Comments (4)
你好, 设计是根据文章来的. 这里没有使用扩大的anchor,是因为anchor和gt box同时扩大是等价的
from pyramidbox.
谢谢你的回答.
我能不能这么理解:
这是一个同步过程,要么gt和anchor都扩大,要么gt和anchor都不动
比如:正常来说,head_anchor需要扩大,对应的根据paper,对应的head_gt也要扩大(这点paper明确说明,而且给出了扩大方法).
而你在code中,并没有会head_gt进行扩大,那么对应的head_anchor也就没有进行相应的扩大.
这样的理解对吗??
还有1点:
第1个head_anchor是(4,4,16,16)
第1个face_anchor是(2,2,16,16)
自认为2者的中心点应该保持一直吧.你code中却发生了变化.为什么这么做呢?
from pyramidbox.
发生了微小的偏移对结果影响不大,关于对gt 和 anchor 的理解是正确的.
from pyramidbox.
@Goingqs
谢谢!!
from pyramidbox.
Related Issues (20)
- shape error
- augmentations error HOT 1
- No such file or directory: '/home/guoqiushan/share/face_box/wider.list' HOT 1
- Cannot use the model HOT 1
- Anyone can get the result comparable to the model released? HOT 1
- shape error HOT 2
- Where can I download the original res50 weights?
- Please add a dropbox link for download as well
- @Goingqs I test the model on V100 machine, but got about 200ms/pic, single scale, and the test time is not stable, floating in 100ms to 700ms, any suggestion? HOT 4
- Size supporting HOT 1
- what gamma should be in learning rate decay HOT 2
- pytorch 0.3.1 runs well
- when I would like to test ,I got the error like this AttributeError: 'NoneType' object has no attribute 'shape' andcan you help me?
- RuntimeError: expected type torch.cuda.FloatTensor but got torch.FloatTensor HOT 2
- RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /opt/conda/conda-bld/pytorch_1549635019666/work/aten/src/THC/THCGeneral.cpp:51
- when i test ,RuntimeError: CUDA out of memory. Tried to allocate 10.62 MiB (GPU 0; 5.77 GiB total capacity; 4.84 GiB already allocated; 2.69 MiB free; 109.45 MiB cached
- annoPath
- test AP
- Error in layers/functions/box_utils 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 pyramidbox.