When I train my Autoencoder I always get the same output

Question

Im creatting an autoencoder to learn features from markets images, but when I train the model I always get the same output. Could anyone help to me?

This is the code:

from keras import layers
input_img = keras.Input(shape=(224, 224, 3))
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same',activity_regularizer=regularizers.L2(1e-4))(input_img)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same',activity_regularizer=regularizers.L2(1e-4))(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.MaxPooling2D((2, 2), padding='same')(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.MaxPooling2D((2, 2), padding='same')(x)
x = layers.Conv2D(256, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(256, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(256, (3, 3), activation='relu', padding='same')(x)
x = layers.MaxPooling2D((2, 2), padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)
x = layers.MaxPooling2D((2, 2), padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(512, (3, 3), activation='relu', padding='same')(x)

encoded = layers.AveragePooling2D((14, 14), padding='same')(x)


x = layers.Conv2D(784, (3, 3), activation='relu', padding='same')(encoded)
x = layers.Conv2D(784, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(784, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((7, 7))(x)
x = layers.Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(16, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((2, 2))(x)
x = layers.Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((2, 2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((2, 2))(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((2, 2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = layers.UpSampling2D((2, 2))(x)

decoded = layers.Conv2D(3, (3, 3), activation='softmax', padding='same')(x)

autoencoder=keras.Model(input_img, decoded)
autoencoder.compile(optimizer='adamax', loss='mse',metrics=["accuracy"])
autoencoder.summary()

I dont know how to deal with this problem, Im new in this kind of task.