Comments (6)
Thanks to your quick replay!
The mistake you point out is indeed the cause that 'LM', that means loss for js regularisation, increases during the training process
tmpOutMap = self.tmpOut[i](ll) heatmaps = dsntnn.flat_softmax(tmpOutMap) outMap.append(tmpOutMap) # <-- Should be
outMap.append(heatmaps)?
But the problem still unresolved is that 'LR', that means Euclidean loss for the numerical coordinates, keeps coverging very slowly. And of course, the performance is still bad.
I think I need go deeper for some other bugs.
Thanks for your answer again!
from dsntnn.
Hi @anibali Thanks for the response, I found the bug, it's indeed on my side. Thanks for this awesome work.
from dsntnn.
One potential problem I can see is this:
tmpOutMap = self.tmpOut[i](ll)
heatmaps = dsntnn.flat_softmax(tmpOutMap)
outMap.append(tmpOutMap) # <-- Should be `outMap.append(heatmaps)`?
You seem to be adding the non-softmaxed version of the heatmap to outMap
, which means that you end up applying the JS regularisation to the non-normalised heatmaps.
from dsntnn.
@Hellomodo @anibali Hi, have you found the bug? I used this layer in another task, and the loss for numerical coordinates doesn't decrease at all.
from dsntnn.
@sunshineatnoon I currently don't have any reason to believe that there's a bug in dsntnn
. It's more likely that the bug is in your usage or your other code. If I'm wrong and you do manage to narrow down the problem to dsntnn
with a minimal example, please feel free to open a new issue.
from dsntnn.
from dsntnn.
Related Issues (20)
- Converting to onnx HOT 2
- Get confidence of prediciton per regressed coordinate HOT 8
- RuntimeError: expected flip dims axis >= 0, but got min flip dims=-1 HOT 1
- dsnt in testing phase HOT 8
- Working with 3D HOT 8
- Suggestion: Define X,Y grid so that they include -1 and 1 HOT 6
- DSNT support only 1 point in 1 heatmap? HOT 2
- Question when I use dsnt in my net HOT 8
- A question about the input and target HOT 4
- how to get the confidence score from the output result? HOT 2
- Is Frobenius computed correctly? HOT 2
- 3 dimension coordinate regression HOT 1
- increase batch size 1 to 16, it made wrong result. HOT 7
- For the normalized_linspace function HOT 2
- Pip install fails HOT 1
- Question re. occluded or missing points in training data HOT 2
- Use generated 2d-guassion heatmap as the regularization. HOT 2
- output coords are negative floats HOT 15
- Values outside (-1,1) HOT 1
- Trace warnings when trying to jit.trace a model HOT 11
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 dsntnn.