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
参照v1.12.0版本中的faster-rcnn修改了rpn层的参数 layer { name: "proposal" type: "RPN" bottom: "rpn_cls_prob_reshape" bottom: "rpn_bbox_pred" bottom: "im_info" top: "rois" rpn_param { feat_stride : 16 basesize : 16 scale : 8 scale : 16 scale : 32 ratio : 0.5 ratio : 1 ratio : 2 boxminsize :16 per_nms_topn : 6000; post_nms_topn : 300; nms_thresh : 0.7 }
但是结果和pc运行的差别较大,不知道怎么去debuge这个问题。 模型如下, 具体结果对比如下: 对比cls_prob(shape:3002):前30个数据出入比较大,后570个数据相同要么是0或者1 对比bbox_pred(shape:3008)回归的坐标坐标位置差别较大,有些是数值对比较大,有些已经是正负号的差别
The text was updated successfully, but these errors were encountered:
No branches or pull requests
参照v1.12.0版本中的faster-rcnn修改了rpn层的参数
layer {
name: "proposal"
type: "RPN"
bottom: "rpn_cls_prob_reshape"
bottom: "rpn_bbox_pred"
bottom: "im_info"
top: "rois"
rpn_param {
feat_stride : 16
basesize : 16
scale : 8
scale : 16
scale : 32
ratio : 0.5
ratio : 1
ratio : 2
boxminsize :16
per_nms_topn : 6000;
post_nms_topn : 300;
nms_thresh : 0.7
}
但是结果和pc运行的差别较大,不知道怎么去debuge这个问题。
![image](https://user-images.githubusercontent.com/37291715/140471415-2e6d96da-0740-4699-9e95-eeee96dd4a10.png)
![image](https://user-images.githubusercontent.com/37291715/140471444-36da6911-75f1-4598-a406-1e95f0644d41.png)
![image](https://user-images.githubusercontent.com/37291715/140471526-c44fc9b4-6470-4834-870a-927e86806d29.png)
![image](https://user-images.githubusercontent.com/37291715/140471576-a3df8817-80ec-4282-af81-c472d05295b2.png)
模型如下,
具体结果对比如下:
对比cls_prob(shape:3002):前30个数据出入比较大,后570个数据相同要么是0或者1
对比bbox_pred(shape:3008)回归的坐标坐标位置差别较大,有些是数值对比较大,有些已经是正负号的差别
The text was updated successfully, but these errors were encountered: