Comments (1)
Hi @ProBURN-E, thanks. VRAM usage varies due to multiple factors, it's normal. There are internal bottlenecks that causes it, as well as different network designs that influences it. For example, networks like as compact
and span
have a stable gpu-util and vram usage, as opposed to omnisr
hich has more fluctuations.
Another reason could be slow dataloading times. If you have an SSD, it is recommended that you put your dataset in it, as it will avoid high reading times from HDD.
ps: another factor could be the image resolution. If your dataset has big images, it will take more time to decode, so it creates a bottleneck. It is recommended that you tile your images to a lower resolution, such as 512x512px.
from neosr.
Related Issues (20)
- wrapper around train.py, ... scripts and release on pypi
- `train_realesrgan.yml` is named "train_esrgan" HOT 1
- imwrite raise IOError when trying to write an image where the filename contains unicode characters HOT 2
- How to save a model fully in pth? Not state dict HOT 3
- Document which architectures have been modified and are incompatible with the original architecture HOT 4
- Add tile option HOT 2
- Modifications for CRAFT, SwinIR, and DCTLAS are not detectable HOT 8
- Automatically remove old checkpoints and visualizations HOT 4
- and again rgb_mean HOT 1
- assets HOT 3
- dataset_enlarge_ratio description HOT 1
- Mismatched resume state issue HOT 1
- All architectures with `rgb_mean = (0.5, 0.5, 0.5)` are incompatible HOT 9
- Python version problem HOT 4
- Question regarding net_d HOT 4
- model zoo HOT 1
- can not start train HOT 3
- ValueError at 79 epoch HOT 3
- NaN errors occurring constantly HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from neosr.