Skip to content
New issue

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

关于caffemodel faster-rcnn转tmfile后,结果的精度问题 #1205

Open
TRQ-UP opened this issue Nov 5, 2021 · 0 comments
Open

关于caffemodel faster-rcnn转tmfile后,结果的精度问题 #1205

TRQ-UP opened this issue Nov 5, 2021 · 0 comments

Comments

@TRQ-UP
Copy link

TRQ-UP commented Nov 5, 2021

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,
image
image
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
image
对比bbox_pred(shape:300
8)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
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant