Comments (4)
I was not able to understand what you mean. A source file is a code file (here, a python script). Each of the scripts in my repo is independent from the others, so you would only call one script.
If you meant multiple source images, then my repo doesn't support is currently. Sadly, since each image takes quite some time, I don't feel queuing multiple source images is optimal.
from neural-style-transfer.
I'm sorry if I was not specific.
I tried to run Network.py /path/to/ *.jpg , in order to process different pictures inside a folder (the frames of a video frame1, frame2, etc)
And i got a gpu ram error (i used a VM with 8gb )
btw, i have used various scripts that do style transfer and yours gives the best results with less hustle 👍
from neural-style-transfer.
I see. Sadly, my script does not support *.jpg format. As I said, it works on one image at a time, so you have to specify the path to a single image.
If you are on a linux environment, you can write a bash script to iterate through all of the image paths in a directory and call the script each time.
If you are on a windows environment, you could probably write a batch or powershell script to do the same, but it would be much more hassle than it is worth.
from neural-style-transfer.
Yes, I will try the bash script, I already had it on the to do list.
Btw, I have used it with jpg files again and again. No problems at all.
Also, how i can modify your script , to not save each iteration, just one file with the final iteration.
from neural-style-transfer.
Related Issues (20)
- [Question] Content mask format HOT 5
- how to run the script on multiples GPU?
- ImportError: cannot import name 'imread' HOT 5
- Google colab neural style transfer HOT 2
- error in MRFNetwork.py HOT 1
- could we apply fast-style-transfer to image deformation? HOT 2
- Update documentation to reflect that tensorflow works on Windows now
- Replace tf.gradients with tf.GradientTape : RuntimeError HOT 2
- Bug using preserve color option HOT 3
- ValueError: Tensor conversion requested dtype float32 for Tensor with dtype int32: 'Tensor("strided_slice_8:0", shape=(), dtype=int32)' HOT 1
- script helper
- script helper
- Saving model
- RuntimeError: tf.gradients is not supported when eager execution is enabled. Use tf.GradientTape instead. HOT 5
- convert_all_kernels_in_model removed from tf2 HOT 1
- RuntimeError: tf.gradients is not supported when eager execution is enabled. Use tf.GradientTape instead. HOT 2
- neural doodle
- broken and unusable HOT 1
- Tensorflow 1 is unsupported in Colab
- Hello, I'm sorry to bother you. I need help
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 neural-style-transfer.