Comments (6)
@IMath123 Maybe that is because you use different configuration for in accelerate config
, train without fp16 and eval with fp16, I guess.
from zipnerf-pytorch.
![image](https://private-user-images.githubusercontent.com/39054181/241252539-64f7816c-a866-44ef-9147-8682dbfb0a66.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.bjtvnALZsACLhfgImt487g26PbfCaJwcbfCVZE8Ea6U)
![image](https://private-user-images.githubusercontent.com/39054181/241252606-27eacb57-b1f2-4706-8d82-e5a6c98d76dd.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.R6JjDvOEZ8SsBZj9Im1iv72hlyE6b4dVuk_qbRrlEik)
from zipnerf-pytorch.
Sorry, it's my fault, you can delete the selected code in the photo, then it may work.
from zipnerf-pytorch.
Thanks!!! It works now!
from zipnerf-pytorch.
@SuLvXiangXin Hi! I have the same error, but in my case render.py doesn't have accelerator = accelerate.Accelerator('mixed_precision'='fp16'), and only accelerator = accelerate.Accelerator(), yet I get the same error. (I also used 'python train.py...' . It appears that it picked up the 'fp16' from the accelerate config even i didn't use 'accelerate launch train.py'...) What to do? I rather not re-train if don't have to, since it takes couple of days..
from zipnerf-pytorch.
as it turned out deleting (or commenting out) the 'fp16' line in default_config.yaml solved the problem
from zipnerf-pytorch.
Related Issues (20)
- Could not locate a supported Microsoft Visual C++ installation HOT 4
- No module named '_cuda_backend' HOT 8
- checkpoint mismatch HOT 1
- Question about the mesh extracting HOT 4
- Error Building gridencoder Can't Open Input file
- how calculate camera parameter ?
- ValueError: surface level must be within volume data range.
- acc_img
- How to create poses_bounds.npy HOT 1
- How to Calculate viewdirs?
- training is very slow HOT 1
- multi-sampling
- fail pip install gridencoder HOT 4
- 'extract mesh' outputs a 'strange' mesh
- viewdirs vs direction in cast_rays
- NaN or Inf found in input tensor.
- Why does the depth value of the depth map generated by the rendering not match the actual one
- Transform to grayscale when calculating SSIM
- too much floaters HOT 2
- Question regarding flipping coordinate system if z component of y-axis is negative
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 zipnerf-pytorch.