在尝试学习 keras 和深度学习时,我想创建一个图像抠图算法,该算法使用类似于修改后的自动编码器的架构,它需要两个图像输入(一个源图像和一个用户生成的 trimap)并产生一个图像输出(图像前景的 alpha 值)。编码器部分(两个输入)是使用预训练的 VGG16 进行简单的特征提取。我想使用低分辨率 alphamatting.com 数据集训练解码器。
运行附加的代码会产生错误:
ValueError: Input 0 of layer block1_conv1 is incompatible with the layer: expected ndim=4, found ndim=2. Full shape received: [None, None]
我无法理解这个错误。我验证了我的 twin_gen 闭包正在为两个输入生成形状 (22, 256,256,3) 的图像批次,所以我猜问题是我以某种方式创建了错误的模型,但我看不出错误在哪里. 任何人都可以帮助阐明我如何看到这个错误吗?
import tensorflow as tf
from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2DTranspose, Concatenate, BatchNormalization, Input
from tensorflow.keras.preprocessing.image import ImageDataGenerator
def DeConvBlock(input, num_output):
x = Conv2DTranspose(num_output, kernel_size=3, strides=2, activation='relu', padding='same')(input)
x = BatchNormalization()(x)
x = Conv2DTranspose(num_output, kernel_size=3, strides=1, activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = Conv2DTranspose(num_output, kernel_size=3, strides=1, activation='relu', padding='same')(x)
x = BatchNormalization()(x)
return x
img_input = Input((256, 256, 3))
img_vgg16 = VGG16(include_top=False, weights='imagenet')
img_vgg16._name = 'img_vgg16'
img_vgg16.trainable = False
tm_input = Input((256, 256, 3))
tm_vgg16 = VGG16(include_top=False, weights='imagenet')
tm_vgg16._name = 'tm_vgg16'
tm_vgg16.trainable = False
img_vgg16 = img_vgg16(img_input)
tm_vgg16 = tm_vgg16(tm_input)
x = Concatenate()([img_vgg16, tm_vgg16])
x = DeConvBlock(x, 512)
x = DeConvBlock(x, 256)
x = DeConvBlock(x, 128)
x = DeConvBlock(x, 64)
x = DeConvBlock(x, 32)
x = Conv2DTranspose(1, kernel_size=3, strides=1, activation='sigmoid', padding='same')(x)
m = Model(inputs=[img_input, tm_input], outputs=x)
m.summary()
m.compile(optimizer='adam', loss='mean_squared_error')
gen = ImageDataGenerator(width_shift_range=0.1, rotation_range=30, height_shift_range=0.1, horizontal_flip=True, validation_split=0.2, preprocessing_function=preprocess_input)
SEED = 49
def twin_gen(generator, subset):
gen_img = generator.flow_from_directory('./data', classes=['input_training_lowres'], seed=SEED, shuffle=False, subset=subset, color_mode='rgb')
gen_map = generator.flow_from_directory('./data/trimap_training_lowres', classes=['Trimap1'], seed=SEED, shuffle=False, subset=subset, color_mode='rgb')
gen_truth = generator.flow_from_directory('./data', classes=['gt_training_lowres'], seed=SEED, shuffle=False, subset=subset, color_mode='rgb')
while True:
img = gen_img.__next__()
tm = gen_map.__next__()
gt = gen_truth.__next__()
yield [[img, tm], gt]
train_gen = twin_gen(gen, 'training')
val_gen = twin_gen(gen, 'validation')
checkpoint_filepath = 'checkpoint'
checkpoint = tf.keras.callbacks.ModelCheckpoint(
filepath=checkpoint_filepath,
save_weights_only=True,
monitor='val_loss',
mode='auto',
save_freq='epoch',
save_best_only=True)
r = m.fit(train_gen, validation_data=val_gen, epochs=10, callbacks=[checkpoint])