True,
14 'kernel_initializer': {'class_name': 'VarianceScaling',
15  'config': {'scale': 2.0, 
16   'mode': 'fan_in',
17   'distribution': 'normal',
18   'seed': None}},
19 'bias_initializer': {'class_name': 'Zeros', 'config': {}},
20 'kernel_regularizer': None,
21 'bias_regularizer': None,
22 'activity_regularizer': None,
23 'kernel_constraint': None,
24 'bias_constraint': None}


1  #normal Conv2D   
2  model.layers[2].get_weights()
3
4  {'name': 'conv1',
5  'trainable': True,
6  'filters': 64,
7  'kernel_size': (7, 7),
8  'strides': (2, 2),
9  'padding': 'valid',
10 'data_format': 'channels_last',
11 'dilation_rate': (1, 1),
12 'activation': 'linear',
13 'use_bias': True,
14 'kernel_initializer': {'class_name': 'VarianceScaling',
15  'config': {'scale': 1.0, 
16   'mode': 'fan_avg',
17   'distribution': 'uniform,',
18   'seed': None}},
19 'bias_initializer': {'class_name': 'Zeros', 'config': {}},
20 'kernel_regularizer': None,
21 'bias_regularizer': None,
22 'activity_regularizer': None,
23 'kernel_constraint': None,
24 'bias_constraint': None}

Answer 1

from keras.initializers import VarianceScaling

convLayer = Conv2D(filters, kernel_size, ..., 
                   kernel_initializer = VarianceScaling(scale=2.0, 
                                                        mode='fan_in', 
                                                        distribution='normal', 
                                                        seed=None), 
                   ...)

Answer 2

You might want to take a look at the initializers documentation : https://keras.io/initializers/

To change this param, you will need to select an initializer by setting kernel_initializer class_name parameter. Then, you can pass argument to that initializer through the config field.