Comments (3)
Thanks for pointing this out-- I found a problem with one of the default config settings which was creating a network with far too many hidden layers. This was creating the flat output. I pushed a fix, so try pulling from the repo and running python train_img.py --config config_img/config_pluto_acorn_1k.ini
from the experiment_scripts
folder. Let me know if this works.
As far as the grid_sample gradient, this is doing bilinear interpolation so it is differentiable. The output is expressed as a weighted combination of features from the input feature grid, and then you can derive the gradient with respect to the input feature grid.
from acorn.
Now, it is working, very efficient, 200it/s in my machine, RTX2080ti
from acorn.
Great! I'll go ahead and close the issue then. Let us know if you see any other problems.
from acorn.
Related Issues (10)
- Train occupancy on point cloud HOT 2
- Training without Gurobi optimizer HOT 1
- Metrics HOT 3
- Training speed HOT 8
- Tokyo/mars gigapixel too large, process killed HOT 5
- How to choose res/patch size for new images HOT 2
- o attribute 'num_scales' HOT 1
- Error of merging and splitting blocks
- About the number of coords sampled within each block.
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 acorn.