Comments (3)
While generating your own dataset, you will render depth. The depth should be rendered as raw, absolute values, possibly stored in .exr or some other formats that are able to hold these floating point numbers. The depth maps people show are usually the offset, scaled, and discretized version of these raw maps. Once you have the raw maps, the min
in depth_minmax
is just the minimum value, and the max
is the maximum excluding the background depth.
from genre-shapehd.
Hi, we render the depth
images and depth_minmax
using Blender but it seems like we got depth_minmax
wrong because the marrnet1 did not converge, the normal/depth/silhou loss kept increasing after some epochs and depth_minmax loss
is extremely large. If we set --pred_depth_minmax
to false, the results looked pretty decent. Is it possible that you open the render depth
code?
from genre-shapehd.
Hi, could you clarify what you mean by "got the depth_minmax
wrong"? I might have missed something, but if those values are wrong, then you should fix the rendering code until they are correct before training the models.
from genre-shapehd.
Related Issues (20)
- Can I read numpy data from the depth,normal and silhouette image? HOT 4
- How to obtain surface normal images from the raw depth data? HOT 1
- I want to use the wgangp which is in the shapehd HOT 2
- ground truth images that give rise to the demo latent inputs
- MarrNet w/o Reprojection Consistency Weights HOT 1
- how to get the intrinsic and extrinsic parameters when i use the GenRE HOT 3
- how can I make my own data set? HOT 1
- 128.npz voxel files are not TDF HOT 4
- Evaluation code HOT 2
- Failure when running test_genre.sh HOT 1
- Full Dataset? HOT 1
- Fail to compile. HOT 2
- Poor Genre results on demo images when compiled with Cuda10 HOT 6
- Generate distance field based on depth image by using render_spherical function HOT 2
- Different prediction results by using different data loader code for GenRe HOT 3
- Could you provide state_dicts for the discriminator of the pretrained models HOT 3
- how to
- how to train marrnet of shapehd? HOT 1
- GenRe docker environment for 2080Ti and 1080Ti HOT 1
- dataset link broken? HOT 2
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 genre-shapehd.