Comments (3)
Sure, you can set --size
in your command.
Please refer to the arguments in inference code: https://github.com/sczhou/ProPainter/blob/main/inference_propainter.py#L177
from propainter.
there seems to be an issue trying to set the tuple with --size from the command line. Tried x, y and x y and (x y) and (x,y) but always seems to error out.
I added the ability to read the input dimensions and set the size internally but the inference quickly runs out of GPU ram (it wanted 96 G for 1920x1080 input)
Also if the new resolution is not divisible by 8 on width and height an error is generated. Could pad the input and then unpad the output?
from propainter.
there seems to be an issue trying to set the tuple with --size from the command line. Tried x, y and x y and (x y) and (x,y) but always seems to error out. I added the ability to read the input dimensions and set the size internally but the inference quickly runs out of GPU ram (it wanted 96 G for 1920x1080 input) Also if the new resolution is not divisible by 8 on width and height an error is generated. Could pad the input and then unpad the output?
The output of 1080P consumes a lot of GPU graphics memory. Unless your GPU graphics memory is large enough, you need to reduce the output resolution.
from propainter.
Related Issues (20)
- Can i select desired object from video for it's removal?
- Not using Gpu ? HOT 4
- Simple demo of ProPrinter in colab
- License HOT 1
- How to draw mask?
- RuntimeError: CUDA out of memory HOT 1
- Result as JPEG or PNG files not a video file HOT 1
- Inference is very slow, seems no GPU usage HOT 1
- Could not run 'torchvision::deform_conv2d' with arguments from the 'CUDA' backend HOT 1
- Davis数据集指标有差异 HOT 2
- Could you help to further explain your sub-video idea
- How to train this model/
- Colab is not working, Can you fix it, please?
- Support ONNX?
- pip package
- How to get this thing "running"
- For preparing youtube-vos dataset HOT 1
- Outpainting task
- Problem with the output with video input HOT 1
- evaluate problem 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 propainter.