tf.trainable_variables()提取訓練參數
具體實例
tf.trainable_variables()提取訓練參數在tf中，參與訓練的參數可用 tf.trainable_variables()提取出來，如：
#取出所有參與訓練的參數params=tf.trainable_variables()print("Trainable variables:------------------------")#循環列出參數for idx, v in enumerate(params): print(" param {:3}: {:15} {}".format(idx, str(v.get_shape()), v.name))這裡只能查看參數的shape和name,並沒有具體的值。如果要查看參數具體的值的話，必須先初始化，即：
sess=tf.Session()sess.run(tf.global_variables_initializer())同理，我們也可以提取圖片經過訓練後的值。圖片經過卷積後變成了特征，要提取這些特征，必須先把圖片feed進去。
具體實例# -*- coding: utf-8 -*-"""Created on Sat Jun 3 12:07:59 [email protected]: Administrator"""import tensorflow as tffrom skimage import io,transformimport numpy as np#-----------------構建網絡----------------------#占位符x=tf.placeholder(tf.float32,shape=[None,100,100,3],name='x')y_=tf.placeholder(tf.int32,shape=[None,],name='y_')#第一個卷積層（100——>50)conv1=tf.layers.conv2d( inputs=x, filters=32, kernel_size=[5, 5], padding="same", activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01))pool1=tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)#第二個卷積層(50->25)conv2=tf.layers.conv2d( inputs=pool1, filters=64, kernel_size=[5, 5], padding="same", activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01))pool2=tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)#第三個卷積層(25->12)conv3=tf.layers.conv2d( inputs=pool2, filters=128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01))pool3=tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=2)#第四個卷積層(12->6)conv4=tf.layers.conv2d( inputs=pool3, filters=128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01))pool4=tf.layers.max_pooling2d(inputs=conv4, pool_size=[2, 2], strides=2)re1 = tf.reshape(pool4, [-1, 6 * 6 * 128])#全連接層dense1 = tf.layers.dense(inputs=re1, units=1024, activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01), kernel_regularizer=tf.nn.l2_loss)dense2= tf.layers.dense(inputs=dense1, units=512, activation=tf.nn.relu, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01), kernel_regularizer=tf.nn.l2_loss)logits= tf.layers.dense(inputs=dense2, units=5, activation=None, kernel_initializer=tf.truncated_normal_initializer(stddev=0.01), kernel_regularizer=tf.nn.l2_loss)#---------------------------網絡結束---------------------------#%%#取出所有參與訓練的參數params=tf.trainable_variables()print("Trainable variables:------------------------")#循環列出參數for idx, v in enumerate(params): print(" param {:3}: {:15} {}".format(idx, str(v.get_shape()), v.name))#%%#讀取圖片img=io.imread('d:/cat.jpg')#resize成100*100img=transform.resize(img,(100,100))#三維變四維（100，100，3）-->(1,100,100,3)img=img[np.newaxis,:,:,:]img=np.asarray(img,np.float32)sess=tf.Session()sess.run(tf.global_variables_initializer()) #提取最後一個全連接層的參數 W和bW=sess.run(params[26])b=sess.run(params[27])#提取第二個全連接層的輸出值作為特征 fea=sess.run(dense2,feed_dict={x:img})最後一條語句就是提取某層的數據輸出作為特征。
注意：這個程序並沒有經過訓練，因此提取出的參數只是初始化的參數。
以上就是python深度學習tensorflow1.0參數和特征提取的詳細內容，更多關於python tensorflow參數特征提取的資料請關注軟件開發網其它相關文章！
