Я построил классификатор двоичных изображений с использованием сверточных нейронных сетей с использованием TensorFlow. Однако он работает нормально, каждый раз, когда тренировка с нуля занимает слишком много времени.Итак, я хочу сохранить обученную модель и загрузить ее в следующий раз.Кажется, я не понимаю, как реализовать эти руководства в моей программе, как показано в документации TensorFlow.Вот полный код:
# Python program to create
# Image Classifier using CNN
# Importing the required libraries
import cv2
import os
import numpy as np
from random import shuffle
from tqdm import tqdm
from keras.models import Sequential
'''Setting up the env'''
TRAIN_DIR = 'D:\\Project\\Final_Project\\chest_xray\\train\\'
TEST_DIR = 'D:\\Project\\Final_Project\\chest_xray\\test0\\'
check_point = 'D:\\Project\\Final_Project\\chest_xray\\chkpt\\'
IMG_SIZE = 80
LR = 1e-4
'''Setting up the model which will help with tensorflow models'''
MODEL_NAME = 'NormalVsAbnormalXRays-{}-{}.model'.format(LR, '6conv-basic')
'''Labelling the dataset'''
def label_img(img):
word_label = img.split('.')[-3]
# DIY One hot encoder
if word_label == 'Nor':
return [1, 0]
elif word_label == 'Pne':
return [0, 1]
else :
return[0, 0]
'''Creating the training data'''
def create_train_data():
# Creating an empty list where we should the store the training data
# after a little preprocessing of the data
training_data = []
# tqdm is only used for interactive loading
# loading the training data
for img in tqdm(os.listdir(TRAIN_DIR)):
# labeling the images
label = label_img(img)
path = os.path.join(TRAIN_DIR, img)
# loading the image from the path and then converting them into
# greyscale for easier covnet prob
img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
# resizing the image for processing them in the covnet
img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))
# final step-forming the training data list with numpy array of the images
training_data.append([np.array(img), np.array(label)])
# shuffling of the training data to preserve the random state of our data
shuffle(training_data)
# saving our trained data for further uses if required
np.save('train_data.npy', training_data)
return training_data
'''Processing the given test data'''
# Almost same as processing the traning data but
# we dont have to label it.
def process_test_data():
testing_data = []
for img in tqdm(os.listdir(TEST_DIR)):
path = os.path.join(TEST_DIR, img)
img_num = img.split('.')[0]
img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))
testing_data.append([np.array(img), img_num])
shuffle(testing_data)
np.save('test_data.npy', testing_data)
return testing_data
'''Running the training and the testing in the dataset for our model'''
#train_data = create_train_data()
#test_data = process_test_data()
train_data = np.load('train_data.npy')
test_data = np.load('test_data.npy')
'''Creating the neural network using tensorflow'''
# Importing the required libraries
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tensorflow as tf
model = Sequential()
tf.reset_default_graph()
saver = tf.train.import_meta_graph('D:\\Project\\Final_Project\\chest_xray\\check_point-78.meta')
convnet = input_data(shape=[None,IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 4, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 4, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 4, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 4, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 32, 4, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.3)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR,
loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log', checkpoint_path='check_point',best_checkpoint_path= 'check_point',max_checkpoints= 5)
# Splitting the testing data and training data
train = train_data
test = train_data
'''Setting up the features and lables'''
# X-Features & Y-Labels
X = np.array([i[0] for i in train]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
Y = [i[1] for i in train]
test_x = np.array([i[0] for i in test]).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
test_y = [i[1] for i in test]
'''Fitting the data into our model'''
# epoch = 40 taken
model.fit({'input': X}, {'targets': Y}, n_epoch=1,
validation_set=0.05,
snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
model.save(MODEL_NAME)
'''Testing the data'''
import matplotlib.pyplot as plt
# if you need to create the data:
# test_data = process_test_data()
# if you already have some saved:
test_data = np.load('test_data.npy')
fig = plt.figure(figsize=(80,80))
for num, data in enumerate(test_data[:1]):
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(1, 1, num + 1)
orig = img_data
data = img_data.reshape(IMG_SIZE, IMG_SIZE, 1)
# model_out = model.predict([data])[0]
model_out = model.predict([data])[0]
if np.argmax(model_out) == 1:
str_label = 'Abnormal'
else:
str_label = 'Normal'
y.imshow(orig, cmap='gray')
plt.title(str_label,fontsize=20)
y.axes.get_xaxis().set_visible(False)
y.axes.get_yaxis().set_visible(False)
plt.show()
Я пытался использовать saver = tf.train.import_meta_graph('D:\\Project\\Final_Project\\chest_xray\\check_point-78.meta') для импорта графика, но я получаю эту ошибку
Traceback (most recent call last):
File "D:/Project/Final_Project/chest_xray/Final_CNN.py", line 104, in <module>
saver = tf.train.import_meta_graph('D:\\Project\\Final_Project\\chest_xray\\check_point-78.meta')
File "C:\Users\waqar\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1674, in import_meta_graph
meta_graph_or_file, clear_devices, import_scope, **kwargs)[0]
File "C:\Users\waqar\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1696, in _import_meta_graph_with_return_elements
**kwargs))
File "C:\Users\waqar\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\meta_graph.py", line 852, in import_scoped_meta_graph_with_return_elements
ops.prepend_name_scope(value, scope_to_prepend_to_names))
File "C:\Users\waqar\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 3490, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "C:\Users\waqar\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 3550, in _as_graph_element_locked
"graph." % repr(name))
KeyError: "The name 'Adam' refers to an Operation not in the graph."
Процесс завершен с кодом выхода 1