QiaoranC

Small reminder: In test_net.py, forgot add ``` if args.vis: cfg.VIS = True ``` Now, '--vis' is not working because the missing.

About the train/valide update, i straight add `run inference` from the test into the train after `save_capt`, and add some parser_argument from the test(--output_dir, --range, -- multi-gpu-testing) and add `cfg.TEST.DATASETS...

@roytseng-tw Any ideals/suggestions or something i should looking for ?

I am not sure what your mean `run_inference ` by 1 image per gpu, cause i run test_net.py with 77 test images, each gpu assigned with 39/38 images(based on the...

@roytseng-tw Sorry to bother, but any interest in combine train and val? Or leave me some suggests about this? I just through this project is great/smart at multiple gpus, it...

谢谢作者的解释，这样几个疑问都解释的通了。我目前是希望能基本复现你的结果，然后再对模型进调整。 不过关于疑问2，既然你提到 `layers[i][j]` 来表示重复次数,那为什么block2,block3不直接传4进去？是不是因为size不一样？但是每一个branch下面的block2,blocke3，`kernel_size`不都是一样的吗? 为什么 `size=sizes[i][0]` 而不是 `size=sizes[i]`, sizes不应该是`[3,5,7]`的循环吗?

@RandomWalk-xzq 好的 thanks

Also looking the train code

Hi, you need prove more information, this just not enough give any suggests.

Hi, the pertrain model is indeed a reasonable ask, but i dont have much time/power/gpu to do it, Sorry for that. And welcome to contribute it. As for the time...