帶有彩色蒙版的語義圖像分割

Question

所以我有一組帶有彩色面具的圖片，例如藍色代表椅子，紅色代表燈等。

由於我對這一切都不熟悉，因此我嘗試使用 unet model 執行此操作，我已經使用 keras 處理了圖像，就像這樣。

def data_generator(img_path,mask_path,batch_size):
    c=0
    n = os.listdir(img_path)
    m = os.listdir(mask_path)
    random.shuffle(n)
    while(True):
        img = np.zeros((batch_size,256,256,3)).astype("float")
        mask = np.zeros((batch_size,256,256,1)).astype("float")

        for i in range(c,c+batch_size):
            train_img = cv2.imread(img_path+"/"+n[i])/255.
            train_img = cv2.resize(train_img,(256,256))
            img[i-c] = train_img

            train_mask = cv2.imread(mask_path+"/"+m[i],cv2.IMREAD_GRAYSCALE)/255.
            train_mask = cv2.resize(train_mask,(256,256))
            train_mask = train_mask.reshape(256,256,1)

            mask[i-c]=train_mask

        c+=batch_size
        if(c+batch_size>=len(os.listdir(img_path))):
            c=0
            random.shuffle(n)

        yield img,mask

現在仔細看，我認為這種方式不適用於我的面具，我嘗試將面具處理為 rgb 顏色，但我的 model 不會像那樣訓練。

model。

def unet(pretrained_weights = None,input_size = (256,256,3)):
    inputs = Input(input_size)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
    merge6 = concatenate([drop4,up6], axis = 3)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    merge7 = concatenate([conv3,up7], axis = 3)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    merge8 = concatenate([conv2,up8], axis = 3)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    merge9 = concatenate([conv1,up9], axis = 3)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)

    model = Model(input = inputs, output = conv10)

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])

    #model.summary()

    if(pretrained_weights):
        model.load_weights(pretrained_weights)

    return model

所以我的問題是如何用彩色圖像蒙版訓練 model。

編輯，我擁有的數據示例。

給定圖像來訓練 model

它的面具

以及每個這樣的面具的百分比。 {"water": 4.2, "building": 33.5, "road": 0.0}

Answer 1

在語義分割問題中，每個像素屬於任何目標 output 類/標簽。 因此，您的 output 層conv10應將類總數 (n_classes) 作為 no._of_kernels 的值，並將softmax作為激活 function 的值，如下所示：

conv10 = Conv2D(**n_classes**, 1, activation = 'softmax')(conv9)

在這種情況下，在編譯 u-net model 時，損失也應更改為categorical_crossentropy 。

model.compile(optimizer = Adam(lr = 1e-4), loss = 'categorical_crossentropy', metrics = ['accuracy'])

此外，您不應該標准化您的真實標簽/蒙版圖像，而是可以編碼如下：

train_mask = np.zeros((height, width, n_classes))
for c in range(n_classes):
    train_mask[:, :, c] = (img == c).astype(int)

[我假設你有兩個以上真正的 output 類/標簽，因為你提到你的面具包含不同的 colors 用於水、道路、建築等； 如果您只有兩個類，那么您的 model 配置很好，除了 train_mask 處理。]