模型的"Input 0"层与该层不兼容：期望形状为(None, 512, 512, 3)，但实际得到形状为(512, 512, 3)。

Question

我正在训练一个二元分类的Unet分割模型。数据集已在tensorflow数据管道中加载。图像形状为(512, 512, 3)，掩码形状为(512, 512, 1)。模型期望输入形状为(512, 512, 3)，但我遇到了以下错误。 “model”层的输入0与该层不兼容：期望形状=(None, 512, 512, 3)，找到形状=(512, 512, 3)。

这是metadata数据帧中的图像。

随机抽样索引以选择训练和验证集

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, ]

尺寸

IMG_WIDTH = 512
IMG_HEIGHT = 512
IMG_CHANNELS = 3

训练图像的解析函数

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

解析测试图像的函数

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

加载数据集

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)

标准化图像

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

映射数据集

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)

增强层

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模型

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
]

将模型拟合到数据中

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

错误：

- Junaid Ali

---

你能展示一下 train_batches 中的一个 batch 的形状吗？ - AloneTogether

对于 train_batches.take(2) 中的图像和掩码： sample_imaDge, sample_mask = images[0], masks[0] print(sample_image.shape) #display([sample_image, sample_mask]) - Junaid Ali

(64, 512, 512, 3) - Junaid Ali

@AloneTogether 使用 train_batches.take(2) 并打印形状。 - Junaid Ali

为什么你在使用 repeat()？移除它。 - AloneTogether

Answer 1

请使用 model.fit 中的 train_batches 而不是 train_images。此外，您不需要使用 repeat() 方法，如果您不指定要重复数据集的次数，它会导致无限数据集。关于标签错误，请尝试按以下方式重写您的模型:

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()

- AloneTogether