Object-Detection-Evaluation-Tool
Object-Detection-Evaluation-Tool copied to clipboard
demo
大佬,跑你的demo,都有问题:
Num of prediction files: 729
Num of ground truth files: 721
groundtruths' size does not match predictions' size, please check ~
Traceback (most recent call last):
File "test.py", line 70, in
你这数据有问题啊,prediction 和我ground truth 数量都不一样。检查下吧。
--------------原始邮件-------------- 发件人:"dreamhighchina "[email protected]; 发送时间:2019年10月11日(星期五) 上午10:58 收件人:"wangzhe0623/Object-Detection-Evaluation-Tool" [email protected]; 抄送:"Subscribed "[email protected]; 主题:[wangzhe0623/Object-Detection-Evaluation-Tool] demo (#2)
大佬,跑你的demo,都有问题: Num of prediction files: 729 Num of ground truth files: 721 groundtruths' size does not match predictions' size, please check ~ Traceback (most recent call last): File "test.py", line 70, in eval.run() File "/home/112831/code/tools/Eval_object_detection-master/evaluation.py", line 272, in run prediction_path, gt_path, predictions, groundtruths, file_format = self.load_all_files() TypeError: cannot unpack non-iterable int object
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.
大佬,我用的是你的数据,我什么都没有改,求大佬指教下
要不大佬你下载这个跑跑,是不是后来修改了,我就下载了你的,然后什么都没有动,包括数据。
大佬可以了,删除了里面几个空的文件就好了
大佬,这两个参数的含义是什么?? overlapRatio': 0.5, 'threshold': 0.5,
@wangzhe0623 兄弟,overlapRatio是ground truth和预测框的IOU;threshold是置信度阈值,prec和rec就是在这个阈值下计算的。