Wenhe Jia

@KaiyuYue yes, set a small batch_rois can reduce the GPU usage when training rcnn, but also get a low performance at the end. Check out in repo [https://github.com/LeonJWH/mx-maskrcnn](url).

@tkuanlun350 I want to know whether you have get end-to-end training worked? If you have get it done, can you release you scripts?

I use 4 titan xp(single image per GPU) to alternatively train mask rcnn on cityscape, in step 1(training RPN), it takes 1.2 hour to run 1 epoch, and the usage...

@ypflll All right, it seems my time cost is acceptable.

@ypflll I want to know whether you have got this in your training progress: Is this the reason that slow down the training process? I am not very familiar with...

@ypflll what is your testing time? My time cost of inference process is: > testing 123/500 data 0.1469s net 1.8130s post 0.0143s > testing 124/500 data 0.1440s net 1.7960s post...

@xingyizhou OK, I just use 8 gpus to train ExtremeNet, keeping batch_size=24.

When I trained ExtremeNet with 4 gpus, batch_size=12(3 imags/gpu), the memory usage of 4 gpus are 12GB(almost), 7GB, 7GB, 7GB. That means the model with 3 images takes 7GB gpu...