Comments (6)
Please post the command you ran and the location of your "landscape" folder...
Also - are you training a new model or are you trying to run the pre-trained model?
from art-dcgan.
Hey did you ever get the issue resolved (and if so- how)? Can I close this?
from art-dcgan.
DATA_ROOT=landscapes dataset=folder ndf=50 ngf=150 th main.lua
Landscapes folder is in the root folder of art-DCGAN.
Trying to use the pretrained networks.
from art-dcgan.
if you're trying to use pretrained networks - instead of passing ndf=50
and ngf=150
, you need to pass
netD=path_to_discriminator_net.t7
netG=path_to_generator_net.t7
Also, your landscapes folder is titled "landscapes" and not "landscape"? Make sure the folder name is correct when specifying DATA_ROOT
, because the error you're getting is related to loading the data.
from art-dcgan.
Hey, thanks for the advice. I decided to full path everything, but I get this error, landscapes file is created with the default scraping.
/home/rzmml/torch/install/bin/luajit: /home/rzmml/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 2 callback] /home/rzmml/torch/install/share/lua/5.1/image/init.lua:235: Not a JPEG file: starts with 0x47 0x49
from art-dcgan.
Hm... Looks like the scraper couldn't finish downloading a few of the images...
If you're on linux, you can run find . -iname '*.jpg' -print0 | xargs -0 jpeginfo -c
and delete all of the files it says there, but if you're on windows you'll have to just sort the images by file size and delete the ~10 smallest and ~10 largest images... The scraper usually messes up on those.
I'll commit something hopefully this weekend and add that into the scraper, but for now you'll have to do it manually :(
from art-dcgan.
Related Issues (20)
- How to resume from checkpoint? There is no checkpoint? HOT 4
- genre-scraper.py HTTP Error 404: Not Found HOT 7
- Feature Request
- Progress Updates HOT 1
- What are the training parameters for pre-trained networks? HOT 3
- genre_scraper.py only scraping 4000 images max HOT 9
- another way to train
- Portrait GAN
- Get painting list requests get throttled by wikiart HOT 2
- Windows Or Virtual Machine? HOT 1
- Feature Request: Image cropping
- Error on training a GAN on a folder of images
- How to run? HOT 2
- cudnn-7.0-linux-x64-v3.0-prod.tgz
- WikiArt scraper only scraping <3000 images HOT 4
- Resuming from pretrained network checkpoints on CPU fails: unknown Torch class <torch.CudaTensor> HOT 31
- 100 epochs with 10,000 images from celebA... still noise? HOT 15
- Error with own image dataset HOT 2
- can't seem to scrape wikiart! HOT 3
- Continuous noisemode?
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 art-dcgan.