时间戳

首页 > 解决方案 > 用于图像增强的 TensorFlow 使 keras 无法工作

python - 用于图像增强的 TensorFlow 使 keras 无法工作

问题描述

我正在实施 CNN 进行图像分类；我使用 keras 采用了一个随机的 CNN 架构

import keras
from keras.models import Sequential,Input,Model
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
from keras.layers.advanced_activations import LeakyReLU

model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), activation="relu", input_shape=(n,n,1)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(filters=64, kernel_size=(5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adam(),metrics=['accuracy'])



train = model.fit(train_X, train_label, batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(valid_X, valid_label))

我正在尝试使用 tensorflow 的代码进行图像增强，我更喜欢此代码而不是使用 keras ImageDataGenerator 进行数据增强，因为它让我更灵活。



import tensorflow as tf


def rotate_images(X_imgs):
    X_rotate = []
    tf.reset_default_graph()
    X = tf.placeholder(tf.float32, shape = (n, n, 1))
    k = tf.placeholder(tf.int32)
    tf_img = tf.image.rot90(X, k = k)
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for img in X_imgs:
            for i in range(3):  # Rotation at 90, 180 and 270 degrees
                rotated_img = sess.run(tf_img, feed_dict = {X: img, k: i + 1})
                X_rotate.append(rotated_img)

    X_rotate = np.array(X_rotate, dtype = np.float32)
    return X_rotate

当我尝试拟合我的模型时，我收到以下错误消息

InvalidArgumentError: Tensor dense_7_target:0, specified in either feed_devices or fetch_devices was not found in the Graph

看起来graph是tensorflow使用的东西，我认为我在keras和tansorflow之间的交互很糟糕；令人惊讶的是我曾经能够运行我的模型，但现在它又坏了..

如果您需要更多信息，请告诉我；感谢帮助

标签： pythontensorflowkerasneural-network

解决方案

不要使用tf.reset_default_graph()，您可以为您的函数创建一个新的临时图表：

import tensorflow as tf

def rotate_images(X_imgs):
    X_rotate = []
    with tf.Graph().as_default():
        X = tf.placeholder(tf.float32, shape = (n, n, 1))
        k = tf.placeholder(tf.int32)
        tf_img = tf.image.rot90(X, k = k)
        with tf.Session() as sess:
            sess.run(tf.global_variables_initializer())
            for img in X_imgs:
                for i in range(3):  # Rotation at 90, 180 and 270 degrees
                    rotated_img = sess.run(tf_img, feed_dict = {X: img, k: i + 1})
                    X_rotate.append(rotated_img)
        X_rotate = np.array(X_rotate, dtype = np.float32)
        return X_rotate

推荐阅读