HRNet-for-Fashion-Landmark-Estimation.PyTorch
HRNet-for-Fashion-Landmark-Estimation.PyTorch copied to clipboard
for catId in catIds} File "/home/sa/anaconda3/envs/torch1.7/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 229, in computeOks e = (dx**2 + dy**2) / vars / (gt['area']+np.spacing(1)) / 2 ValueError: operands could not be broadcast together with shapes (294,) (17,)
训练的时候出现以下错误
for catId in catIds}
File "/home/sa/anaconda3/envs/torch1.7/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 229, in computeOks
e = (dx2 + dy2) / vars / (gt['area']+np.spacing(1)) / 2
ValueError: operands could not be broadcast together with shapes (294,) (17,)
@ShenhanQian
本Repo面向DeepFashion2数据集,其包含294个关键点,因此需要安装DeepFashion2专用的pycocotools
,即deepfashion2_api
。而你使用的是原生的COCO数据集的pycocotools
,其包含17个人体关键点,因此出现这行报错信息:
ValueError: operands could not be broadcast together with shapes **(294,) (17,)**
。
请按照本repo提供的安装方法,正确安装deepfashion2_api
。