xmfbit

@xupeng1125 The first problem. The darknet has two different versions. If `minor==1`, which is the early version, the size of `seen` is 4 bytes. And if `minor==2`, the size of...

@babycamel Thanks for your comment! However, I believe that LuaTex engine is for md-> pdf conversion, not for notebook -> md conversion. Anyway, thanks!

Thanks! I currently don't have motivation to solve this problem. Maybe I will try the solution afterwards. 🤕

OK...I see. You [used one-hot vector as gt_classes](https://github.com/longcw/yolo2-pytorch/blob/master/datasets/pascal_voc.py#L136). But a new question is that: the gradient `(gt_class - prob)` should be passed directly to the output of the final conv-layer...

@tegg89 @Jmx5200 This has nothing to do with YOLO2-Pytorch. You should re-install opencv package. It works well for me. ``` conda remove opencv conda update conda conda install --channel menpo...

下载最新v1.2的话，需要改下名字，例如将其改名为 芝麻开门，这样才能通过Siri芝麻开门唤起

另外需要手动触发一次，允许openai的网络访问权限

I have met the same problem, and how to fix it?

@jonpryai hi, have you solved the problem?

考虑到`forward`只会调用一次，是否可以将上面比较hack的方法直接加入？这样可以避免像我一样因为环境配置产生问题