We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
采用 VGG16 的基础网络结构,使用前面的前 5 层,然后利用 astrous 算法将 fc6 和 fc7 层转化成两个卷积层。再格外增加了 3 个卷积层,和一个 average pool层。不同层次的 feature map 分别用于 default box 的偏移以及不同类别得分的预测,最后通过 nms得到最终的检测结果。
SSD is an unified framework for object detection with a single network.
use_depthwise options for both box_predictor and feature_extractor
正样本 / 负样本 根据Feature map 确定Default Box 匹配ground truth 选择IOU 最大和 IOU>0.5 的作为候选正样本集, 其他的作为候选负样本集。 将每一个GT上对应prior boxes的分类loss 进行排序,选取loss 较低的样本作为正负样本。
The text was updated successfully, but these errors were encountered:
#213 #85
Sorry, something went wrong.
No branches or pull requests
SSD Single Shot MultiBox Detector
Reference
Brief
采用 VGG16 的基础网络结构,使用前面的前 5 层,然后利用 astrous 算法将 fc6 和 fc7 层转化成两个卷积层。再格外增加了 3 个卷积层,和一个 average pool层。不同层次的 feature map 分别用于 default box 的偏移以及不同类别得分的预测,最后通过 nms得到最终的检测结果。
训练过程
样本选取
正样本 / 负样本
根据Feature map 确定Default Box 匹配ground truth 选择IOU 最大和 IOU>0.5 的作为候选正样本集, 其他的作为候选负样本集。
将每一个GT上对应prior boxes的分类loss 进行排序,选取loss 较低的样本作为正负样本。
Term
The text was updated successfully, but these errors were encountered: