檔案training.py

匯入檔案

import os
import numpy as np
import tensorflow as tf
import input_data
import model

變數宣告

N_CLASSES = 2 #貓和狗
IMG_W = 208  # resize影象，太大的話訓練時間久
IMG_H = 208
BATCH_SIZE = 16
CAPACITY = 2000
MAX_STEP = 10000 # 一般大於10K
learning_rate = 0.0001 # 一般小於0.0001

獲取批次batch

train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
 

logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/'

train, train_label = input_data.get_files(train_dir)
train_batch,train_label_batch=input_data.get_batch(train,
                                train_label,
                                IMG_W,
                                IMG_H,
                                BATCH_SIZE, 
                                CAPACITY)      
 

操作定義

train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, train_label_batch)        
train_op = model.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all() #這個是log彙總記錄
 


#產生一個會話
sess = tf.Session()  
#產生一個writer來寫log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 % 50 == 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2000步，儲存一次訓練好的模型
        if step % 2000 == 0 or (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()