Python try 使用KERAS Sequential向图像添加噪声时图像尺寸不匹配

要在您的系统上重新创建此问题的提问，请找到源代码和数据集here

What I am trying?
I am trying to create a simple GAN (Generative Adversarial N/w) where I am trying to recolor Black and White images using a few ImageNet images.

What Process am I following?
I have take a few Dog images, which are stored in folder ./ImageNet/dogs/ directory. Using Python code I have created 2 more steps where I convert

1. 将狗狗图像转换为244 x 244分辨率并保存为./ImageNet/dogs_lowres/
2. 将低分辨率图像转换为灰度并保存为./ImageNet/dogs_bnw/
3. 将低分辨率的BNW图像送入GaN模型，生成彩色图像.

Where am I Stuck?
I am stuck at understanding how the Image dimensions / shape are used. I am getting the error as such:

ValueError: `logits` and `labels` must have the same shape, received ((32, 28, 28, 3) vs (32, 224, 224)).

下面是生成器和鉴别器的代码:

# GAN model for recoloring black and white images
generator = Sequential()
generator.add(Dense(7 * 7 * 128, input_dim=100))
generator.add(Reshape((7, 7, 128)))
generator.add(Conv2DTranspose(64, kernel_size=5, strides=2, padding='same'))
generator.add(Conv2DTranspose(32, kernel_size=5, strides=2, padding='same'))
generator.add(Conv2DTranspose(3, kernel_size=5, activation='sigmoid', padding='same'))

# Discriminator model
discriminator = Sequential()
discriminator.add(Flatten(input_shape=(224, 224, 3)))
discriminator.add(Dense(1, activation='sigmoid'))

# Compile the generator model
optimizer = Adam(learning_rate=0.0002, beta_1=0.5)
generator.compile(loss='binary_crossentropy', optimizer=optimizer)

# Train the GAN to recolor images
epochs = 10000
batch_size = 32

训练循环如下:

for epoch in range(epochs):
    idx = np.random.randint(0, bw_images.shape[0], batch_size)
    real_images = bw_images[idx]

    noise = np.random.normal(0, 1, (batch_size, 100))
    generated_images = generator.predict(noise)

    # noise_rs = noise.reshape(-1, 1)
    g_loss = generator.train_on_batch(noise, real_images)

    if epoch % 100 == 0:
        print(f"Epoch: {epoch}, Generator Loss: {g_loss}")

Where is the Error? I get error on line:
g_loss = generator.train_on_batch(noise, real_images)

当我判断shape个噪波和Real_Image对象时，我得到的是:

real_images.shape
(32, 224, 224)
noise.shape
(32, 100)

任何帮助/建议都很感激.