如何使用Gammatone过滤器(或任何过滤器)初始化CNN图层以进行声音回归(或分类)? [英] How to initialize CNN Layer with Gammatone Filters (or any filter) for sound regression (Or Classification)?

问题描述

对于我的项目，我需要根据论文(使用 https://www.mdpi.com/1099-4300/20/12/990/htm )，(

For my project I need to initialize the CNN 1st Layer kernel with Gammatone filters according to papers ( https://www.mdpi.com/1099-4300/20/12/990/htm ) ,( https://www.groundai.com/project/end-to-end-environmental-sound-classification-using-a-1d-convolutional-neural-network/1 ) and a few others. What does it exactly mean to initialize the cnn kernel with Gammatone filter (Or any filter). How does one implement it? Is it a custom layer? Any tips and guidance would be much appreciated!

例如

conv_1 = Conv1D(filters = 64, kernel_size = 3, kernel_initializer = *insert Gammatone Filter*, padding = 'same', activation='relu', input_shape = (timesteps, features))(decoder_outputs3)

TIA

推荐答案

您可以使用TensorFlows 常量初始化程序:

You could use TensorFlows constant initializer:

gammatone_filter_kernel = np.array([...])
init_kernel = tf.constant_initializer(gammatone_filter_kernel)
# ...
conv_1 = Conv1D(filters = 64, kernel_size = 3, kernel_initializer = init_kernel, padding = 'same', activation='relu', input_shape = (timesteps, features))(decoder_outputs3)
# ...

如果过滤器是信号的某种预处理步骤，则可以将转换层的trainable属性设置为False，权重将固定.

If your filter is some kind of preprocessing step to your signal you could set the trainable attribute of the conv laver to False and the weights will be fixed.

这篇关于如何使用Gammatone过滤器(或任何过滤器)初始化CNN图层以进行声音回归(或分类)?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！