Comments (5)
@Durobert
The values of 1640./25
and 32./534*590
are the offset of test-time-augmentation (TTA).
During TTA, we would first shift the image, and get the prediction of the shifted image. Then we inverse-shift the prediction of the shifted image to get the correct prediction. In this way, a TTA is finished.
For example, if we shift the image to the left for x
pixels, then the predicted coordinates should add x
as well. The difference is that we shift the image in the strided feature map. If the feature map's width is 25
, then we shift the feature by 1 pixel means image width * 1 / 25
pixels in the original image space, which is the derivation of 1640./25
(1640 is the image width on CULane).
The values of 32./534*590
is similar, but this part contains a crop operation.
from ultra-fast-lane-detection-v2.
@cfzd
For the CULane, you resize the image to 1600*320, I use the backbone resnet18, The downsampling multiple is 32,so the feature map's width is 1600/32=50,the value is 1640./50, is right?
from ultra-fast-lane-detection-v2.
@Durobert
It should be correct. In fact, another interesting point is that: if you always do TTA both in the opposite directions with the same shift, you can directly average the shifted predictions together without offset and get the correct results. Since (pred - offset) + (pred + offset) = 2*pred
.
from ultra-fast-lane-detection-v2.
@cfzd
Another problem, about the value 32./534 * 590,For the CULane,the crop_ratio is 0.6,so the resized image height is 320/0.6=534, the value 32./534 * 590 means the croped image height is 32, is right?If I don't crop, the value is 0?
from ultra-fast-lane-detection-v2.
@Durobert
The offset with the crop operation is a little tricky, and sorry I have forgotten the derivation details. However, the core idea is the same, and it is just to make sure the shift prediction is correct.
If you don't crop, it is the same as the logic of 1640./25
. For example, suppose the height of the feature map is hf
, the height of original image is hi
, the number of shifted pixels is x
, then the offset is: x/hf * hi
.
from ultra-fast-lane-detection-v2.
Related Issues (20)
- how to label for data
- 关于数据集转换
- 如何测试 论文中的 time 和fps
- 弯道的优化思路 HOT 1
- 根据CULane做测试的时候,训练莫名被killed HOT 6
- 无法生成culane_anno_cache.json文件 HOT 7
- 自己的dataset的__getitem__使用my_interp,出现re-initialize CUDA in forked subproces的问题
- 训练过程中会找不到一个文件
- 能否像V1那样使用辅助分支的方法训练
- 当我启用了SegHead结构后,就发生了报错。 HOT 2
- 更改输入网络的图片大小之后还有哪些需要修改 HOT 1
- curvelanes HOT 1
- Tusimple数据集问题
- 请问是否能够读取摄像头画面并实时进行预测呢?该如何设置? HOT 2
- python test.py python test.py configs/culane_res18.py --test_model --test_work_dir 时报错:No such file or directory: 'list/test.txt' HOT 1
- cuda installation
- Some raw file doesn't exist
- CULane data error
- demo.py for curvelane
- Calculating TN and TP for TuSimple
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 ultra-fast-lane-detection-v2.