Hanwen Cao
Hanwen Cao
Hi, I hope I can help you. But I am not 100% sure. You might want to monitor the run time of https://github.com/dougsm/ggcnn/blob/0c50aa7600e8a30d44c5c85cebd6e3394a81f30e/eval_ggcnn.py#L78 using a python timer.
@aPonza Hi, I was wondering if you have figured it out? I am facing the same error ``` q_am_neigh_avg = np.average(q_am_neigh, weights=neighbour_weights, axis=0) ZeroDivisionError: Weights sum to zero, can't be...
@fkendlessly Sorry man I do not have a perfect solution. One thing you could probably try is to bypass it. I think you can do grasping without that. But forgive...
> 郑博士,你好,请问 > name SE_imbalance_s1_384_p0.5_lr2_mt_d0_b24+v+aug,这个对应哪一块代码,论文哪里提到了?麻烦,谢谢 请问您知道了吗?
> @郑博士 你好。我这边运行train+virtual数据集,当运行到40个Epoch的时候,太慢了,我把它停了,然后跑测试集,但结果rank@5才不到90%,mAP才0.35,这正常吗??会是哪里出错了呢?? 您好@s20163081161,请问您跑的测试集是怎么制作的?我看readme只讲了训练集的制作。谢谢!
您好@s20163081161,打扰了,我在网上申请并得到了所有数据集。您说的mAP的测试代码是submit.py还是test_2020.py?
> test_2020.py。你跑的如何? > […](#) > ---原始邮件--- 发件人: "Hanwen Cao"
https://drive.google.com/file/d/1RAQFT9umi6kTehFRiISu0g9xKI3PScbc/view?usp=sharing
> crop_dir 我用的是MaskRCNN 抠出来的car 类别的图。 对应文章中的image alignment的后处理 > https://github.com/facebookresearch/detectron2 郑博士您好 @layumi ,请问您的意思是crop操作不包含在这个respo里,而是需要自己额外手动扣吗?谢谢~ 另外test_dir是怎么来的呢?
> @HanwenCao > 是用detectron的模型来crop的。 谢谢郑博士 @layumi ,请问test_dir,就是./data/test_data,是怎么prepare出来的?