whyandbecause

Results 11 issues of whyandbecause

Hi,your work is really work for me, but In model zoo, some pretrained models aren't provided, like osnet_ibn_0_5, how can i train it by myself? thank you for you time.

你好,感谢你开源出色的工作,本人在使用代码的过程中有点小疑问。在loss计算输入中,参数为网络输出的特征和label,但是网络输出特征为num_classes个通道,与label的通道不一致,它们为何能计算loss?望解答,谢谢!

hello,will you share the test dataset? thanks

Hello, thanks for your great work, I found all examples implemented in TF codes, Now I want to optimize hyper-parameters on Pytorch. How do I use it?

您好,我在使用MIL_train文件的时候出现如下错误,想请教下是什么问题?谢谢 File "/home/santiago/program/others/anaconda2/envs/guanjuwei/lib/python3.7/site-packages/openslide/deepzoom.py", line 173, in get_tile tile = self._osr.read_region(*args) File "/home/santiago/program/others/anaconda2/envs/guanjuwei/lib/python3.7/site-packages/openslide/__init__.py", line 237, in read_region self._osr, location[0], location[1], level, size[0], size[1] File "/home/santiago/program/others/anaconda2/envs/guanjuwei/lib/python3.7/site-packages/openslide/lowlevel.py", line 311, in read_region _read_region(slide, buf,...

你好,make_dataset文件中直接load了mat文件,想问下mat文件是怎么得到的?谢谢

您好,这个工作特别出色,很有启发意义,我有一点小疑问,论文中提到训练经过了100个epoch,但是我实际训练的时候,大概25个epoch后就收敛了,后面的训练loss和验证mae几乎没变化了,这是什么原因?期待您的解答,谢谢!

您好,请问如何下载clothing1M的数据集,邮件已发送,但未回复

Thank you for your great work. I would like to ask if you can provide the training log as a reference. I would like to find whether the changes of...

Hi, thank you for your great work! How can i train from scratch with other datasets?