train VGG-SSD from scratch get a better result

[ujsyehao]

Hi, I follow your experiment setting, train VGG-SSD from scratch(no pretraining, no BN in the backbone, no BN in the head), use the following hyper param(caffe):

• train batch size: 32, iter: 1, test batch size: 8
• base_lr: 0.001
• max_iter: 120000
• type: SDG
• weight_decay: 0.0005
• gamma: 0.1

At 110k iterations, I get 68.8% mAP, It is higher than 67.6% mAP(paper reported).

[CHKswiftly]

Can your share your VGG-SSD code with me? there is some problems with the code which i want to repeat,