Comments (5)
CENTER_VARIANCE, SIZE_VARIANCE 在代码中的应用在编码和解码这两个部分。
Line 34 in cdf7076
理解编码和解码的作用,就比较好理解这个参数了。
编码的输入,是标注框与检测框(anchor,代码中是prior),以及这两个参数, 然后编码的结果拿去计算损失。
编码的输出,分别是中心偏移,以及尺寸差异。 对中心偏移和尺寸差异 分别除以这两个参数,实际上的作用,就是对中心和尺寸的损失贡献做一个平衡。
像这里,中心偏移/0.1, 尺寸差异/0.2 ,意味着相对于尺寸,更加关注预测结果的中心。
至于 PIXEL_MEAN, PIXEL_STD 就是你说的整个数据集的均值和方差。
欢迎关注,有什么问题可以随时问我
from ssd-pytorch.
控制中心落点和尺寸的损失影响,其实可以在损失函数中更加简便的实现。
但SSD原文是这么实现的
from ssd-pytorch.
CENTER_VARIANCE, SIZE_VARIANC这两个参数受什么的影响呢?是输入图片的尺寸,还是说与数据集中目标的大小?还是其它什么因素?
from ssd-pytorch.
如果CENTER_VARIANCE 比SIZE_VARIANC小,则 中心偏移对损失的影响较大; 反之,则预测框尺寸随损失影响较大。
看你最终更加侧重哪方面。
对这个参数的理解,类似于torch.nn.cross_entropy()中的weights参数
from ssd-pytorch.
好的,谢谢你的解释!非常感谢您!
from ssd-pytorch.
Related Issues (16)
- 你好,请问fps能达到多少 HOT 4
- "Invalid device id" HOT 1
- center_form_to_corner_form HOT 2
- 请问我想尝试修改iou阈值,但是修改了config里面的_C.MODEL.ANCHORS.THRESHOLD和 修改voc_cal_ap.py但是训练时ap没有变化,请问应该在哪里可以修改iou阈值,我是个新手小白,麻烦您解答。
- hard_negative_mining
- 遇到了一个问题,想问下解决方案
- 希望训练支持CPU训练 照顾照顾 没有显卡的弟弟们 HOT 1
- 超过迭代次数但是还在运行
- ImportError: cannot import name 'int_classes' from 'torch._six'
- 您好 请问我单独取出VOC的两个类别训练 HOT 1
- 请问1080Ti下需要训练多长时间,我稍微改了一下训练了两天发现还没收敛,loss大于2
- 求数据集来源 HOT 2
- gpu利用率特别低 HOT 4
- 精确度
- 训练无法达到作者给的模型精度 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ssd-pytorch.