如何获得层上神经元的值？巨蟒
如何获得层上神经元的值？巨蟒
提问于 2016-06-20 15:51:54
我用诺尔学习图书馆建立了神经网络。
net = NeuralNet(
layers=[
('input', layers.InputLayer),
('conv1', layers.Conv2DLayer),
('pool1', layers.MaxPool2DLayer),
('dropout1', layers.DropoutLayer),
('conv2', layers.Conv2DLayer),
('pool2', layers.MaxPool2DLayer),
('dropout2', layers.DropoutLayer),
('conv3', layers.Conv2DLayer),
('pool3', layers.MaxPool2DLayer),
('dropout3', layers.DropoutLayer),
('hidden4', layers.DenseLayer),
('output', layers.DenseLayer),
],
input_shape=(None, 1, imgSize, imgSize),
conv1_num_filters=32, conv1_filter_size=(param1, param1), pool1_pool_size=(2, 2),
dropout1_p=0.4,
conv2_num_filters=64, conv2_filter_size=(param2, param2), pool2_pool_size=(2, 2),
dropout2_p=0.4,
conv3_num_filters=128, conv3_filter_size=(param3, param3), pool3_pool_size=(2, 2),
dropout3_p=0.4,
hidden4_num_units=1000,
output_num_units=classNum, output_nonlinearity=lasagne.nonlinearities.softmax,
update_learning_rate=0.01,
update_momentum=0.9,
regression=False,
max_epochs=100,
verbose=1,
)
net.fit(trainD, trainL)如何才能得到某些x上隐层神经元的值？我不习惯得到这些值，并在其他一些算法中使用它们来获得更好的结果。
回答 1
Stack Overflow用户
回答已采纳
发布于 2016-06-23 11:24:03
所以我找到了解决办法。
hidden_layer = layers.get_output(net.layers_['hidden4'], deterministic=True)
input_var = net.layers_['input'].input_var
f_hidden = theano.function([input_var], hidden_layer)
instance = TestD[i][None, :, :, :]
pred = f_hidden(instance)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/37926768
复制相关文章
相似问题
腾讯云开发者
