search

svip-lab / HRNet-for-Fashion-Landmark-Estimation.PyTorch

[DeepFashion2 Challenge] Fashion Landmark Estimation with HRNet
MIT License
132 stars 22 forks source link

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,) #13

Open APeiZou opened 2 years ago

APeiZou commented 2 years ago

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

ShenhanQian commented 2 years ago

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。