如何在CNN中的每一层之后打印特征向量形状答案

【问题标题】：how to print feature vector shape after each layer in CNN如何在CNN中的每一层之后打印特征向量形状
【发布时间】：2019-06-22 04:04:37
【问题描述】：

我的CNN模型架构如下： def model_a(x_train):

input_batch = tflearn.layers.core.input_data(shape=(None, x_train.shape[1], x_train.shape[2], x_train.shape[3]))

input_batch=tflearn.layers.normalization.batch_normalization(input_batch)

network = tflearn.layers.conv.conv_2d(input_batch, 32, 5, activation='relu')
network = tflearn.layers.conv.max_pool_2d(network, 2,2)
network = tflearn.dropout(network, .8)

network = tflearn.layers.conv.conv_2d(network, 32, 5, activation='relu')
network = tflearn.layers.conv.max_pool_2d(network, 2,2)

network = tflearn.dropout(network, .8)

network = tflearn.fully_connected(network, 256, activation='relu')
network = tflearn.dropout(network, .8)
network = tflearn.fully_connected(network, 128, activation='relu')
network= tflearn.dropout(network, .8)
network = tflearn.fully_connected(network,2, activation='softmax')

return network

我想在训练结束时打印并保存每一层之后的特征向量形状和每一层的权重。我如何在 tflearn 中做到这一点？

【问题讨论】：

标签： python tflearn

【解决方案1】：

您可以使用以下方法获取层的权重和偏差值：

model.get_weights(layer_name.W)

model.get_weights(layer_name.b)

例如：

network1 = tflearn.layers.conv.conv_2d(input_batch, 32, 5, activation='relu')
network2 = tflearn.layers.conv.max_pool_2d(network1, 2,2)
network3 = tflearn.dropout(network2, .8)
// ...
// To get the weights and bias value of the convolutional layer i.e. network1
weight_network1 = model.get_weights(network1.W)
bias_network1 = model.get_weights(network1.b)

您可以查看此example 了解更多详情。

【讨论】：