TOC
如何计算一个BatchNormalization的参数？
# Environment：
# OS macOS Catalina 10.15.6
# python 3.7
# pip 20.1.1
# tensorflow 1.14.0
# Keras 2.1.5
from keras.models import Sequential
from keras.layers import Conv2D,BatchNormalization
model = Sequential();
# conv2d + max pooling
model.add(
Conv2D(96,
kernel_size = (11,11),
strides=(4, 4),
padding="valid",
input_shape=(224,224,3),
activation="relu")
); # output 55 * 55 * 96
# batchNormalization !
model.add(BatchNormalization()) # output
model.summary();
output:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 54, 54, 96) 34944
_________________________________________________________________
batch_normalization_1 (Batch (None, 54, 54, 96) 384
=================================================================
Total params: 35,328
Trainable params: 35,136
Non-trainable params: 192
_________________________________________________________________
问第二行batch_normalization_1右边的384是怎么计算？
这里参数=前一层卷积数量x4=96x4=384;
为什么是4呢？
因为共有这4组参数[gamma weights, beta weights, moving_mean(non-trainable), moving_variance(non-trainable)]，每组是96个；
REFERENCES: How the number of parameters associated with BatchNormalization layer is 2048?
「点个赞」
Yaohong
点个赞
使用微信扫描二维码完成支付
