ValueError: Error when checking target: expected conv2d_19 to have shape (None, 320, 320, 1) but got array with shape (18, 320, 320, 2)

0
votes

I try to train a U-Net model in keras, with regular segmentation (not multui-classe), but I get the following error:

ValueError: Error when checking target: expected conv2d_19 to have shape (None, 320, 320, 1) but got array with shape (18, 320, 320, 2)

I know this is related to the input Y_train, and I to the keras.utils.to_categorical function, but to_categorical(Y_train) and to_categorical(Y_train, 2) returns this error, while to_categorical(Y_train, 1) returns IndexError: index 1 is out of bounds for axis 1 with size 1.

I even tried to change Y_train by reshaping it into (None, 320, 320, 1) but it returned

'ValueError: You are passing a target array of shape (18, 320, 320, 1) while using as loss categorical_crossentropy. categorical_crossentropy expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via: from keras.utils import to_categorical y_binary = to_categorical(y_int) Alternatively, you can use the loss function sparse_categorical_crossentropy instead, which does expect integer targets.'

The error is returned when I try to fit the model, using the training function.

    def preprocess_images(X_train, Y_train, X_test, Y_test):

        X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], X_train.shape[2], 1)
        X_test = X_test.reshape(X_test.shape[0], X_train.shape[1], X_train.shape[2], 1)

        X_train = X_train.astype("float32")
        X_test = X_test.astype("float32")
        X_train /= 255
        X_test /= 255

        Y_train /= 255
        Y_test /= 255
        #Y_train = Y_train.reshape(Y_train.shape[0], Y_train.shape[1], Y_train.shape[2], 1)
        #Y_test = Y_test.reshape(Y_test.shape[0], Y_train.shape[1], Y_train.shape[2], 1)
        Y_train = keras.utils.to_categorical(Y_train, 1)
        Y_test = keras.utils.to_categorical(Y_test, 1)

        return ((X_train, Y_train), (X_test, Y_test))


    def CNNs_layers(nb_conv_pool = 1, filters = 32, kernel_size = (3, 3), activation = 'relu', pool_size = (2 ,2), dropout_rate = 0.25, input_shape = (28, 28, 1), data_format = 'channels_last'):


        inputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))
        s = tf.keras.layers.Lambda(lambda x: x / 255)(inputs)

        c1 = tf.keras.layers.Conv2D(16, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(s)
        c1 = tf.keras.layers.Dropout(0.1)(c1)
        c1 = tf.keras.layers.Conv2D(16, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(c1)
        p1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)

        c2 = tf.keras.layers.Conv2D(32, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(p1)
        c2 = tf.keras.layers.Dropout(0.1)(c2)
        c2 = tf.keras.layers.Conv2D(32, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(c2)
        p2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)

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

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

        c4 = tf.keras.layers.Conv2D(128, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(p3)
        c4 = tf.keras.layers.Dropout(0.2)(c4)
        c4 = tf.keras.layers.Conv2D(128, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(c4)
        p4 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(c4)

        c5 = tf.keras.layers.Conv2D(256, (3, 3), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(p4)
        c5 = tf.keras.layers.Dropout(0.3)(c5)
        c5 = tf.keras.layers.Conv2D(256, (3, 3), activation=tf.keras.activations.elu, 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=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(u6)
        c6 = tf.keras.layers.Dropout(0.2)(c6)
        c6 = tf.keras.layers.Conv2D(128, (3, 3), activation=tf.keras.activations.elu, 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=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(u7)
        c7 = tf.keras.layers.Dropout(0.2)(c7)
        c7 = tf.keras.layers.Conv2D(64, (3, 3), activation=tf.keras.activations.elu, 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=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(u8)
        c8 = tf.keras.layers.Dropout(0.1)(c8)
        c8 = tf.keras.layers.Conv2D(32, (3, 3), activation=tf.keras.activations.elu, 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), activation=tf.keras.activations.elu, kernel_initializer='he_normal',
                                padding='same')(u9)
        c9 = tf.keras.layers.Dropout(0.1)(c9)
        c9 = tf.keras.layers.Conv2D(16, (3, 3), activation=tf.keras.activations.elu, 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()

        return (model)


    def training(model, X_train, Y_train, loss = 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'], batch_size = 32, nb_epoch = 100, verbose = 2, validation_split = 0.3):
        model.compile(loss = loss, optimizer = optimizer, metrics = metrics)
        history = model.fit(X_train, Y_train, batch_size = batch_size, epochs = nb_epoch, verbose = verbose, validation_split = validation_split)
        return (history)
1
pythontensorflowkerasconv-neural-network
Why are your labels (18, 320, 320, 2)? What does the last element (the 2) in your shape mean? Are these one-hot encoded binary labels? – Dr. Snoopy
Because masks are binary matrix of 0 and 1, and so the to_categorical function create 2 classes. I don't know really what should I do to the input labels, but when I look to the U-Net diagram the last block is composed of 2 channels. – Hagear

1 Answers

0
votes

Assuming your labels are one-hot encoded, then you should change the output layer to:

outputs = tf.keras.layers.Conv2D(2, (1, 1), activation='softmax')(c9)

And the loss function to categorical_crossentropy. If you want to use your current model and loss with no modifications, then you must not one-hot encode your labels, as binary_crossentropy takes 0-1 binary labels directly without one-hot encoding.