Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 512, 512, 3-CodePudding

I am training a Unet segmentation model for binary class. The dataset is loaded in tensorflow data pipeline. The images are in (512, 512, 3) shape, masks are in (512, 512, 1) shape. The model expects the input in (512, 512, 3) shape. But I am getting the following error. Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 512, 512, 3), found shape=(512, 512, 3)

Here are the images in metadata dataframe.

Randomly sampling the indices to select the training and validation set

num_samples = train_metadata.shape[0]
train_indices = np.random.choice(range(num_samples), int(num_samples * 0.8), replace=False)

valid_indices = list(set(range(num_samples)) - set(train_indices))

train_samples = train_metadata.iloc[train_indices, ]
valid_samples = train_metadata.iloc[valid_indices, ]

Dimensions

IMG_WIDTH = 512
IMG_HEIGHT = 512
IMG_CHANNELS = 3

Parsing function for training images

def parse_function_train_images(image_path):
    image_path = image_path
    mask_path = tf.strings.regex_replace(image_path, "sat", "mask")
    mask_path = tf.strings.regex_replace(mask_path, "jpg", "png")

    image = tf.io.read_file(image_path)
    image = tf.image.decode_jpeg(image, channels=3)
    image = tf.image.convert_image_dtype(image, tf.uint8)
    image = tf.image.resize(image, (IMG_WIDTH, IMG_HEIGHT))
    #image = tf.expand_dims(image, axis=0)

    mask = tf.io.read_file(mask_path)
    mask = tf.image.decode_png(mask, channels=1)
    mask = tf.image.convert_image_dtype(mask, tf.uint8)
    mask = tf.image.resize(mask, (IMG_WIDTH, IMG_HEIGHT))
    #mask = tf.where(mask == 255, np.dtype("uint8").type(0), mask)

    return image, mask

Parsing function for test images

def parse_function_test_images(image_path):
    image = tf.io.read_file(image_path)
    image = tf.image.decode_jpeg(image, channels=3)
    image = tf.image.convert_image_dtype(image, tf.uint8)
    image = tf.image.resize(image, (IMG_WIDTH, IMG_HEIGHT))
    #image = tf.expand_dims(image, axis=0)

    return image

Loading the dataset

ds = tf.data.Dataset.from_tensor_slices(train_samples["sat_with_path"].values)
train_dataset = ds.map(parse_function_train_images)

validation_ds = tf.data.Dataset.from_tensor_slices(valid_samples["sat_with_path"].values)
validation_dataset = validation_ds.map(parse_function_train_images)

test_ds = tf.data.Dataset.from_tensor_slices(test_metadata["sat_with_path"].values)
test_dataset = test_ds.map(parse_function_test_images)

Normalizing the images

def normalize(image, mask):
    image = tf.cast(image, tf.float32) / 255.0
    mask  = tf.cast(mask, tf.float32) / 255.0
    return image, mask

def test_normalize(image):
    image = tf.cast(image, tf.float32) / 255.0
    return image

TRAIN_LENGTH = len(train_dataset)
BATCH_SIZE = 64
BUFFER_SIZE = 1000
STEPS_PER_EPOCH = TRAIN_LENGTH // BATCH_SIZE

Mapping the dataset

train_images = train_dataset.map(normalize, num_parallel_calls=tf.data.AUTOTUNE)
validation_images = validation_dataset.map(normalize, num_parallel_calls=tf.data.AUTOTUNE)
test_images = test_dataset.map(test_normalize, num_parallel_calls=tf.data.AUTOTUNE)

Augmentation Layer

class Augment(tf.keras.layers.Layer):
    def __init__(self, seed=42):
        super().__init__()
        self.augment_inputs = tf.keras.layers.RandomFlip(mode="horizontal", seed=seed)
        self.augment_labels = tf.keras.layers.RandomFlip(mode="horizontal", seed=seed)

    def call(self, inputs, labels):
        inputs = self.augment_inputs(inputs)
        inputs = tf.expand_dims(inputs, axis=0)
        labels = self.augment_labels(labels)
    
        return inputs, labels

train_batches = (
    train_images
        .cache()
        .shuffle(BUFFER_SIZE)
        .batch(BATCH_SIZE)
        .repeat()
        .map(Augment())
        .prefetch(buffer_size=tf.data.AUTOTUNE)
)

validation_batches = (
    validation_images
        .cache()
        .shuffle(BUFFER_SIZE)
        .batch(BATCH_SIZE)
        .repeat()
        .map(Augment())
        .prefetch(buffer_size=tf.data.AUTOTUNE)
)

test_batches = test_images.batch(BATCH_SIZE)

Unet Model

inputs = tf.keras.layers.Input((IMG_WIDTH, IMG_HEIGHT, IMG_CHANNELS))
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer="he_normal", padding="same")(inputs)
c1 = tf.keras.layers.Dropout(0.1)(c1)
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer="he_normal", padding="same")(c1)

p1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)

c2 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p1)
c2 = tf.keras.layers.Dropout(0.1)(c2)
c2 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c2)

p2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)

c3 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p2)
c3 = tf.keras.layers.Dropout(0.2)(c3)
c3 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c3)

p3 = tf.keras.layers.MaxPooling2D((2, 2))(c3)

c4 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p3)
c4 = tf.keras.layers.Dropout(0.2)(c4)
c4 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c4)

p4 = tf.keras.layers.MaxPooling2D((2, 2))(c4)

c5 = tf.keras.layers.Conv2D(256, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p4)
c5 = tf.keras.layers.Dropout(0.3)(c5)
c5 = tf.keras.layers.Conv2D(256, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c5)

u6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding="same")(c5)
u6 = tf.keras.layers.concatenate([u6, c4])

c6 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u6)
c6 = tf.keras.layers.Dropout(0.2)(c6)
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c6)

u7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding="same")(c6)
u7 = tf.keras.layers.concatenate([u7, c3])

c7 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u7)
c7 = tf.keras.layers.Dropout(0.2)(c7)
c7 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c7)

u8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding="same")(c7)
u8 = tf.keras.layers.concatenate([u8, c2])

c8 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u8)
c8 = tf.keras.layers.Dropout(0.1)(c8)
c8 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c8)

u9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding="same")(c8)
u9 = tf.keras.layers.concatenate([u9, c1], axis=3)

c9 = tf.keras.layers.Conv2D(16, (3, 3), strides=(2, 2), padding="same")(u9)
c9 = tf.keras.layers.Dropout(0.1)(c9)
c9 = tf.keras.layers.Conv2D(16, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c9)

outputs = tf.keras.layers.Conv2D(1, (1, 1), activation="sigmoid")(c9)

model = tf.keras.Model(inputs=[inputs], outputs=[outputs])
model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
model.summary()

checkpointer = tf.keras.callbacks.ModelCheckpoint('model_for_nuclie.h5', verbose=1, save_best_only=True)
callbacks = [
    tf.keras.callbacks.EarlyStopping(patience=2, monitor="val_loss"),
    tf.keras.callbacks.TensorBoard(log_dir="logs"),
    checkpointer
]

Fit the model to data

results = model.fit(train_images, validation_data=validation_images, \
                batch_size=16, epochs=25, callbacks=callbacks
        )

Error:

CodePudding user response：

Use train_batches in model.fit and not train_images. Also, you do not need to use repeat(), which causes an infinite dataset if you do not specify how many times you want to repeat your dataset. Regarding your labels error, try rewriting your model like this:

import tensorflow as tf

inputs = tf.keras.layers.Input((512, 512, 3))
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer="he_normal", padding="same")(inputs)
c1 = tf.keras.layers.Dropout(0.1)(c1)
c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer="he_normal", padding="same")(c1)

p1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)

c2 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p1)
c2 = tf.keras.layers.Dropout(0.1)(c2)
c2 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c2)

p2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)

c3 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p2)
c3 = tf.keras.layers.Dropout(0.2)(c3)
c3 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c3)

p3 = tf.keras.layers.MaxPooling2D((2, 2))(c3)

c4 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p3)
c4 = tf.keras.layers.Dropout(0.2)(c4)
c4 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c4)

p4 = tf.keras.layers.MaxPooling2D((2, 2))(c4)

c5 = tf.keras.layers.Conv2D(256, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(p4)
c5 = tf.keras.layers.Dropout(0.3)(c5)
c5 = tf.keras.layers.Conv2D(256, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c5)

u6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding="same")(c5)
u6 = tf.keras.layers.concatenate([u6, c4])

c6 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u6)
c6 = tf.keras.layers.Dropout(0.2)(c6)
c6 = tf.keras.layers.Conv2D(128, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c6)

u7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding="same")(c6)
u7 = tf.keras.layers.concatenate([u7, c3])

c7 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u7)
c7 = tf.keras.layers.Dropout(0.2)(c7)
c7 = tf.keras.layers.Conv2D(64, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c7)

u8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding="same")(c7)
u8 = tf.keras.layers.concatenate([u8, c2])

c8 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(u8)
c8 = tf.keras.layers.Dropout(0.1)(c8)
c8 = tf.keras.layers.Conv2D(32, (3, 3), activation="relu", kernel_initializer="he_normal", padding="same")(c8)

u9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding="same")(c8)
u9 = tf.keras.layers.concatenate([u9, c1], axis=3)

outputs = tf.keras.layers.Conv2D(1, (1, 1), activation="sigmoid")(u9)

model = tf.keras.Model(inputs=[inputs], outputs=[outputs])
model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
model.summary()