Comments (8)
@7Khalil sure! I mean, you just have to download all the images to a folder and run one command
from lightweight-gan.
@7Khalil the dataset size doesn't determine the amount of GPU memory used, it's the batch size and image resolution that are the determinants
from lightweight-gan.
pin_memory=True is set to True. This is a trick used to disable constant freeing and reallocating of memory by PyTorch, therefore improving the training speed by a bit. Usually, pinning the memory improves the speeds by something around 1% to 15%. If you're facing GPU memory issues, perhaps turning this flag off would be a good first step.
from lightweight-gan.
@7Khalil do you really think it needs a colab?
from lightweight-gan.
@lucidrains actualy i have tried it, and i got with a dataset of ~1300 images, i got GPU memory overflow. after reading your comment i the tried it with a smaller dataset with 500 images and it seems to work well.
from lightweight-gan.
@7Khalil ohh, what sized images did you try to train? you shouldn't overflow with anything below or at 512x512
from lightweight-gan.
@lucidrainsit seems weird, because both datasets that i used are 1024px resolution. wondering why ?!
from lightweight-gan.
Ok, @ClashLuke thanks.
from lightweight-gan.
Related Issues (20)
- Error(s) in loading state_dict for LightweightGAN HOT 2
- Batchnorm layer missing in the discriminator?
- showing results while training ? HOT 2
- G is showing up a negative number. What does that mean?
- Multi GPU utilization problem.
- TypeError: __init__() got an unexpected keyword argument 'hparams' HOT 1
- unable to load save model. please try downgrading the package to the version specified by the saved model HOT 7
- --load_strict=False failing to load model HOT 1
- Can't find "__main__" module (sorry if noob question) HOT 4
- loss implementation differs from paper HOT 1
- Doesn't detect CUDA from Nvidia GPU HOT 1
- Torchvision Assertion error while importing custom data
- Aim installation error HOT 4
- Discriminator Loss converges to 0 while Generator loss pretty high HOT 3
- Dont detects cuda HOT 1
- Using Lightweight GAN as a library
- Projecting generated Images to Latent Space HOT 1
- Executing with a trailing \ in the arguments sets the variable new to the truthy value '\\' and deletes all progress
- CUDA out of memory error while generating interpolations
- Minimum number data training
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 lightweight-gan.