Comments (2)
As an added on, looks this issue only happens with supervised:Ture(SS-DCNet),
and training the S-DCNet version do not have such issue.
supervised: False
True for the Supervised S-DCNet (SS-DCNet)
False for the older version (unsupervised, ordinary S-DCNet)
Thanks
from s-dcnet.
Hi,
essentially, only batch size == 1 is supported. The reasons for that are:
- The input images have different resolutions;
- After the augmentations that change the input sample resolution (QuasiRandomCrop and PadToMultipleOf64 in ShanghaiTech_dataset.py) the samples still have different resolutions.
No preprocessing is done in order to make the samples have the same resolution. It would complicate preprocessing and significantly reduce the meaningful part of a sample area.
Consider a case when you have two input images, the 1st one has landscape orientation, and the 2nd one has portrait orientation. How can we make them have the same resolution in order to put them into the same batch? Simple resizing that changes aspect ratio is not allowed (because of the nature of the problem -- the network should always see the same natural aspect ratio of people's bodies and heads). The only option would be to choose an excessive frame size that would cover both input images simultaneously and pad the images by zeros to fit them to the chosen excessive frame size. In that case, the meaningful parts of the images become relatively small and the network forward pass time increases. I decided not to deal with such negative effects. This issue can be even more pronounced if there are, say, 4 images that you want to put into the same batch.
from s-dcnet.
Related Issues (14)
- error creating density map HOT 24
- convert model to tensorrt HOT 2
- batchsize==1? HOT 1
- Count method is different from the original code in testing HOT 2
- Changing batch size HOT 1
- Why your error rate is higher than original paper? HOT 4
- EOFError: Ran out of input HOT 10
- RuntimeError: GPU out of memory HOT 5
- epoch size
- SSDCNet or SDCNet HOT 2
- Self Dataset HOT 2
- Training on multiple GPUs? HOT 1
- Could you please provide the way to get bounding box of each person ? 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 s-dcnet.