Comments (7)
Why is the DUT output video cropped,Is it because of the model?How should this problem be solved?
You can output uncropped video frames in dutstabilizer.py's function to generate video, but this model will generate black boxes, so I recommend cropping the video. Black edge compensation, I saw the author share a boundary extrapolation method, but has not uploaded the project code, I think, you can try to use generative adversarial network to predict the boundary generation.
from dutcode.
Thank you very much for your reply! I have one more question to ask. I set up the code environment according to the readme.file, but when I ran it, I got an error: RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED。What is the reason for this problem?
from dutcode.
Thank you very much for your reply! I have one more question to ask. I set up the code environment according to the readme.file, but when I ran it, I got an error: RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED。What is the reason for this problem?
I guess it may be caused by the mismatch between your cuda and pytorch. Are you running code on Ubuntu? I haven't tried this before? Because I was configured and successfully run under the Windows 10 environment. Can you show me your conda list or pip list ,so that I can find the diffrence between your configuration and mine?
from dutcode.
Thank you for reminding me! Now I also debug code in the windows environment. After investigation, I found that it was caused by insufficient video memory,Maybe I need to change the size of batchsize. Do you know how to modify the batchsize in dut?In addition, I wonder if it is convenient for you to leave your email address so that I can consult you more conveniently.
from dutcode.
Thank you for reminding me! Now I also debug code in the windows environment. After investigation, I found that it was caused by insufficient video memory,Maybe I need to change the size of batchsize. Do you know how to modify the batchsize in dut?In addition, I wonder if it is convenient for you to leave your email address so that I can consult you more conveniently.
hello,my email is [email protected]
from dutcode.
Thank you for reminding me! Now I also debug code in the windows environment. After investigation, I found that it was caused by insufficient video memory,Maybe I need to change the size of batchsize. Do you know how to modify the batchsize in dut?In addition, I wonder if it is convenient for you to leave your email address so that I can consult you more conveniently.
you can reduce your length of input video,out of memory can be slolved.The batch size can adjusted in config.but I remember it is 1.
from dutcode.
Thank you for reminding me! Now I also debug code in the windows environment. After investigation, I found that it was caused by insufficient video memory,Maybe I need to change the size of batchsize. Do you know how to modify the batchsize in dut?In addition, I wonder if it is convenient for you to leave your email address so that I can consult you more conveniently.
you can reduce your length of input video,out of memory can be slolved.The batch size can adjusted in config.but I remember it is 1.
Do you have any code for evaluation metrics?
from dutcode.
Related Issues (20)
- great a job.just a question HOT 1
- Training code 安定metrics calculation code
- Training code and metrics calculation code. HOT 2
- AttributeError: module 'correlation' has no attribute 'FunctionCorrelation'
- Training detail for Smooth kernel
- training code HOT 1
- Infinite running time
- Code is unusable due to missing models (sintel.pytorch and stabNet.pth) HOT 4
- issue in loading difnet model HOT 3
- can't download the models in google colab
- trainning code! HOT 7
- The definition of the loss function
- Where is the supplementary video? HOT 1
- CANT INSTALL CUPY
- full training code and data HOT 6
- [REQ] add a (GH-compliant) license file HOT 1
- Do you have the training code for StabNet?
- nice work, but one issue HOT 1
- Hello, does anyone know how to train? Various. npy files are missing.
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 dutcode.