您好,登錄后才能下訂單哦!
這篇文章將為大家詳細(xì)講解有關(guān)tensorflow如何獲取變量&打印權(quán)值,小編覺(jué)得挺實(shí)用的,因此分享給大家做個(gè)參考,希望大家閱讀完這篇文章后可以有所收獲。
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(lái)獲取,但是當(dāng)我們利用一些第三方的庫(kù)來(lái)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(wú)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(kù)時(shí):
<span >def resnet_stack(images, output_shape, hparams, scope=None):</span> <span > """Create a resnet style transfer block.</span> <span ></span> <span > Args:</span> <span > images: [batch-size, height, width, channels] image tensor to feed as input</span> <span > output_shape: output image shape in form [height, width, channels]</span> <span > hparams: hparams objects</span> <span > scope: Variable scope</span> <span ></span> <span > Returns:</span> <span > Images after processing with resnet blocks.</span> <span > """</span> <span > end_points = {}</span> <span > if hparams.noise_channel:</span> <span > # separate the noise for visualization</span> <span > end_points['noise'] = images[:, :, :, -1]</span> <span > assert images.shape.as_list()[1:3] == output_shape[0:2]</span> <span ></span> <span > with tf.variable_scope(scope, 'resnet_style_transfer', [images]):</span> <span > with slim.arg_scope(</span> <span > [slim.conv2d],</span> <span > normalizer_fn=slim.batch_norm,</span> <span > kernel_size=[hparams.generator_kernel_size] * 2,</span> <span > stride=1):</span> <span > net = slim.conv2d(</span> <span > images,</span> <span > hparams.resnet_filters,</span> <span > normalizer_fn=None,</span> <span > activation_fn=tf.nn.relu)</span> <span > for block in range(hparams.resnet_blocks):</span> <span > net = resnet_block(net, hparams)</span> <span > end_points['resnet_block_{}'.format(block)] = net</span> <span ></span> <span > net = slim.conv2d(</span> <span > net,</span> <span > output_shape[-1],</span> <span > kernel_size=[1, 1],</span> <span > normalizer_fn=None,</span> <span > activation_fn=tf.nn.tanh,</span> <span > scope='conv_out')</span> <span > end_points['transferred_images'] = net</span> <span > 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(guò)打印 tf.trainable_variables() 來(lái)獲取該卷積層的名稱(chēng)(或者你也可以自己根據(jù)scope來(lái)看出來(lái)該變量的name ),然后利用tf.get_default_grap().get_tensor_by_name 來(lái)獲取該變量。
舉個(gè)簡(jiǎn)單的例子:
<span >import tensorflow as tf</span> <span >with tf.variable_scope("generate"):</span> <span > with tf.variable_scope("resnet_stack"):</span> <span > #簡(jiǎn)單起見(jiàn),這里沒(méi)有用第三方庫(kù)來(lái)說(shuō)明,</span> <span > bias = tf.Variable(0.0,name="bias")</span> <span > weight = tf.Variable(0.0,name="weight")</span> <span ></span> <span >for tv in tf.trainable_variables():</span> <span > print (tv.name)</span> <span ></span> <span >b = tf.get_default_graph().get_tensor_by_name("generate/resnet_stack/bias:0")</span> <span >w = tf.get_default_graph().get_tensor_by_name("generate/resnet_stack/weight:0")</span> <span ></span> <span >with tf.Session() as sess:</span> <span > tf.global_variables_initializer().run()</span> <span > print(sess.run(b))</span> <span > print(sess.run(w)) </span>
結(jié)果如下:
關(guān)于“tensorflow如何獲取變量&打印權(quán)值”這篇文章就分享到這里了,希望以上內(nèi)容可以對(duì)大家有一定的幫助,使各位可以學(xué)到更多知識(shí),如果覺(jué)得文章不錯(cuò),請(qǐng)把它分享出去讓更多的人看到。
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀(guān)點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。