-
您好,在代码运行中发现以下情况:使用train.py训练的过程中的评价指标数值与其所保存权重使用test.py得到的评价指标具有较大偏差,检查代码发现在训练与测试过程中项目使用了两组不同的评价指标计算代码,且在训练阶段似乎是使用RGB图像进行评价而在测试阶段使用灰度图像进行评价(在自述文件中有提到)。请问这样的设计是否会对结果产生影响?并且在test.py中同样使用RGB图像进行评价后两阶段得到的…
-
没有对源码进行修改, 只是把feature!=None改成了feature is not None,得到的结果文件用compute_ap单独测试过,也确实是0 ,请问可能出现什么问题了?
-
Hi, I have read the detector.c code and it seems that the mAP calculation when using ./darknet detector map ... calculates the old mAP metric (calculating the precision for recall values of 0.1, 0.2, …
gnoya updated
2 years ago
-
I use the released code without problem before updating. Now, I notice that the codes are updated newly. So I can not wait to try it, and successfully run the python setup.py install. Then when I run …
-
Hi,
Wonderful work, thanks for sharing the code. Could you please, share the script to split the original ObjectNet dataset into train, and test according to the filenames you provided?
Thanks !…
-
Hi,
I have some observations on the coco metrics, specially the precision metric that I would like to share.
it would be great if some could clarify these points :) /cc. @pdollar @tylin
for c…
-
您好,我是来自北航计算机的一名本科大四生,去年读了您CVPR2023的工作之后觉得非常有趣,想尝试复现的时候发现自己的编程能力有些欠缺了,很开心最近能在github找到您的开源,但我目前在google scholar和IJCV在springer下的网站(https://link.springer.com/journal/11263/articles)都没找到您的IJCV文章,请问您IJCV的工作(…
-
I am glad to see your work, and I also hope that the work in IJCV can be smoothly accepted. I have some questions about the paper 'Generalized UAV Object Detection via Frequency Domain Disentanglement…
-
hi, The following error occurs in the means = self.fc1(data), RuntimeError: size mismatch, m1: [1 x 25088], m2: [18432 x 100] at c:\a\w\1\s\tmp_conda_3.7_110206\conda\conda-bld\pytorch_1550401474361\…
-
Dear Hiroaki Santo,
Would it be possible to have access to some real data, e.g. the ones used in the IJCV paper ?
Thanks in advance,
Yvain Queau