Comments (2)
Hi @foralliance
(1) code,paper中都是分了三个分支,通过堆叠层数和dilation的设置,不同的分支其实会有不同的dilation系数。
(2) 是的,一阶段模型中,多尺度测试融合能极大的提升性能,multi_scale_test_pyramid比multi_scale_test测试尺度多,结果好。
(3)可以可视化一下看看结果。其原因是:图片缩小目的是为了检测大目标,因而不需要关心小于30的物体,那些小于30的那些目标就交由放大测试操作进行检测。否则会引入误检。
(4)这个在测试脚本里面应该有体现,write_to_txt函数里面。
(5)在350,351,352三行代码有体现。
from facedetection-dsfd.
@lijiannuist
谢谢您的回复.
对于第5点:
根据350,351,352三行代码的设置,
self.face_priors生层6组anchors,对应尺度[16, 32, 64, 128, 256, 512],对应6个分支p0-p5.
self.head_priors生层5组anchors,对应尺度[16, 32, 64, 128, 256],对应5个分支p1-p5.
self.body_priors生层4组anchors,对应尺度[16, 32, 64, 128],对应4个分支p2-p5.
根据PyramidBoxFig4的描述:p0上16的face,对应p1上32的head,对应p2上64body.所以,自认为,self.head_priors对应的尺度应该是[32, 64, 128, 256, 512],self.body_priorss对应的尺度应该是[64, 128,256, 512].
所以说应改为:
self.face_priors = self.init_priors(self.cfg)
self.head_priors = self.init_priors(self.cfg , min_size=cfg['min_sizes'][1:], max_size=cfg['max_sizes'][1:])
self.body_priors = self.init_priors(self.cfg , min_size=cfg['min_sizes'][2:], max_size=cfg['max_sizes'][2:])
不知道自己的理解对不?
from facedetection-dsfd.
Related Issues (20)
- how about the eval_tools? HOT 1
- Add 'configuration' files to install requirements easily
- TypeError: mul(): The parameter'other' (position 1) must be Tensor, not numpy.ndarray
- Excuse me, how to train the network? I don't seem to see the code about the training model
- How can we use webcam to test our DSFD model.
- FileNotFoundError: [Errno 2] No such file or directory: '/data/wider_face_split\\wider_face_val.mat' HOT 2
- [SOLVED] How to Implement DSFD on Windows, Mac, and Linux HOT 9
- [SOLVED] How to Implement DSFD on Windows, Mac, and Linux
- RandomBaiduCrop
- How do I test multiple images using Demo.py HOT 1
- TypeError: can't convert cuda:0 device type tensor to numpy. HOT 1
- Error in running demo.py
- demo.py RuntimeError: Legacy autograd function with non-static forward method is deprecated. HOT 2
- TypeError: forward() missing 1 required positional argument: 'x' HOT 5
- How do I test the video in the demo.py?
- GPU out of memory HOT 1
- Fix RuntimeError: Legacy autograd function with non-static forward method is deprecated
- training code
- Legacy autograd function with non-static forward method is deprecated.
- 论文里SSL损失函数公式最外面那个括号是不是放错位置了
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 facedetection-dsfd.