1. 首先了解下tensorflow的一些基礎語法知識

這里不再詳細說明其細節，只舉例學習。

1.1 tensorflow的tf.transpose()簡單使用：

tf.reshape(tensor, shape, name=None)
矩陣變形是常用的操作，在Tensorflow中調用方式有多種，例如：
1.tf.reshape

tf.reshape(L3, [-1, W4.get_shape().as_list()[0]])

2.object.reshape

mnist.test.images.reshape(-1, 28, 28, 1)

例子：

import tensorflow as tf #import numpy as np# tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9] # tensor 't' has shape [9] t1=[1, 2, 3, 4, 5, 6, 7, 8, 9] print('t:',t1) print(tf.reshape(t1, [3, 3]))with tf.Session() as sess:print(sess.run(tf.reshape(t1, [3, 3])))print('----------------------')# tensor 't' is [[[1, 1], [2, 2]], # [[3, 3], [4, 4]]] # tensor 't' has shape [2, 2, 2] t2=[[[1, 1], [2, 2]], [[3, 3], [4, 4]]] print('t:',t2) print(tf.reshape(t2, [2,4]))with tf.Session() as sess:print(sess.run(tf.reshape(t2, [2, 4])))print('----------------------')# tensor 't' is [[[1, 1, 1], # [2, 2, 2]], # [[3, 3, 3], # [4, 4, 4]], # [[5, 5, 5], # [6, 6, 6]]] # tensor 't' has shape [3, 2, 3] # pass '[-1]' to flatten 't' t3=[[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]], [[5, 5, 5], [6, 6, 6]]] print('t:',t3) print(tf.reshape(t3, [-1]))with tf.Session() as sess:print(sess.run(tf.reshape(t3, [-1])),'\n') # -1 can also be used to infer the shape # -1 is inferred to be 9: print(sess.run(tf.reshape(t3, [2,-1])),'\n')# -1 is inferred to be 2:print(sess.run(tf.reshape(t3, [-1,9])),'\n')# -1 is inferred to be 3:print(sess.run(tf.reshape(t3, [2,-1,3])),'\n')print(sess.run(tf.reshape(t3, [-1,3, 2, 3])))

運行結果：

t: [1, 2, 3, 4, 5, 6, 7, 8, 9] Tensor("Reshape_47:0", shape=(3, 3), dtype=int32) [[1 2 3][4 5 6][7 8 9]] ---------------------- t: [[[1, 1], [2, 2]], [[3, 3], [4, 4]]] Tensor("Reshape_49:0", shape=(2, 4), dtype=int32) [[1 1 2 2][3 3 4 4]] ---------------------- t: [[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]], [[5, 5, 5], [6, 6, 6]]] Tensor("Reshape_51:0", shape=(18,), dtype=int32) [1 1 1 2 2 2 3 3 3 4 4 4 5 5 5 6 6 6] [[1 1 1 2 2 2 3 3 3][4 4 4 5 5 5 6 6 6]] [[1 1 1 2 2 2 3 3 3][4 4 4 5 5 5 6 6 6]] [[[1 1 1][2 2 2][3 3 3]][[4 4 4][5 5 5][6 6 6]]] [[[[1 1 1][2 2 2]][[3 3 3][4 4 4]][[5 5 5][6 6 6]]]]

2. 模型訓練和保存實例

2.1 線性擬合

import tensorflow as tf import numpy as np# 訓練模型 def train_model():# 假造數據x_data = np.random.rand(100).astype(np.float32)print ('x_data:',x_data)y_data = x_data * 0.1 + 0.2print ('y_data:',y_data)# 定義權重W = tf.Variable(tf.random_uniform([1], -20.0, 20.0), dtype=tf.float32, name='w')b = tf.Variable(tf.random_uniform([1], -10.0, 10.0), dtype=tf.float32, name='b')# 計算線性輸出y = W * x_data + b# 定義損失函數loss = tf.reduce_mean(tf.square(y - y_data))train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)# 保存模型：這里的max_to_keep=4是最終會保存最新的4個模型saver = tf.train.Saver(max_to_keep=4)# 定義會話，訓練模型with tf.Session() as sess:sess.run(tf.global_variables_initializer())print ("------------------------------------------------------")print ("before the train, the W is %6f, the b is %6f" % (sess.run(W), sess.run(b)))for epoch in range(300):if epoch % 10 == 0:print ("------------------------------------------------------")print ("after epoch %d, the loss is %6f" % (epoch, sess.run(loss)))print ("the W is %f, the b is %f" % (sess.run(W), sess.run(b)))saver.save(sess, "model/my-model", global_step=epoch)print ("save the model")sess.run(train_step)print ("------------------------------------------------------")# 加載模型 def load_model():with tf.Session() as sess:# import_meta_graph填的名字meta文件的名字saver = tf.train.import_meta_graph('model/my-model-290.meta')# 檢查checkpoint，所以只填到checkpoint所在的路徑下即可，不需要填checkpointsaver.restore(sess, tf.train.latest_checkpoint("model"))# saver.restore(sess, tf.train.latest_checkpoint("model/checkpoint"))print (sess.run('w:0'))print (sess.run('b:0'))# 模型訓練 #train_model()# 模型加載 load_model()

結果：

INFO:tensorflow:Restoring parameters from model/my-model-290 [0.09999993] [0.20000005]

這里的運行結果省略了訓練的過程，其實應該先進行訓練，保存模型，然后進行模型的調用進行測試數據的測試，這里的數據是隨機生成的，所以準確率不必在意。

要注意的幾點：

• 創建saver時，可以指定需要存儲的tensor，如果沒有指定，則全部保存。
• 創建saver時，可以指定保存的模型個數，利用max_to_keep=4，則最終會保存4個模型
• saver.save()函數里面可以設定global_step，說明是哪一步保存的模型。
• 如果不想保存所有變量，可以在創建saver實例時，指定保存的變量，可以以list或者dict的類型保存。如：

w1 = tf.Variable(tf.random_normal(shape=[2]), name='w1') w2 = tf.Variable(tf.random_normal(shape=[5]), name='w2') saver = tf.train.Saver([w1,w2])

• 程序結束后，會生成四個文件，而每個文件包括三個類型的小文件：存儲網絡結構.meta、存儲訓練好的參數.data和.index、記錄最新的模型checkpoint。
• .meta文件：一個協議緩沖，保存tensorflow中完整的graph、variables、operation、collection。
• import_meta_graph導入的是meta文件的名字。然后restore時，是檢查checkpoint，所以只填到checkpoint所在的路徑下即可，不需要填checkpoint，不然會報錯“ValueError: Can’t load save_path when it is None.”。
• 最好在定義tensor的時候就指定名字，如上面代碼中的name='w'
• 如果想設置每多長時間保存一次，可以設置saver = tf.train.Saver(keep_checkpoint_every_n_hours=2)，這個是每2個小時保存一次。

2.2 簡單的卷積神經網絡

下面定義了一個簡單的卷積神經網絡：有兩個卷積層、兩個池化層和兩個全連接層。并且加載的數據是無意義的數據，模擬的是10張32x32的RGB圖像，共4個類別0、1、2、3。這里主要是為了學習模型的保存和調用，對于數據怎樣得來和準確率不用在意。

import tensorflow as tf import numpy as np import os# 自定義要加載的訓練集 def load_data(resultpath):datapath = os.path.join(resultpath, "data10_4.npz")# 如果有已經存在的數據，則加載if os.path.exists(datapath):data = np.load(datapath)# 注意提取數值的方法X, Y = data["X"], data["Y"]else:# 加載的數據是無意義的數據，模擬的是10張32x32的RGB圖像，共4個類別:0、1、2、3# 將30720個數字化成10*32*32*32*3的張量X = np.array(np.arange(30720)).reshape(10, 32, 32, 3)Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0]X = X.astype('float32')Y = np.array(Y)# 把數據保存成dataset.npz的格式np.savez(datapath, X=X, Y=Y)print('Saved dataset to dataset.npz')# 一種很好用的打印輸出顯示方式print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape))return X, Y# 搭建卷積網絡：有兩個卷積層、兩個池化層和兩個全連接層。 def define_model(x):x_image = tf.reshape(x, [-1, 32, 32, 3])print ('x_image.shape:',x_image.shape)def weight_variable(shape):initial = tf.truncated_normal(shape, stddev=0.1)return tf.Variable(initial, name="w")def bias_variable(shape):initial = tf.constant(0.1, shape=shape)return tf.Variable(initial, name="b")def conv3d(x, W):return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2d(x):return tf.nn.max_pool(x, ksize=[1, 3, 3, 1], strides=[1, 3, 3, 1], padding='SAME')with tf.variable_scope("conv1"): # [-1,32,32,3]weights = weight_variable([3, 3, 3, 32])biases = bias_variable([32])conv1 = tf.nn.relu(conv3d(x_image, weights) + biases)pool1 = max_pool_2d(conv1) # [-1,11,11,32]with tf.variable_scope("conv2"):weights = weight_variable([3, 3, 32, 64])biases = bias_variable([64])conv2 = tf.nn.relu(conv3d(pool1, weights) + biases)pool2 = max_pool_2d(conv2) # [-1,4,4,64]with tf.variable_scope("fc1"):weights = weight_variable([4 * 4 * 64, 128]) # [-1,1024]biases = bias_variable([128])fc1_flat = tf.reshape(pool2, [-1, 4 * 4 * 64])fc1 = tf.nn.relu(tf.matmul(fc1_flat, weights) + biases)fc1_drop = tf.nn.dropout(fc1, 0.5) # [-1,128]with tf.variable_scope("fc2"):weights = weight_variable([128, 4])biases = bias_variable([4])fc2 = tf.matmul(fc1_drop, weights) + biases # [-1,4]return fc2# 訓練模型 def train_model():# 訓練數據的占位符x = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name="x")y_ = tf.placeholder('int64', shape=[None], name="y_")# 學習率initial_learning_rate = 0.001# 定義網絡結構，前向傳播，得到預測輸出y_fc2 = define_model(x)# 定義訓練集的one-hot標簽y_label = tf.one_hot(y_, 4, name="y_labels")# 定義損失函數loss_temp = tf.losses.softmax_cross_entropy(onehot_labels=y_label, logits=y_fc2)cross_entropy_loss = tf.reduce_mean(loss_temp)# 訓練時的優化器train_step = tf.train.AdamOptimizer(learning_rate=initial_learning_rate, beta1=0.9, beta2=0.999,epsilon=1e-08).minimize(cross_entropy_loss)# 一樣返回True,否則返回Falsecorrect_prediction = tf.equal(tf.argmax(y_fc2, 1), tf.argmax(y_label, 1))# 將correct_prediction，轉換成指定tf.float32類型accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))# 保存模型，這里做多保存4個模型saver = tf.train.Saver(max_to_keep=4)# 把預測值加入predict集合tf.add_to_collection("predict", y_fc2)tf.add_to_collection("acc", accuracy )# 定義會話with tf.Session() as sess:# 所有變量初始化sess.run(tf.global_variables_initializer())print ("------------------------------------------------------")# 加載訓練數據，這里的訓練數據是構造的，旨在保存/加載模型的學習X, Y = load_data("model1/") # 這里需要提前新建一個文件夾X = np.multiply(X, 1.0 / 255.0)for epoch in range(200):if epoch % 10 == 0:print ("------------------------------------------------------")train_accuracy = accuracy.eval(feed_dict={x: X, y_: Y})train_loss = cross_entropy_loss.eval(feed_dict={x: X, y_: Y})print ("after epoch %d, the loss is %6f" % (epoch, train_loss))# 這里的正確率是以整體的訓練樣本為訓練樣例的print ("after epoch %d, the acc is %6f" % (epoch, train_accuracy))saver.save(sess, "model1/my-model", global_step=epoch)print ("save the model")train_step.run(feed_dict={x: X, y_: Y})print ("------------------------------------------------------")# 保存模型 def load_model():# 測試數據構造：模擬2張32x32的RGB圖X = np.array(np.arange(6144, 12288)).reshape(2, 32, 32, 3)Y = [3, 1]Y = np.array(Y)X = X.astype('float32')X = np.multiply(X, 1.0 / 255.0)with tf.Session() as sess:# 加載元圖和權重saver = tf.train.import_meta_graph('model1/my-model-190.meta')saver.restore(sess, tf.train.latest_checkpoint("model1/"))# 獲取權重graph = tf.get_default_graph()fc2_w = graph.get_tensor_by_name("fc2/w:0")fc2_b = graph.get_tensor_by_name("fc2/b:0")print ("------------------------------------------------------")print ('fc2_w:',sess.run(fc2_w))print ("#######################################")print ('fc2_b:',sess.run(fc2_b))print ("------------------------------------------------------")#input_x = graph.get_operation_by_name("x").outputs[0]# 預測輸出feed_dict = {"x:0":X, "y_:0":Y}y = graph.get_tensor_by_name("y_labels:0")yy = sess.run(y, feed_dict)print ('yy:',yy)print ("the answer is: ", sess.run(tf.argmax(yy, 1)))print ("------------------------------------------------------")pred_y = tf.get_collection("predict") print('i am here..1')pred = sess.run(pred_y, feed_dict)[0]print ('pred:',pred, '\n')pred = sess.run(tf.argmax(pred, 1))print ("the predict is: ", pred)print ("------------------------------------------------------")acc = tf.get_collection("acc")#acc = graph.get_operation_by_name("acc")acc = sess.run(acc, feed_dict)#print(acc.eval())print ("the accuracy is: ", acc)print ("------------------------------------------------------")# 訓練模型 train_model()# 加載模型 load_model()

注意上面按照順序應該是先訓練，訓練好以后再調用訓練好的模型進行測試。
單獨訓練結果：

x_image.shape: (?, 32, 32, 3) ------------------------------------------------------ X_shape:(10, 32, 32, 3) Y_shape:(10,) ------------------------------------------------------ after epoch 0, the loss is 37.972336 after epoch 0, the acc is 0.200000 save the model ------------------------------------------------------ after epoch 10, the loss is 55.470387 after epoch 10, the acc is 0.100000 save the model ------------------------------------------------------ after epoch 20, the loss is 17.129293 after epoch 20, the acc is 0.200000 save the model ------------------------------------------------------ after epoch 30, the loss is 15.748987 after epoch 30, the acc is 0.300000 save the model ------------------------------------------------------ after epoch 40, the loss is 4.500556 after epoch 40, the acc is 0.300000 save the model ------------------------------------------------------ after epoch 50, the loss is 2.675602 after epoch 50, the acc is 0.200000 save the model ------------------------------------------------------ after epoch 60, the loss is 2.377462 after epoch 60, the acc is 0.500000 save the model ------------------------------------------------------ after epoch 70, the loss is 1.419432 after epoch 70, the acc is 0.500000 save the model ------------------------------------------------------ ... ... ... after epoch 130, the loss is 1.356822 after epoch 130, the acc is 0.500000 save the model ------------------------------------------------------ after epoch 140, the loss is 1.361622 after epoch 140, the acc is 0.200000 save the model ------------------------------------------------------ after epoch 150, the loss is 1.204934 after epoch 150, the acc is 0.300000 save the model ------------------------------------------------------ after epoch 160, the loss is 1.273999 after epoch 160, the acc is 0.300000 save the model ------------------------------------------------------ after epoch 170, the loss is 1.213519 after epoch 170, the acc is 0.400000 save the model ------------------------------------------------------ after epoch 180, the loss is 1.276478 after epoch 180, the acc is 0.300000 save the model ------------------------------------------------------ after epoch 190, the loss is 1.162433 after epoch 190, the acc is 0.300000 save the model ------------------------------------------------------

單獨測試結果：

INFO:tensorflow:Restoring parameters from model1/my-model-190 ------------------------------------------------------ fc2_w: [[ 0.09413899 -0.07282051 0.02397597 0.05508222][-0.05514605 -0.03894351 -0.0548727 -0.02125386][ 0.06236398 -0.00028329 0.13300249 0.06448492][-0.0921673 0.00342558 0.10539673 -0.02442357][-0.04699677 0.11520271 -0.04514726 -0.13220425].........[ 0.08583067 -0.06123111 0.10699942 0.03429044][-0.05737718 0.0714161 -0.04370898 -0.0397063 ][ 0.00849419 -0.04352335 0.01004444 0.03862172]] ####################################### fc2_b: [0.12246324 0.11658503 0.10220832 0.06499074] ------------------------------------------------------ yy: [[0. 0. 0. 1.][0. 1. 0. 0.]] the answer is: [3 1] ------------------------------------------------------ i am here..1 pred: [[ 0.6232525 0.18511544 0.08325944 -0.4809047 ][ 0.12246324 0.11658503 0.10220832 0.06499074]] the predict is: [0 0] ------------------------------------------------------ the accuracy is: [0.0, 0.0] ------------------------------------------------------

2.3 加載滑動平均模型和變量重命名

在使用梯度下降算法訓練模型時，每次更新權重時，為每個權重維護一個影子變量，該影子變量隨著訓練的進行，會最終穩定在一個接近真實權重的值的附近。那么，在進行預測的時候，使用影子變量的值替代真實變量的值，可以得到更好的結果。 滑動平均模型在梯段下降算法上才會有好的結果，別的優化算法沒有這個現象，還沒有合理的解釋。而優化的方法有很多，這個可以作為提高健壯性的有效措施。

# 執行時要注意IDE的當前工作過路徑，最好每段重啟控制器一次，輸出結果更準確# Part1: 通過tf.train.Saver類實現保存和載入神經網絡模型# 執行本段程序時注意當前的工作路徑 import tensorflow as tfv1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2") result = v1 + v2saver = tf.train.Saver()with tf.Session() as sess:sess.run(tf.global_variables_initializer())saver.save(sess, "Model/model.ckpt")# Part3: 若不希望重復定義計算圖上的運算，可直接加載已經持久化的圖import tensorflow as tfsaver = tf.train.import_meta_graph("Model/model.ckpt.meta") graph=tf.get_default_graph() with tf.Session() as sess:saver.restore(sess, "./Model/model.ckpt") # 注意路徑寫法print(sess.run(graph.get_tensor_by_name("add:0"))) # [ 3.]# Part4： tf.train.Saver類也支持在保存和加載時給變量重命名import tensorflow as tf# 聲明的變量名稱name與已保存的模型中的變量名稱name不一致 u1 = tf.Variable(tf.constant(1.0, shape=[1]), name="other-v1") u2 = tf.Variable(tf.constant(2.0, shape=[1]), name="other-v2") result = u1 + u2# 若直接生命Saver類對象，會報錯變量找不到 # 使用一個字典dict重命名變量即可，{"已保存的變量的名稱name": 重命名變量名} # 原來名稱name為v1的變量現在加載到變量u1（名稱name為other-v1）中 saver = tf.train.Saver({"v1": u1, "v2": u2})with tf.Session() as sess:saver.restore(sess, "./Model/model.ckpt")print(sess.run(result)) # [ 3.]#INFO:tensorflow:Restoring parameters from ./Model/model.ckpt #[3.] #INFO:tensorflow:Restoring parameters from ./Model/model.ckpt #[3.]# Part5: 保存滑動平均模型import tensorflow as tfv = tf.Variable(0, dtype=tf.float32, name="v")for variables in tf.global_variables():print(variables.name) # v:0print('...........') ema = tf.train.ExponentialMovingAverage(0.99) maintain_averages_op = ema.apply(tf.global_variables()) for variables in tf.global_variables():print(variables.name) # v:0# v/ExponentialMovingAverage:0saver = tf.train.Saver()with tf.Session() as sess:sess.run(tf.global_variables_initializer())sess.run(tf.assign(v, 10))sess.run(maintain_averages_op)saver.save(sess, "Model/model_ema.ckpt")print('here..1:',sess.run([v, ema.average(v)])) # [10.0, 0.099999905]#v:0 #........... #v:0 #v/ExponentialMovingAverage:0 #here..1: [10.0, 0.099999905]# Part6: 通過變量重命名直接讀取變量的滑動平均值import tensorflow as tfv = tf.Variable(0, dtype=tf.float32, name="v") # {"已保存的變量的名稱name": 重命名變量名} saver = tf.train.Saver({"v/ExponentialMovingAverage": v}) with tf.Session() as sess:saver.restore(sess, "./Model/model_ema.ckpt")print('here..2:',sess.run(v)) # 0.0999999# INFO:tensorflow:Restoring parameters from ./Model/model_ema.ckpt # here..2: 0.099999905# Part7: 通過tf.train.ExponentialMovingAverage的variables_to_restore()函數獲取變量重命名字典import tensorflow as tfv = tf.Variable(0, dtype=tf.float32, name="v") # 注意此處的變量名稱name一定要與已保存的變量名稱一致 ema = tf.train.ExponentialMovingAverage(0.99) print(ema.variables_to_restore()) # {'v/ExponentialMovingAverage': <tf.Variable 'v:0' shape=() dtype=float32_ref>} # 此處的v取自上面變量v的名稱name="v"saver = tf.train.Saver(ema.variables_to_restore())with tf.Session() as sess:saver.restore(sess, "./Model/model_ema.ckpt")print(sess.run(v)) # 0.0999999#{'v/ExponentialMovingAverage': <tf.Variable 'v:0' shape=() dtype=float32_ref>} #INFO:tensorflow:Restoring parameters from ./Model/model_ema.ckpt #0.099999905# Part8: 通過convert_variables_to_constants函數將計算圖中的變量及其取值通過常量的方式保存于一個文件中import tensorflow as tf from tensorflow.python.framework import graph_utilv1 = tf.Variable(tf.constant(1.0, shape=[1]), name="v1") v2 = tf.Variable(tf.constant(2.0, shape=[1]), name="v2") result = v1 + v2with tf.Session() as sess:sess.run(tf.global_variables_initializer())# 導出當前計算圖的GraphDef部分，即從輸入層到輸出層的計算過程部分graph_def = tf.get_default_graph().as_graph_def()output_graph_def = graph_util.convert_variables_to_constants(sess,graph_def, ['add'])with tf.gfile.GFile("Model/combined_model.pb", 'wb') as f:f.write(output_graph_def.SerializeToString())#INFO:tensorflow:Froze 2 variables. #INFO:tensorflow:Converted 2 variables to const ops.# Part9: 載入包含變量及其取值的模型import tensorflow as tf from tensorflow.python.platform import gfilewith tf.Session() as sess:model_filename = "Model/combined_model.pb"with gfile.FastGFile(model_filename, 'rb') as f:graph_def = tf.GraphDef()graph_def.ParseFromString(f.read())result = tf.import_graph_def(graph_def, return_elements=["add:0"])print(sess.run(result)) #[array([3.], dtype=float32)]

tf.train.Saver類也支持在保存和加載時給變量重命名，聲明Saver類對象的時候使用一個字典dict重命名變量即可，{"已保存的變量的名稱name": 重命名變量名}，saver = tf.train.Saver({"v1":u1, "v2": u2})即原來名稱name為v1的變量現在加載到變量u1（名稱name為other-v1）中。

這樣就是為了方便使用變量的滑動平均值。如果在加載模型時直接將影子變量映射到變量自身，則在使用訓練好的模型時就不需要再調用函數來獲取變量的滑動平均值了。載入時，聲明Saver類對象時通過一個字典將滑動平均值直接加載到新的變量中，saver = tf.train.Saver({"v/ExponentialMovingAverage": v})，另通過tf.train.ExponentialMovingAverage的variables_to_restore()函數獲取變量重命名字典。

2.4 fine-tuning

使用已經預訓練好的模型，自己fine-tuning。

• 首先獲得pre-traing的graph結構，saver = tf.train.import_meta_graph('my_test_model-1000.meta')
• 加載參數，saver.restore(sess,tf.train.latest_checkpoint('./'))
• 準備feed_dict，新的訓練數據或者測試數據。這樣就可以使用同樣的模型，訓練或者測試不同的數據。
• 如果想在已有的網絡結構上添加新的層，如前面卷積網絡，獲得fc2時，然后添加了一個全連接層和輸出層。(這里的添加網絡層沒有進行測試)

# pre-train and fine-tuning fc2 = graph.get_tensor_by_name("fc2/add:0") fc2 = tf.stop_gradient(fc2) # stop the gradient compute fc2_shape = fc2.get_shape().as_list() # fine -tuning new_nums = 6 weights = tf.Variable(tf.truncated_normal([fc2_shape[1], new_nums], stddev=0.1), name="w") biases = tf.Variable(tf.constant(0.1, shape=[new_nums]), name="b") conv2 = tf.matmul(fc2, weights) + biases output2 = tf.nn.softmax(conv2)

參考：
https://blog.csdn.net/liuxiao214/article/details/79048136
https://blog.csdn.net/marsjhao/article/details/72829635
https://blog.csdn.net/qq_36330643/article/details/77323554

總結

以上是生活随笔為你收集整理的tensorflow加载训练好的模型实例的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。