ERROR:root:Error processing image while training Mask-RCNN - machine-learning

Question

I need to train a MASK-RCNN. But when I start the training, I got the following error message:
ERROR:root:Error processing image {'id': 'ISIC_0010064.jpg', 'source': 'lesion', 'path': '/home/mine/Desktop/ISIC2018/ISIC2018_inputs/ISIC_0010064.jpg'}
Traceback (most recent call last):
File "/home/mine/.virtualenvs/cv/lib/python3.6/site-packages/mask_rcnn-2.1-py3.6.egg/mrcnn/model.py", line 1709, in data_generator
use_mini_mask=config.USE_MINI_MASK)
File "/home/mine/.virtualenvs/cv/lib/python3.6/site-packages/mask_rcnn-2.1-py3.6.egg/mrcnn/model.py", line 1265, in load_image_gt
class_ids = class_ids[_idx]
IndexError: invalid index to scalar variable.
I've already changed the number of classes, change more parameters in config, but the error persists.
There is my code:
DATASET_PATH = "/home/enacom/Desktop/ISIC2018"
IMAGES_PATH = os.path.join(DATASET_PATH, "ISIC2018_inputs")
MASKS_PATH = os.path.join(DATASET_PATH, "ISIC2018_ground_truth")
IMAGES_PATH = sorted(list(paths.list_images(IMAGES_PATH)))
idxs = list(range(0, len(IMAGES_PATH)))
random.seed(42)
random.shuffle(idxs)
i = int(len(idxs) * 0.8)
trainIdxs = idxs[:i]
valIdxs = idxs[i:]
CLASS_NAMES = {1: "lesion"}
COCO_PATH = "mask_rcnn_coco.h5"
LOGS_AND_MODEL_DIR = "lesion_logs"
class LesionBoundaryConfig(Config):
NAME = "lesion"
GPU_COUNT = 1
IMAGES_PER_GPU = 1
STEPS_PER_EPOCH = len(trainIdxs)
VALIDATION_STEPS = len(valIdxs) # doesnt suport low values
NUM_CLASSES = len(CLASS_NAMES) + 1
DETECTION_MIN_CONFIDENCE = 0.75
IMAGE_MIN_DIM = 128
IMAGE_MAX_DIM = 1024
class LesionBoundaryDataset(Dataset):
def __init__(self, imagePaths, classNames, width = 1024):
super().__init__(self)
self.imagePaths = imagePaths
self.classNames = classNames
self.width = width
def load_lesions(self, idxs):
for (classID, label) in self.classNames.items():
self.add_class("lesion", classID, label)
for i in idxs:
imagePath = self.imagePaths[i]
filename = imagePath.split(os.path.sep)[-1]
self.add_image("lesion", image_id=filename, path = imagePath)
def load_image(self, image_ID):
p = self.image_info[image_ID]["path"]
image = cv2.imread(p)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = imutils.resize(image, width=self.width, height=self.width)
return image
def load_mask(self, image_id):
info = self.image_info[image_id]
filename = info["id"].split(".")[0]
annot_path = os.path.sep.join([MASKS_PATH, "{}_segmentation.png".format(filename)])
annot_mask = cv2.imread(annot_path)
annot_mask = cv2.split(annot_mask)[0]
annot_mask = imutils.resize(annot_mask, width=self.width, inter = cv2.INTER_NEAREST)
annot_mask[annot_mask > 0] = 1
# function to take unique ids
class_ids = np.unique(annot_mask)
# remove the id 0 because we should ignore the background
class_ids = np.delete(class_ids, [0])
masks = np.zeros((annot_mask.shape[0], annot_mask.shape[1], 1),
dtype="uint8")
for (i, class_ids) in enumerate(class_ids):
class_mask = np.zeros(annot_mask.shape, dtype="uint8")
class_mask[annot_mask == class_ids] = 1
masks[:, :, i] = class_mask
return (masks.astype("bool"), class_ids.astype("int32"))
mode = "training"
train_dataset = LesionBoundaryDataset(IMAGES_PATH, CLASS_NAMES)
train_dataset.load_lesions(trainIdxs)
train_dataset.prepare()
val_dataset = LesionBoundaryDataset(IMAGES_PATH, CLASS_NAMES)
val_dataset.load_lesions(valIdxs)
val_dataset.prepare()
config = LesionBoundaryConfig()
config.display()
aug = iaa.SomeOf((0, 2), [
iaa.Fliplr(0.5),
iaa.Fliplr(0.5),
iaa.Affine(rotate=(-10, 10))
])
model = MaskRCNN(mode, config = config, model_dir=LOGS_AND_MODEL_DIR)
model.load_weights(COCO_PATH, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc","mrcnn_bbox", "mrcnn_mask"])
model.train(train_dataset, val_dataset, epochs=20,
layers="heads", learning_rate=config.LEARNING_RATE /10, augmentation=aug)
I just want a resolution to make my training works. I've searched before post here, but I couldn't found any solution.