How to change 257x251x1 uint8 into 257x251x3 uint8?

Can anyone help me out? How to change my input image data in grayscale 257x251x1 uint8 change into 'truecolor' rgb type? (mxnx3)

Here my codes:

I=imread('1222.png');

I2=I(:,:,1:3);

The error occured; Index in position 3 exceeds array bounds (must not exceed 1).

Answer 1

[Walter Roberson]

I=imread('1222.png');
if ndims(I) == 2; I = I(:,:,[1 1 1]); end   %convert to rgb

[Dayangku Nur Faizah Pengiran Mohamad]

Thank you Walter! It works for me

[Dayangku Nur Faizah Pengiran Mohamad]

Hi Sir Walter! I want to ask some more question.

I got error when running my U-net architecture network and I'm not sure where is the error and to fix that. Here's my codes input image codes: and I have tried so many times to fix this problem, but at the end still error. I am using U-Net architecture network to segment my image data. Since my input image data is M x N x 3, but the dimension is not the same as 256 x 256 x 3. My dimension input image is 251 x 257 x 3 uint8.

I have tried to change the codes into:

#imgs = np.asarray((total, image_rows, image_cols, 3), dtype=np.uint8)
#imgs_mask = np.asarray((total, image_rows, image_cols), dtype=np.uint8)

from this:

imgs = np.ndarray((total, image_rows, image_cols, 3), dtype=np.uint8)
imgs_mask = np.ndarray((total, image_rows, image_cols), dtype=np.uint8)

Here the full codes for my testing input data:

def create_test_data():
for i in range(len(image)):
    print('-'*9)
    print("Creating testing images...")
    print('-'*9)
    print(image[i])
    
    
    test_data_path = '/home/motmot/Documents/unet/data/test/img/'
    test_mask_path = '/home/motmot/Documents/unet/data/test/msk/'
    image = os.listdir(test_data_path)
    mask = os.listdir(test_mask_path)
    total = len(image)
    imgs = np.ndarray((total, image_rows, image_cols, 3), dtype=np.uint8)
    #imgs = np.asarray((total, image_rows, image_cols, 3), dtype=np.uint8)
    imgs_mask = np.ndarray((total, image_rows, image_cols), dtype=np.uint8)
    #imgs_mask = np.asarray((total, image_rows, image_cols), dtype=np.uint8)
    
    create_test_data()
    

And here my U-net architecture network codes:

    def get_unet():
    inputs = Input((img_rows, img_cols, 3))
    conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(inputs)
    conv1 = BatchNormalization()(conv1)
    conv1 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv1)
    conv1 = BatchNormalization()(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    
    conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(pool1)
    conv2 = BatchNormalization()(conv2)
    conv2 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv2)
    conv2 = BatchNormalization()(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    
    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool2)
    conv3 = BatchNormalization()(conv3)
    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv3)
    conv3 = BatchNormalization()(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    
    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool3)
    conv4 = BatchNormalization()(conv4)
    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv4)
    conv4 = BatchNormalization()(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
    
    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool4)
    conv5 = BatchNormalization()(conv5)
    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv5)
    conv5 = BatchNormalization()(conv5)
    
    up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(conv5), conv4], axis=3)
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(up6)
    conv6 = BatchNormalization()(conv6)
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv6)
    conv6 = BatchNormalization()(conv6)
    
    up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv6), conv3], axis=3)
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(up7)
    conv7 = BatchNormalization()(conv7)
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv7)
    conv7 = BatchNormalization()(conv7)

    up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv7), conv2], axis=3)
    conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(up8)
    conv8 = BatchNormalization()(conv8)
    conv8 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv8)
    conv8 = BatchNormalization()(conv8)
    
    up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(conv8), conv1], axis=3)
    conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(up9)
    conv9 = BatchNormalization()(conv9)
    conv9 = Conv2D(32, (3, 3), activation='relu', padding='same')(conv9)
    conv9 = BatchNormalization()(conv9)
        
    conv10 = Conv2D(1, (1, 1), activation='sigmoid')(conv9)

    model = Model(inputs=[inputs], outputs=[conv10])
    model.compile(optimizer=Adam(), loss=[loss], metrics=[dice_coef, iou_coef])
    return model
    
    

And the error occured :

ValueError: Error when checking input: expected input_1 to have 4 dimensions, but got array with shape (2048, 256, 3)

[Walter Roberson]

@Dayangku Nur Faizah Pengiran Mohamad

Sorry, I do not know Python.

[Walter Roberson]

Based on the sizes it looks like you concatenated along the first dimension when you needed to concatenate along the 4th dimension.

[mohd akmal masud]

Dear @Dayangku Nur Faizah Pengiran Mohamad, maybe you can attached the image data, and groundtruth labeling here.

quite imposiible to find the error just read the code given.