快捷導(dǎo)航

tensorflow 獲取變量&打印權(quán)值的實(shí)例講解

更新時(shí)間：2018年06月14日 09:11:12 作者：cassiePython

今天小編就為大家分享一篇tensorflow 獲取變量&打印權(quán)值的實(shí)例講解，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過來看看吧

在使用tensorflow中，我們常常需要獲取某個(gè)變量的值，比如：打印某一層的權(quán)重，通常我們可以直接利用變量的name屬性來獲取，但是當(dāng)我們利用一些第三方的庫來構(gòu)造神經(jīng)網(wǎng)絡(luò)的layer時(shí)，存在一種情況：就是我們自己無法定義該層的變量，因?yàn)槭亲詣?dòng)進(jìn)行定義的。

比如用tensorflow的slim庫時(shí)：

<span style="font-size:14px;">def resnet_stack(images, output_shape, hparams, scope=None):</span>
<span style="font-size:14px;"> """Create a resnet style transfer block.</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;"> Args:</span>
<span style="font-size:14px;"> images: [batch-size, height, width, channels] image tensor to feed as input</span>
<span style="font-size:14px;"> output_shape: output image shape in form [height, width, channels]</span>
<span style="font-size:14px;"> hparams: hparams objects</span>
<span style="font-size:14px;"> scope: Variable scope</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;"> Returns:</span>
<span style="font-size:14px;"> Images after processing with resnet blocks.</span>
<span style="font-size:14px;"> """</span>
<span style="font-size:14px;"> end_points = {}</span>
<span style="font-size:14px;"> if hparams.noise_channel:</span>
<span style="font-size:14px;"> # separate the noise for visualization</span>
<span style="font-size:14px;"> end_points['noise'] = images[:, :, :, -1]</span>
<span style="font-size:14px;"> assert images.shape.as_list()[1:3] == output_shape[0:2]</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;"> with tf.variable_scope(scope, 'resnet_style_transfer', [images]):</span>
<span style="font-size:14px;"> with slim.arg_scope(</span>
<span style="font-size:14px;">  [slim.conv2d],</span>
<span style="font-size:14px;">  normalizer_fn=slim.batch_norm,</span>
<span style="font-size:14px;">  kernel_size=[hparams.generator_kernel_size] * 2,</span>
<span style="font-size:14px;">  stride=1):</span>
<span style="font-size:14px;">  net = slim.conv2d(</span>
<span style="font-size:14px;">   images,</span>
<span style="font-size:14px;">   hparams.resnet_filters,</span>
<span style="font-size:14px;">   normalizer_fn=None,</span>
<span style="font-size:14px;">   activation_fn=tf.nn.relu)</span>
<span style="font-size:14px;">  for block in range(hparams.resnet_blocks):</span>
<span style="font-size:14px;">  net = resnet_block(net, hparams)</span>
<span style="font-size:14px;">  end_points['resnet_block_{}'.format(block)] = net</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;">  net = slim.conv2d(</span>
<span style="font-size:14px;">   net,</span>
<span style="font-size:14px;">   output_shape[-1],</span>
<span style="font-size:14px;">   kernel_size=[1, 1],</span>
<span style="font-size:14px;">   normalizer_fn=None,</span>
<span style="font-size:14px;">   activation_fn=tf.nn.tanh,</span>
<span style="font-size:14px;">   scope='conv_out')</span>
<span style="font-size:14px;">  end_points['transferred_images'] = net</span>
<span style="font-size:14px;"> return net, end_points</span>

我們希望獲取第一個(gè)卷積層的權(quán)重weight，該怎么辦呢？？

在訓(xùn)練時(shí)，這些可訓(xùn)練的變量會(huì)被tensorflow保存在 tf.trainable_variables() 中，于是我們就可以通過打印 tf.trainable_variables() 來獲取該卷積層的名稱（或者你也可以自己根據(jù)scope來看出來該變量的name ），然后利用tf.get_default_grap().get_tensor_by_name 來獲取該變量。

舉個(gè)簡(jiǎn)單的例子：

<span style="font-size:14px;">import tensorflow as tf</span>
<span style="font-size:14px;">with tf.variable_scope("generate"):</span>
<span style="font-size:14px;"> with tf.variable_scope("resnet_stack"):</span>
<span style="font-size:14px;">  #簡(jiǎn)單起見，這里沒有用第三方庫來說明，</span>
<span style="font-size:14px;">  bias = tf.Variable(0.0,name="bias")</span>
<span style="font-size:14px;">  weight = tf.Variable(0.0,name="weight")</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;">for tv in tf.trainable_variables():</span>
<span style="font-size:14px;"> print (tv.name)</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;">b = tf.get_default_graph().get_tensor_by_name("generate/resnet_stack/bias:0")</span>
<span style="font-size:14px;">w = tf.get_default_graph().get_tensor_by_name("generate/resnet_stack/weight:0")</span>
<span style="font-size:14px;"></span>
<span style="font-size:14px;">with tf.Session() as sess:</span>
<span style="font-size:14px;"> tf.global_variables_initializer().run()</span>
<span style="font-size:14px;"> print(sess.run(b))</span>
<span style="font-size:14px;"> print(sess.run(w))
</span>

結(jié)果如下：