About "seg_label":

[xu19971109]

The new annotation file provided by BDD100K provides the mask map directly, while YOLOP author handles json file——gen_bDD_seglabel.py with different filling values from the mask map generated by the official.I don't have the old annotations, how can I haddle the AutoDriveDataset.py with mask?

if self.cfg.num_seg_class == 3:
_,seg0 = cv2.threshold(seg_label[:,:,0],128,255,cv2.THRESH_BINARY) # 二值分割
_,seg1 = cv2.threshold(seg_label[:,:,1],1,255,cv2.THRESH_BINARY)
_,seg2 = cv2.threshold(seg_label[:,:,2],1,255,cv2.THRESH_BINARY)
else:
_,seg1 = cv2.threshold(seg_label,1,255,cv2.THRESH_BINARY)
_,seg2 = cv2.threshold(seg_label,1,255,cv2.THRESH_BINARY_INV)
_,lane1 = cv2.threshold(lane_label,1,255,cv2.THRESH_BINARY)
_,lane2 = cv2.threshold(lane_label,1,255,cv2.THRESH_BINARY_INV)

用官方给的mask图做这个分类的时候好像有点问题，作者原来的json处理方式其中一些字段又和现在的json字段不同，处理不成作者需要的那种mask结果，有没有朋友知道怎么处理这一块啊

[LuthraBhomik]

for seg_label and lane_label, YOLOP code is picking up these from the mask maps already provided. Do you want to create mask maps again ? It is not picking up the masks from the json, only the path is being used from json.