我已经使用 keras 构建了一个 CNN 自动编码器,它对 MNIST 测试数据集运行良好。我现在正在尝试使用从另一个来源收集的不同数据集。有纯图像,我必须使用 cv2 阅读它们,效果很好。然后我将这些图像转换成一个 numpy 数组,我认为它再次工作正常。但是当我尝试执行 .fit 方法时,它给了我这个错误。
Error when checking target: expected conv2d_39 to have shape (100, 100, 1) but got array with shape (100, 100, 3)
我尝试将图像转换为灰度,但它们随后得到的是模型想要的形状 (100,100) 而不是 (100,100,1)。我在这里做错了什么?
这是我使用的代码:
def read_in_images(path):
images = []
for files in os.listdir(path):
img = cv2.imread(os.path.join(path, files))
if img is not None:
images.append(img)
return images
train_images = read_in_images(train_path)
test_images = read_in_images(test_path)
x_train = np.array(train_images)
x_test = np.array(test_images) # (36, 100, 100, 3)
input_img = Input(shape=(100,100,3))
x = Conv2D(32, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(168, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(x_train, x_train,
epochs=25,
batch_size=128,
shuffle=True,
validation_data=(x_test, x_test),
callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])
该模型适用于 MNIST 数据集,但不适用于我自己的数据集。任何帮助将不胜感激。
最佳答案
您的输入和输出形状不同。这会触发错误(我认为)。
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
应该是
decoded = Conv2D(num_channels, (3, 3), activation='sigmoid', padding='same')(x)
关于python - Keras CNN 自动编码器输入形状错误,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/56438374/