遷移學習與retrain.py是一樣的
這是TensorFlow 實戰(zhàn)Google深度學習框架 ,鄭澤宇書上的代碼：其也是改編了retrain.py的代碼
這里和retrain.py是一樣的恍风，因為pb文件的參數無法繼續(xù)進行訓練了蹦狂，所以取出pb文件模型圖里的頭和尾（頭是'DecodeJpeg/contents:0'，把圖片編碼成二進制文件朋贬，在model里面會進行剪裁凯楔，此尾是sofmax前面某一conv層，pool_3/_reshape:0）锦募，把圖片輸入inception_model后生成一個特征摆屯，作為新模型的輸入，這里BOTTLENECK_TENSOR_SIZE = 2048說明pool_3/_reshape:0之后特征的shape為2048糠亩，新模型的輸出為n_classes虐骑，與你的具體任務有關，這flower有四類赎线，所以為n_classes = 4廷没，這里 n_classes = len(image_lists.keys())，看你在flower_potos文件夾建立幾個子個文件夾垂寥，flower_potos官方的文件有這四類
開始上代碼
import glob
import os.path
import random
import numpy as np
import tensorflow as tf
from tensorflow.python.platform import gfile
# #### 1. 模型和樣本路徑的設置
# In[2]:
BOTTLENECK_TENSOR_SIZE = 2048
BOTTLENECK_TENSOR_NAME = 'pool_3/_reshape:0'
JPEG_DATA_TENSOR_NAME = 'DecodeJpeg/contents:0'
MODEL_DIR = 'inception_model'
MODEL_FILE= 'classify_image_graph_def.pb'
CACHE_DIR = 'bottleneck'
INPUT_DATA = 'flower_photos'
VALIDATION_PERCENTAGE = 10
TEST_PERCENTAGE = 10
# #### 2. 神經網絡參數的設置
# In[3]:
LEARNING_RATE = 0.01
STEPS = 4000
BATCH = 100
# #### 3. 把樣本中所有的圖片列表并按訓練颠黎、驗證、測試數據分開
# In[4]:
def create_image_lists(testing_percentage, validation_percentage):
result = {}
sub_dirs = [x[0] for x in os.walk(INPUT_DATA)]
is_root_dir = True
for sub_dir in sub_dirs:
if is_root_dir:
is_root_dir = False
continue
extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']
file_list = []
dir_name = os.path.basename(sub_dir)
for extension in extensions:
file_glob = os.path.join(INPUT_DATA, dir_name, '*.' + extension)
file_list.extend(glob.glob(file_glob))
if not file_list: continue
label_name = dir_name.lower()
# 初始化
training_images = []
testing_images = []
validation_images = []
for file_name in file_list:
base_name = os.path.basename(file_name)
# 隨機劃分數據
chance = np.random.randint(100)
if chance < validation_percentage:
validation_images.append(base_name)
elif chance < (testing_percentage + validation_percentage):
testing_images.append(base_name)
else:
training_images.append(base_name)
result[label_name] = {
'dir': dir_name,
'training': training_images,
'testing': testing_images,
'validation': validation_images,
}
return result
# #### 4. 定義函數通過類別名稱矫废、所屬數據集和圖片編號獲取一張圖片的地址盏缤。
# In[5]:
def get_image_path(image_lists, image_dir, label_name, index, category):
label_lists = image_lists[label_name]
category_list = label_lists[category]
mod_index = index % len(category_list)
base_name = category_list[mod_index]
sub_dir = label_lists['dir']
full_path = os.path.join(image_dir, sub_dir, base_name)
return full_path
# #### 5. 定義函數獲取Inception-v3模型處理之后的特征向量的文件地址。
# In[6]:
def get_bottleneck_path(image_lists, label_name, index, category):
return get_image_path(image_lists, CACHE_DIR, label_name, index, category) + '.txt'
# #### 6. 定義函數使用加載的訓練好的Inception-v3模型處理一張圖片蓖扑，得到這個圖片的特征向量唉铜。
# In[7]:
def run_bottleneck_on_image(sess, image_data, image_data_tensor, bottleneck_tensor):
bottleneck_values = sess.run(bottleneck_tensor, {image_data_tensor: image_data})
bottleneck_values = np.squeeze(bottleneck_values)
return bottleneck_values
# #### 7. 定義函數會先試圖尋找已經計算且保存下來的特征向量，如果找不到則先計算這個特征向量律杠，然后保存到文件潭流。
# In[8]:
def get_or_create_bottleneck(sess, image_lists, label_name, index, category, jpeg_data_tensor, bottleneck_tensor):
label_lists = image_lists[label_name]
sub_dir = label_lists['dir']
sub_dir_path = os.path.join(CACHE_DIR, sub_dir)
if not os.path.exists(sub_dir_path): os.makedirs(sub_dir_path)
bottleneck_path = get_bottleneck_path(image_lists, label_name, index, category)
if not os.path.exists(bottleneck_path):
image_path = get_image_path(image_lists, INPUT_DATA, label_name, index, category)
image_data = gfile.FastGFile(image_path, 'rb').read()
bottleneck_values = run_bottleneck_on_image(sess, image_data, jpeg_data_tensor, bottleneck_tensor)
bottleneck_string = ','.join(str(x) for x in bottleneck_values)
with open(bottleneck_path, 'w') as bottleneck_file:
bottleneck_file.write(bottleneck_string)
else:
with open(bottleneck_path, 'r') as bottleneck_file:
bottleneck_string = bottleneck_file.read()
bottleneck_values = [float(x) for x in bottleneck_string.split(',')]
return bottleneck_values
# #### 8. 這個函數隨機獲取一個batch的圖片作為訓練數據竞惋。
# In[9]:
def get_random_cached_bottlenecks(sess, n_classes, image_lists, how_many, category, jpeg_data_tensor, bottleneck_tensor):
bottlenecks = []
ground_truths = []
for _ in range(how_many):
label_index = random.randrange(n_classes)
label_name = list(image_lists.keys())[label_index]
image_index = random.randrange(65536)
bottleneck = get_or_create_bottleneck(
sess, image_lists, label_name, image_index, category, jpeg_data_tensor, bottleneck_tensor)
ground_truth = np.zeros(n_classes, dtype=np.float32)
ground_truth[label_index] = 1.0
bottlenecks.append(bottleneck)
ground_truths.append(ground_truth)
return bottlenecks, ground_truths
# #### 9. 這個函數獲取全部的測試數據，并計算正確率灰嫉。
# In[10]:
def get_test_bottlenecks(sess, image_lists, n_classes, jpeg_data_tensor, bottleneck_tensor):
bottlenecks = []
ground_truths = []
label_name_list = list(image_lists.keys())
for label_index, label_name in enumerate(label_name_list):
category = 'testing'
for index, unused_base_name in enumerate(image_lists[label_name][category]):
bottleneck = get_or_create_bottleneck(sess, image_lists, label_name, index, category,jpeg_data_tensor, bottleneck_tensor)
ground_truth = np.zeros(n_classes, dtype=np.float32)
ground_truth[label_index] = 1.0
bottlenecks.append(bottleneck)
ground_truths.append(ground_truth)
return bottlenecks, ground_truths
# #### 10. 定義主函數拆宛。
# In[11]:
def main():
image_lists = create_image_lists(TEST_PERCENTAGE, VALIDATION_PERCENTAGE)
n_classes = len(image_lists.keys())
# 讀取已經訓練好的Inception-v3模型。
with gfile.FastGFile(os.path.join(MODEL_DIR, MODEL_FILE), 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
bottleneck_tensor, jpeg_data_tensor = tf.import_graph_def(
graph_def, return_elements=[BOTTLENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME])
# 定義新的神經網絡輸入
bottleneck_input = tf.placeholder(tf.float32, [None, BOTTLENECK_TENSOR_SIZE], name='BottleneckInputPlaceholder')
ground_truth_input = tf.placeholder(tf.float32, [None, n_classes], name='GroundTruthInput')
# 定義一層全鏈接層
with tf.name_scope('final_training_ops'):
weights = tf.Variable(tf.truncated_normal([BOTTLENECK_TENSOR_SIZE, n_classes], stddev=0.001))
biases = tf.Variable(tf.zeros([n_classes]))
logits = tf.matmul(bottleneck_input, weights) + biases
final_tensor = tf.nn.softmax(logits)
# 定義交叉熵損失函數讼撒。
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=ground_truth_input)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
train_step = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(cross_entropy_mean)
# 計算正確率浑厚。
with tf.name_scope('evaluation'):
correct_prediction = tf.equal(tf.argmax(final_tensor, 1), tf.argmax(ground_truth_input, 1))
evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
# 訓練過程。
for i in range(STEPS):
train_bottlenecks, train_ground_truth = get_random_cached_bottlenecks(
sess, n_classes, image_lists, BATCH, 'training', jpeg_data_tensor, bottleneck_tensor)
sess.run(train_step, feed_dict={bottleneck_input: train_bottlenecks, ground_truth_input: train_ground_truth})
if i % 100 == 0 or i + 1 == STEPS:
validation_bottlenecks, validation_ground_truth = get_random_cached_bottlenecks(
sess, n_classes, image_lists, BATCH, 'validation', jpeg_data_tensor, bottleneck_tensor)
validation_accuracy = sess.run(evaluation_step, feed_dict={
bottleneck_input: validation_bottlenecks, ground_truth_input: validation_ground_truth})
print('Step %d: Validation accuracy on random sampled %d examples = %.1f%%' %
(i, BATCH, validation_accuracy * 100))
# 在最后的測試數據上測試正確率根盒。
test_bottlenecks, test_ground_truth = get_test_bottlenecks(
sess, image_lists, n_classes, jpeg_data_tensor, bottleneck_tensor)
test_accuracy = sess.run(evaluation_step, feed_dict={
bottleneck_input: test_bottlenecks, ground_truth_input: test_ground_truth})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100))
if __name__ == '__main__':
main()
來個圖吧
