基於TensorFlow的Cats vs. Dogs(貓狗大戰)實現和詳解(2)
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" ) as scope:
weights = tf.get_variable("weights",
shape=[3, 3, 3, 16],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
biases = tf.get_variable("biases" ,
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
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="conv1" )
# pool1 && norm1
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')
# conv2
with tf.variable_scope("conv2") as scope:
weights = tf.get_variable("weights",
shape=[3, 3, 16, 16],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
biases = tf.get_variable("biases",
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
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")
# pool2 && norm2
with tf.variable_scope("pooling2_lrn") as scope:
pool2 = tf.nn.max_pool(conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding="SAME", name="pooling2")
norm2 = tf.nn.lrn(pool2, depth_radius=4, bias=1.0, alpha=0.001/9.0,
beta=0.75, name='norm2')
# full-connect1
with tf.variable_scope("fc1") as scope:
reshape = tf.reshape(norm2, shape=[batch_size, -1])
dim = reshape.get_shape()[1].value
weights = tf.get_variable("weights",
shape=[dim, 128],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
biases = tf.get_variable("biases",
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name="fc1")
# full_connect2
with tf.variable_scope("fc2") as scope:
weights = tf.get_variable("weights",
shape=[128, 128],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
biases = tf.get_variable("biases",
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
fc2 = tf.nn.relu(tf.matmul(fc1, weights) + biases, name="fc2")
# softmax
with tf.variable_scope("softmax_linear") as scope:
weights = tf.get_variable("weights",
shape=[128, n_classes],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
biases = tf.get_variable("biases",
shape=[n_classes],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
softmax_linear = tf.add(tf.matmul(fc2, weights), biases, name="softmax_linear")
softmax_linear = tf.nn.softmax(softmax_linear)
return softmax_linear
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()