‘'DNN’对象在ImageDataGenerator() - keras中没有属性‘ImageDataGenerator’。

Question

下面的代码用于使用带有tensorflow后端的keras和python识别5个图像类。我使用过imageDataGenerator，但是当我运行它时，它已经开始训练了，过了一段时间之后，出现了错误。

我怎么才能解决这个问题？

训练步骤:127个全损失: 0.01171倍时间:32.772秒比亚当区: 005倍损失: 0.01171 - acc: 0.9971 -- iter: 1536/1550训练步骤:128个总损失: 0.01055倍时间:36.283秒:0.005倍损失: 0.01055 - acc: 0.9974 - val_loss: 3.05709 - val_acc: 0.6500 - iter: 1550/1550 -找到属于0类的0幅图像。找到了属于0类的0幅图像。回溯(最近一次调用)： 文件""，第1行，在runfile('D:/My Projects/FinalProject_Vr_01.2/CNN_IMGDG_stackoverflow.py'，wdir='D:/My Projects/FinalProject_Vr_01.2') 文件"C:\Users\Asus\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py"，行704，在runfile中(文件名，命名空间) 文件"C:\Users\Asus\Anaconda3\lib\site-packages\spyder_kernels\customize\spydercustomize.py"，第108行，在execfile exec(f.read()，filename，'exec')，命名空间中 文件"D:/My Projects/FinalProject_Vr_01.2/CNN_IMGDG_stackoverflow.py"，line 191，in model.fit_generator(train_generator， AttributeError: DNN对象没有属性'fit_generator‘

import cv2                
import numpy as np         
import os                
from random import shuffle 
from tqdm import tqdm      
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential

TRAIN_DIR = 'train'
VALID_DIR = 'validate'
TEST_DIR = 'test'
IMG_SIZE = 128
LR = 1e-3
train_samples = 1500
valdate_samples = 250
epochs = 5
batch_size = 10



MODEL_NAME = 'snakes-{}-{}.model'.format(LR, '2conv-basic')

def label_img(img):
    print("\nImage = ",img)
    print("\n",img.split('.')[-2])
    temp_name= img.split('.')[-2]
    print("\n",temp_name[:1])
    temp_name=temp_name[:1]
    word_label = temp_name


    if word_label == 'A': return [0,0,0,0,1]    
    elif word_label == 'B': return [0,0,0,1,0]
    elif word_label == 'C': return [0,0,1,0,0]
    elif word_label == 'D': return [0,1,0,0,0]
    elif word_label == 'E' : return [1,0,0,0,0]   

def create_train_data():
    training_data = []
    for img in tqdm(os.listdir(TRAIN_DIR)):
        label = label_img(img)
        path = os.path.join(TRAIN_DIR,img)
        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
        img = cv2.resize(img,(IMG_SIZE,IMG_SIZE))
        training_data.append([np.array(img),np.array(label)])
    shuffle(training_data)
    np.save('train_data.npy', training_data)
    return training_data


def create_validate_data():
    validating_data = []
    for img in tqdm(os.listdir(VALID_DIR)):
        label = label_img(img)
        path = os.path.join(VALID_DIR,img)
        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
        img = cv2.resize(img,(IMG_SIZE,IMG_SIZE))
        validating_data.append([np.array(img),np.array(label)])
    shuffle(validating_data)
    np.save('validate_data.npy', validating_data)
    return validating_data


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

train_data = create_train_data()
validate_data = create_validate_data()


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
tf.reset_default_graph()


convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')

convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 128, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 5, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

model = tflearn.DNN(convnet, tensorboard_dir='log')



if os.path.exists('{}.meta'.format(MODEL_NAME)):
    model.load(MODEL_NAME)
    print('model loaded!')


train = train_data[:]
validate = validate_data[:]

X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = [i[1] for i in train]


validate_x = np.array([i[0] for i in validate]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
validate_y = [i[1] for i in validate]

model.fit({'input': X}, {'targets': Y}, n_epoch=epochs, validation_set=({'input': validate_x}, {'targets': validate_y}), 
    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)


train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

validation_datagen = ImageDataGenerator(rescale=1. / 255)


train_generator = train_datagen.flow_from_directory('train',
                                                    target_size=(IMG_SIZE, IMG_SIZE),
                                                    batch_size=batch_size,
                                                    class_mode='categorical')

validation_generator = validation_datagen.flow_from_directory('validate',
                                                        target_size=(IMG_SIZE, IMG_SIZE),
                                                        batch_size=batch_size,
                                                        class_mode='categorical')


model.fit_generator(train_generator,
                    steps_per_epoch=25,
                    epochs=epochs,
                    validation_data=validation_generator,
                    validation_steps=25)


model.save(MODEL_NAME)

Answer 1

在定义神经网络时，可以使用Keras。(您在这里所做的是使用Tensorflow定义网络。它没有fit_generator方法。)

import keras
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.models import Sequential

这些是您可以在应用程序中与Keras一起使用的层。然后用DNN = Sequential()初始化DNN

参考这个用Keras编写的简单分类器，您就会得到这个想法。

Answer 2

您的模型对象是tflearn.DNN类的一个实例，它根本没有fit_generator方法。此方法仅适用于keras对象。也许您可以在keras中定义您的体系结构，并且您可以使用您的数据生成器。

Answer 3

其他意见

如果你想看一个模型和ACC，那就输吧

你需要使用张紧板

例1:在Colab

load_ext tensorboard
tensorboard --logdir='/tmp/tflearn_logs'