Comments (9)
Hi @saudades18! Could you please describe how you launch the code on 40 images?
from neuralhaircut.
thanks for your reply @VanessaSklyarova .i just change the monoculardataset and add [:40] at the end of string in 330-340
from neuralhaircut.
And i use h3ds dataset to test, howerer, during the training, it still occur "NaN during backprop was found, skipping iteration", is it normal?
from neuralhaircut.
@saudades18 did you face any uploading weights error in https://github.com/SamsungLabs/NeuralHaircut/blob/main/src/models/dataset.py#L378 and did you use configs from ./example?
Yes, "NaN during backprop was found, skipping iteration" is okay if it happens not frequently.
from neuralhaircut.
@VanessaSklyarova i did not face uploading weights error, however "NaN during backprop was found, skipping iteration" happens frequently, about 90%.
And i use configs from ./example, i just follow the command in https://github.com/SamsungLabs/NeuralHaircut/tree/main/example/readme.md
And when i using h3ds dataset, the hair is optimized. but when using the data given(this time all images), the loss still was not decreased, and the hair primitives were still long and straight.
Could you please provide the checkpoint for the second stage?
Thanks for your reply :)
from neuralhaircut.
@saudades18 Could you set https://github.com/SamsungLabs/NeuralHaircut/blob/main/configs/example_config/hair_strands_textured.yaml#L54 to false, change https://github.com/SamsungLabs/NeuralHaircut/blob/main/configs/example_config/hair_strands_textured.yaml#L77 and https://github.com/SamsungLabs/NeuralHaircut/blob/main/configs/example_config/hair_strands_textured.yaml#L78 to 0. and check if the loss decrease with time? (You could try it on 40 images as well)
from neuralhaircut.
@VanessaSklyarova Thanks for your kind reply! Now the hair is optimized, and the loss is decreasing except hair_L_diff loss. And before most of the render images are black, maybe this is the reason? So how can i train successfully with rendering?
Maybe first train without render loss, and get a approximate hair shape, and then use all loss to refine? will it help?
from neuralhaircut.
@saudades18 Yes, it should be more stable if you start rendering after approx. 1000 steps, but still it is very strange why it doesn't work from the beginning. I didn't face such rendering problems before when checked on different scenes, so I'll have a look at this.
from neuralhaircut.
@VanessaSklyarova i start rendering after 1000 steps, but it seems like the render images are still not optimized. And "Nan" still happens frequently so the iteration is skipped. Below is one of the render images, and it looks like rasterize image rather than real rgb.
from neuralhaircut.
Related Issues (18)
- Afro hairs, anyone ? xD HOT 1
- numpy.core._exceptions._ArrayMemoryError: Unable to allocate HOT 4
- Couldn't create the environment using .yaml HOT 2
- failing to compute hair_mask with CDGnet HOT 2
- Unable to create the enviroment in any of my devices
- Example Result HOT 1
- How does NeuralHaircut overcome the "noisy orientations map" problem in real-world data? HOT 2
- How to generate `initialization_pixie` file while executing the `multiview_optimization` HOT 1
- Unconditional random sampling from pretrained diffusion model HOT 1
- Need support section for further updates...
- About strand_ckpt. pth
- Add some about section to elaborate the aim of this site....
- Error testing the example provided HOT 4
- ValueError: need at least one array to stack HOT 4
- PIXIE initialization HOT 3
- Experiment folder cannot be crated on Windows HOT 4
- Can use own dataset? 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 neuralhaircut.