JiaLim98

Hi @EMCP, thank you so much for the help! Much appreciated!

Hi @alontrais @cskarthik7 @Drifter02 @RebornL, Has anyone got the solution? I have tried to recompile torch 0.4.0 with torchvision 0.2.0 and CUDA-10.1 as I'm using Google Colab. I have also...

@SkeletonOne I have not overcome this issue. I am still struggling to get this repo working. If you can get it to work, please let me know.

@hanhao2019102935 No, I did not manage to solve it. If you find any solution in the future, feel free to post here. I think a lot of people are facing...

@QQ2737499951 您好，我需要使用faster rcnn训练自己的数据。QQ现在有些问题我注册不了。请问你可以把可使用的文件全发到一个链接吗？如果不方便透露数据，可以帮帮忙拿出您的数据再发吗？之后我再试试下载后把我的数据依次放进每个文件并修改一些码试试看能不能使用。 本人已经试了好多方法，也觉得他们的教学好复杂。希望能得到您的教导。只是个初学者。。。

@xiaozhangya 你好，请问可以教我如何跑通吗？您有创建Colab程序吗？您是使用什么PyTorch的版本?

Thanks for the reply. For anyone who wants to output class-wise mAP, this is the most straightforward way I found. The mAP for entire model is calculated from the average...

Hi @yangyang117, My final accuracy (without finetuning) are: [email protected] = 92.02% and [email protected]:0.05:0.95 = 40.60% Hope it helps.

It is an open-sourced PCB defects dataset.

您可以检查文件目录是否确实存在. 对于第一次训练，这个问题不应该存在.