资源分类
》 资源 》算法》 SSD_mobilenetv2-with-Focal-loss

SSD_mobilenetv2-with-Focal-loss

2020-02-27 | |  44 |   0 |   0

SSD_mobilenetv2-with-Focal-loss

this repo is forked from https://github.com/amdegroot/ssd.pytorch. Implemented by pytorch.

Contributions:

  1. implement mobielentv2 for ssd.

  2. add focal loss. (need adjuct super-parameters).

  3. add detection.py demo for image and video detection.

result(train on voc 2007trainval + 2012, test on voc 2007test):

  1. ssd-mobielnetv2 (this repo): 70.27%. (without focal loss).

  2. ssd-mobielentv1: 68.% (without COCO pretaining), 72.7% (with COCO pretraining) https://github.com/chuanqi305/MobileNet-SSD.

  3. ssd-vgg16 (paper): 77.20%.

pretrained model and trained model:

  1. 百度网盘: https://pan.baidu.com/s/1RmOPF4jQYpYlE_8E4DifeQ 提取码: f53n

  2. Google drive: https://drive.google.com/drive/folders/1JoDYukyWZZ-iWVWPhUDD998cSPB3LeUw?usp=sharing


上一篇：Pruned-MobileNet_v2

下一篇：Caffe-MobileNetV2-ReLU6

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...