feynman

https://gluon-cv.mxnet.io/build/examples_detection/finetune_detection.html shall fix this issue.

It seems that the https://gluon-cv.mxnet.io/build/examples_detection/finetune_detection.html fixed this issue.

check this issue: https://github.com/keras-team/keras/issues/450 for more details. The root cause is that `steps_per_epoch = 0`, as mentioned in https://github.com/Hironsan/BossSensor/issues/17#issuecomment-312389567.

BTW, this issue has been fixed by https://github.com/keras-team/keras/pull/8854. Use the latest codes of keras shall fix this issue.

@soulteary Thanks for your tutorial. Just for remind, it seems that `echo '' > xformers/requirements.txt` is missed in your comment.

> Its offline. For maintenance reason @xavier114 thanks for your great work. Will the server be back online? If not, is there an alternative method to obtain the data? Thanks.

It seems that the mmcv 1.7.2 supports `jit` in mmcv while the newer mmcv only supports `jit` in mmcv.utils.   Replace `@mmcv.jit` with `@mmcv.utils.jit`.

看起来像是pytorch安装问题？应该跟这个repo无关。 既然使用conda安装相应包，可以从conda运行环境入手，查看当前运行环境是否为自己希望的环境，是否正确安装pytorch包。

不确定是否与你的环境有关，我在ios(iphone se)上跑到350分，如不手动停止应该可以得更高的分数。 而且，作者在知乎上提供的图显示可以跑到2254分。 不如你提供下你的环境配置，以及log，看看是不是哪里有些问题

> Before the error, you can see the terminal mentioned that colmap is not installed. So you need to install colmap first. I compile the colmap and install it. @Fishsix20236356...