基於TensorFlow的Cats vs. Dogs（貓狗大戰）實現和詳解（2）
阿新 • • 發佈：2019-01-06
2. 卷積神經網路模型的構造——model.py
關於神經網路模型不想說太多，視訊中使用的模型是仿照TensorFlow的官方例程cifar-10的網路結構來寫的。就是兩個卷積層（每個卷積層後加一個池化層），兩個全連線層，最後一個softmax輸出分類結果。
import tensorflow as tf
def inference(images, batch_size, n_classes):
# conv1, shape = [kernel_size, kernel_size, channels, kernel_numbers]
with tf.variable_scope("conv1" 發現程式裡面有很多with tf.variable_scope("name")的語句，這其實是TensorFlow中的變數作用域機制，目的是有效便捷地管理需要的變數。
變數作用域機制在TensorFlow中主要由兩部分組成：
tf.get_variable(<name>, <shape>, <initializer>): 建立一個變數tf.variable_scope(<scope_name>): 指定名稱空間
如果需要共享變數，需要通過reuse_variables()方法來指定，詳細的例子去官方文件中看就好了。（連結在部落格參考部分）
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
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
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 函式losses(logits, labels)用於計算訓練過程中的loss，這裡輸入引數logtis是函式inference()的輸出，代表圖片對貓和狗的預測概率，labels則是圖片對應的標籤。
通過在程式中設定斷點，檢視logtis的值，結果如下圖所示，根據這個就很好理解了，一個數值代表屬於貓的概率，一個數值代表屬於狗的概率，兩者的和為1。
而函式tf.nn.sparse_sotfmax_cross_entropy_with_logtis從名字就很好理解，是將稀疏表示的label與輸出層計算出來結果做對比。然後因為訓練的時候是16張圖片一個batch，所以再用tf.reduce_mean求一下平均值，就得到了這個batch的平均loss。
training(loss, learning_rate)就沒什麼好說的了，loss是訓練的loss，learning_rate是學習率，使用AdamOptimizer優化器來使loss朝著變小的方向優化。
evaluation(logits, labels)功能是在訓練過程中實時監測驗證資料的準確率，達到反映訓練效果的作用。
參考
補充
本來是自己之前犯懶，最後一篇關於訓練的部落格沒寫=0=，鑑於不少人想要訓練程式碼，這裡我就從簡貼一下程式碼好了，大夥將就著看看，最近自己的事比較多，不想再把最開始的程式碼拿來翻了（剛開始寫的太醜了）。
import os
import numpy as np
import tensorflow as tf
import input_data
import model
N_CLASSES = 2
IMG_H = 208
IMG_W = 208
BATCH_SIZE = 32
CAPACITY = 2000
MAX_STEP = 15000
learning_rate = 0.0001
def run_training():
train_dir = "data\\train\\"
logs_train_dir = "logs\\"
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)
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()
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
if step % 100 == 0:
print("Step %d, train loss = %.2f, train accuracy = %.2f%%" % (step, tra_loss, tra_acc))
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
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()
coord.join(threads)
sess.close()
# 評估模型
from PIL import Image
import matplotlib.pyplot as plt
def get_one_image(train):
n = len(train)
ind = np.random.randint(0, n)
img_dir = train[ind]
image = Image.open(img_dir)
plt.imshow(image)
plt.show()
image = image.resize([208, 208])
image = np.array(image)
return image
def evaluate_one_image():
train_dir = "C:\\Users\\panch\\Documents\\PycharmProjects\\Cats_vs_Dogs\\data\\train\\"
train, train_label = input_data.get_files(train_dir)
image_array = get_one_image(train)
with tf.Graph().as_default():
BATCH_SIZE = 1
N_CLASSES = 2
image = tf.cast(image_array, tf.float32)
image = tf.reshape(image, [1, 208, 208, 3])
logit = model.inference(image, BATCH_SIZE, N_CLASSES)
logit = tf.nn.softmax(logit)
x = tf.placeholder(tf.float32, shape=[208, 208, 3])
logs_train_dir = "C:\\Users\\panch\\Documents\\PycharmProjects\\Cats_vs_Dogs\\logs\\"
saver = tf.train.Saver()
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(logs_train_dir)
if ckpt and ckpt.model_checkpoint_path:
global_step = ckpt.model_checkpoint_path.split("/")[-1].split("-")[-1]
saver.restore(sess, ckpt.model_checkpoint_path)
print("Loading success, global_step is %s" % global_step)
else:
print("No checkpoint file found")
prediction = sess.run(logit, feed_dict={x: image_array})
max_index = np.argmax(prediction)
if max_index == 0:
print("This is a cat with possibility %.6f" % prediction[:, 0])
else:
print("This is a dog with possibility %.6f" % prediction[:, 1])
run_training()
# evaluate_one_image()