搭建簡單圖片分類的卷積神經網路(二)-- CNN模型與訓練
阿新 • • 發佈:2018-11-19
一、首先,簡單來說CNN卷積神經網路與BP神經網路主要區別在於:
1、網路的層數的多少(我這裡的CNN是比較簡單的,層數較少,真正應用的話,層數是很多的)。
2、CNN名稱來說,具有卷積運算的特點,對於大型的圖片或者數量多的圖片,卷積運算可以大量提高計算效能,而BP神經網路大都為全連線層,計算量本身就大,輸入大量的圖片,效能就不好了。
二、新建CNN檔案
import tensorflow as tf def inference(images, batch_size, n_classes): # 一個簡單的卷積神經網路,卷積+池化層x2,全連線層x2,最後一個softmax層做分類。 # 卷積層1 # 64個3x3的卷積核(3通道),padding=’SAME’,表示padding後卷積的圖與原圖尺寸一致,啟用函式relu() with tf.variable_scope('conv1') as scope: weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 3, 64], stddev=1.0, dtype=tf.float32), name='weights', dtype=tf.float32) biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[64]), name='biases', dtype=tf.float32) conv = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv1 = tf.nn.relu(pre_activation, name=scope.name) # 池化層1 # 3x3最大池化,步長strides為2,池化後執行lrn()操作,區域性響應歸一化,對訓練有利。 with tf.variable_scope('pooling1_lrn') as scope: pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling1') norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm1') # 卷積層2 # 16個3x3的卷積核(16通道),padding=’SAME’,表示padding後卷積的圖與原圖尺寸一致,啟用函式relu() with tf.variable_scope('conv2') as scope: weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 64, 16], stddev=0.1, dtype=tf.float32), name='weights', dtype=tf.float32) biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[16]), name='biases', dtype=tf.float32) conv = tf.nn.conv2d(norm1, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv2 = tf.nn.relu(pre_activation, name='conv2') # 池化層2 # 3x3最大池化,步長strides為2,池化後執行lrn()操作, # pool2 and norm2 with tf.variable_scope('pooling2_lrn') as scope: norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm2') pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME', name='pooling2') # 全連線層3 # 128個神經元,將之前pool層的輸出reshape成一行,啟用函式relu() with tf.variable_scope('local3') as scope: reshape = tf.reshape(pool2, shape=[batch_size, -1]) dim = reshape.get_shape()[1].value weights = tf.Variable(tf.truncated_normal(shape=[dim, 128], stddev=0.005, dtype=tf.float32), name='weights', dtype=tf.float32) biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]), name='biases', dtype=tf.float32) local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name) # 全連線層4 # 128個神經元,啟用函式relu() with tf.variable_scope('local4') as scope: weights = tf.Variable(tf.truncated_normal(shape=[128, 128], stddev=0.005, dtype=tf.float32), name='weights', dtype=tf.float32) biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]), name='biases', dtype=tf.float32) local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4') # dropout層 # with tf.variable_scope('dropout') as scope: # drop_out = tf.nn.dropout(local4, 0.8) # Softmax迴歸層 # 將前面的FC層輸出,做一個線性迴歸,計算出每一類的得分,在這裡是2類,所以這個層輸出的是兩個得分。 with tf.variable_scope('softmax_linear') as scope: weights = tf.Variable(tf.truncated_normal(shape=[128, n_classes], stddev=0.005, dtype=tf.float32), name='softmax_linear', dtype=tf.float32) biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[n_classes]), name='biases', dtype=tf.float32) softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear') return softmax_linear #loss計算 #傳入引數:logits,網路計算輸出值。labels,真實值,在這裡是0或者1 #返回引數:loss,損失值 def losses(logits, labels): with tf.variable_scope('loss') as scope: cross_entropy =tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='xentropy_per_example') loss = tf.reduce_mean(cross_entropy, name='loss') tf.summary.scalar(scope.name+'/loss', loss) return loss # loss損失值優化 # 輸入引數:loss。learning_rate,學習速率。 # 返回引數:train_op,訓練op,這個引數要輸入sess.run中讓模型去訓練。 def trainning(loss, learning_rate): with tf.name_scope('optimizer'): optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) global_step = tf.Variable(0, name='global_step', trainable=False) train_op = optimizer.minimize(loss, global_step=global_step) return train_op # 評價/準確率計算 # 輸入引數:logits,網路計算值。labels,標籤,也就是真實值,在這裡是0或者1。 # 返回引數:accuracy,當前step的平均準確率,也就是在這些batch中多少張圖片被正確分類了。 def evaluation(logits, labels): with tf.variable_scope('accuracy') as scope: correct = tf.nn.in_top_k(logits, labels, 1) correct = tf.cast(correct, tf.float16) accuracy = tf.reduce_mean(correct) tf.summary.scalar(scope.name + '/accuracy', accuracy) return accuracy
這裡的網路為2個卷積層,2個池化層,2個全連線層,最後通過softmax層輸出。
三、新建TestCnn檔案
import os import numpy as np import tensorflow as tf import CNN import GetCnnData #變數宣告 N_CLASSES = 0 #類別 IMG_W = 64 # resize影象,太大的話訓練時間久 IMG_H = 64 BATCH_SIZE =20 CAPACITY = 200 MAX_STEP = 2000 # 一般大於10K learning_rate = 0.0001 # 一般小於0.0001 train_dir = r'E:\PycharmPython\NewCnn\train\train_data' #訓練樣本的讀入 logs_train_dir = r'E:\PycharmPython\NewCnn\logs' #logs儲存路徑 #計算分類類別 for str in os.listdir(train_dir): N_CLASSES = N_CLASSES+1 train,trian_label,val,val_label = GetCnnData.get_files(train_dir,0.3) #訓練資料以及標籤 train_batch,train_label_batch = GetCnnData.get_batch(train,trian_label,IMG_W,IMG_H,BATCH_SIZE,CAPACITY) #測試資料以及標籤 val_batch,val_label_batch = GetCnnData.get_batch(val,val_label,IMG_W,IMG_H,BATCH_SIZE,CAPACITY) #訓練操作定義 train_logits = CNN.inference(train_batch,BATCH_SIZE,N_CLASSES) train_loss = CNN.losses(train_logits, train_label_batch) train_op = CNN.trainning(train_loss, learning_rate) train_acc = CNN.evaluation(train_logits, train_label_batch) #測試操作定義 test_logits = CNN.inference(val_batch, BATCH_SIZE, N_CLASSES) test_loss = CNN.losses(test_logits, val_label_batch) test_acc = CNN.evaluation(test_logits, val_label_batch) #LOGS summary_op = tf.summary.merge_all() #定義一個會話 sess = tf.Session() #寫logs檔案 train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) #產生一個saver來儲存訓練好的模型 saver = tf.train.Saver() #所有節點初始化 sess.run(tf.global_variables_initializer()) #佇列監控 coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) # 進行batch的訓練 try: # 執行MAX_STEP步的訓練,一步一個batch for step in np.arange(MAX_STEP): if coord.should_stop(): break # 啟動以下操作節點,有個疑問,為什麼train_logits在這裡沒有開啟? _, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc]) # 每隔50步列印一次當前的loss以及acc,同時記錄log,寫入writer if step % 10 == 0: print('Step %d, train loss = %.2f, train accuracy = %.2f%%' % (step, tra_loss, tra_acc * 100.0)) summary_str = sess.run(summary_op) train_writer.add_summary(summary_str, step) # 每隔100步,儲存一次訓練好的模型 if (step + 1) == MAX_STEP: checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt') saver.save(sess, checkpoint_path, global_step=step) except tf.errors.OutOfRangeError: print('Done training -- epoch limit reached') finally: coord.request_stop()
這裡是對模型的訓練和模型的儲存。
連載:https://blog.csdn.net/qq_28821995/article/details/83587032 https://blog.csdn.net/qq_28821995/article/details/83587802
參考:https://blog.csdn.net/ywx1832990/article/details/78610711