TypeError: 'NoneType' object is not subscriptable

[Catofblue]

I downloaded the Pascal VOC2012 datase and I make sure that the path of the dataset file and the location of the segmentationclassaug file are correct and printed correctly

The code in line #80 under the folder voc_train.py does not runing

    #78    mask_path = self.mask_dir + name + '.png'
   #79      mask = cv2.imread(mask_path)
   #80      labels = np.unique(mask[:,:,0])

[wn-device]

Please make sure there is no Chinese in the path,then sloved

[Catofblue]

ok,thanks, I have solved the problem, but I don't understand what this code means：
labels = np.unique(mask[:,:,0])

        labels = [label - 1 for label in labels if label != 255 and label != 0]
        if set(labels).issubset(self.train_id_list):
            new_exist_class_list.append([name, class_])

[JmZhang2021]

I had the same problem. How did you solve it, please？

[Yang-Bob]

Hi,
Sorry for replying so late.

1. 'NoneType' means the data is empty. I think that you could check if the data or data path is correct.
2. 'labels = np.unique(mask[:,:,0])' is used to search what semantic classes are in the image. Since the annotated mask in semantic segmentation is pixel-level annotation, thus, we should remove the duplicated pixel mask value to find the unique labels. After that, the labels are used to judge whether this image should be involved in the training set, according to the training id, to follow the few-shot learning setting.

[JmZhang2021]

Hi, Sorry for replying so late.

1. 'NoneType' means the data is empty. I think that you could check if the data or data path is correct.
2. 'labels = np.unique(mask[:,:,0])' is used to search what semantic classes are in the image. Since the annotated mask in semantic segmentation is pixel-level annotation, thus, we should remove the duplicated pixel mask value to find the unique labels. After that, the labels are used to judge whether this image should be involved in the training set, according to the training id, to follow the few-shot learning setting.

Thanks so much！I had already solved it~