Comments (3)
Looks like you have python 2.x ... therefore f string is giving syntax error.
You can change that line like the one below, then you're good to go
print('\nSaving final output image to:', output_path)
from watermark-removal-pytorch.
I modified the line in api.py as above
Make it as
print('\nSaving final output image to:', output_path)
Then I run python inference.py
It has the following error:
mac:Watermark-Removal-Pytorch MyUserName $ python inference.py
Traceback (most recent call last):
File "inference.py", line 2, in
from api import remove_watermark
File "/Users/MyUserName/Documents/GitHub/Watermark-Removal-Pytorch/api.py", line 1, in
from torch import optim
ImportError: No module named torch
I tried to install torch by
cd pytorch
Lots of files are downloaded inside my atermark-Removal-Pytorch folder as pytorch
I tried python inference.py
It still gives the above error
Can you script batch remove watermarks on multiple images?
from watermark-removal-pytorch.
cd command doesn't install anything... It stands for change directory... You have to install pytorch through pip, head over to pytorch official website for complete installation guide based on your operating system.
And removing watermark for multiple images is not possible... It's just not how the model works.
You can try passing batch of images with batch of overlay masks but the outputs wouldn't be as good as compared to single image training.
from watermark-removal-pytorch.
Related Issues (20)
- TypeError: 'NoneType' object does not support item assignment HOT 5
- Processing was stopped out , Upsampling is deprecated
- Not an issue. wondering if the set up is correct. HOT 2
- Does it work on CPU? HOT 1
- on video ? HOT 1
- [RuntimeError: CUDA out of memory] when max dimensions of final image are increased HOT 2
- An iteration takes on my laptop dozens of seconds (cpu only) HOT 1
- retrain HOT 2
- Loss of resolution HOT 9
- Broken can't install it even with build tools HOT 2
- Inference time HOT 3
- Using the same model for the batch of images HOT 1
- CPU usage. HOT 1
- Model learns to synthesize watermark too HOT 2
- Need some data on performance of this application HOT 1
- Licence? HOT 2
- Instructions HOT 1
- requirements.txt HOT 2
- Default parameters HOT 1
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 watermark-removal-pytorch.