Open ysh329 opened 6 years ago
@ysh329 I train squeezenet-ssd without pretrained weights, and get mAP 64.4
@ujsyehao eh, great! 👍 What's your optimization method? Is over-fitting?
just SGD, no over-fitting
@ujsyehao I think if pretrained model used, higher mAP and faster convergence are possible.
@ysh329 yeah.
chuanqi305/MobileNet-SSD: Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727. https://github.com/chuanqi305/MobileNet-SSD
chuanqi305/MobileNetv2-SSDLite: Caffe implementation of SSD detection on MobileNetv2, converted from tensorflow. https://github.com/chuanqi305/MobileNetv2-SSDLite
chuanqi305/SqueezeNet-SSD: SSD detection network of SqueezeNet, with pretrained weights on VOC0712 and mAP=0.643 https://github.com/chuanqi305/SqueezeNet-SSD