Joshua Z. Zhang

Guys, I've uploaded a new resnet50, see if it works for you. Next one is inceptionv3. BTW, the updated vgg model is still not good enough. I will revisit back...

@BunnyShan It's basically the standard arguments. ``` python train.py --gpus 0,1,2,3 --network resnet50 --lr 0.004 --freeze '' --data-shape 512 ```

@BunnyShan I have some idea to tune the configs for models with smaller input size, will need to verify that.

@BunnyShan Fixed https://github.com/zhreshold/mxnet-ssd/commit/e7cc662f3d0ce29e10670f60a8cfcce854036780

@nopattern mAP is no longer an issue in https://github.com/dmlc/gluon-cv I admit that data aug is quite tricky and prune to change, that's why I am not developing using C++ iterator...

"Different from caffe-ssd"??

@315386775 It's basically the same, just use smaller relative size

Use export MXNET_ENGINE_TYPE=NaiveEngine to disable mutli-threading first.

I guess due to the mxnet execute engine, you may not be able to stop anywhere you want. And I would like to know a elegant way to debug as...

@piiswrong @szha