Comments (13)
Oh, train.txt should contain both image and label split by blank, which is different from test.txt.
from lip_ssl.
E0516 17:22:28.599076 34580 io.cpp:81] Could not open or find file human/data/
Please check your directory of the image data.
from lip_ssl.
Thank you for your reply.
my train.txt is the same as test.txt,it is just like this:
And my files in human/data:
I'm so confused that I can run TEST but I failed when training.
I run the code in the root path : LIP_SSL
from lip_ssl.
Thanks for your reply. It works fine now!
from lip_ssl.
@CPFLAME May I know if you uncomment USE_CUDA when make caffe folder?
I ran into #2 problem.
Best,
from lip_ssl.
@adwin5 I used cuda when I make caffe folder.
It seems that the memory of your GPU is not big enough to run test, I think you can choose a GPU of larger memory to run this code.
By the way, I used the memory of 2579M to run the test code. You can check your momery size.
from lip_ssl.
@CPFLAME Thank you!
I will try uncomment USE_CUDA
I have 8G, should be OK for testing!
from lip_ssl.
@adwin5 You may use cuDNN or a larger memory GPU.
from lip_ssl.
@Engineering-Course
Thanks it works.
from lip_ssl.
@Engineering-Course @CPFLAME
I can run training, and I reference init.model from deeplap attention model.
I want to ask how to set path to use pose ground truth for training.
The run_human.sh code seems just reading ground truth labels not including pose, right?
My second question is what does strong and weak means in the training section in the run_human.sh file
Thank you.
from lip_ssl.
@adwin5
Sorry, these scripts are only used for parsing tasks.
Strong and weak mean nothing which are used by deeplab not this project.
from lip_ssl.
@Engineering-Course
Can I confirm with you that the code is just using parsing loss (pixel-wise softmax loss) instead of structure loss (structure-sensitive loss) which mentioned in paper.
Thank you.
from lip_ssl.
@adwin5 NONONO, it does use a structure loss. You can see the configuration in train.prototxt.
from lip_ssl.
Related Issues (20)
- Git clone failed HOT 1
- Incorrect output in test HOT 11
- follow your instructions but wrong answer HOT 1
- How long does this model takes when you segment a picture? HOT 1
- Error in testing with pretrained model HOT 6
- 代码测试问题 HOT 1
- Train model with new data get error HOT 1
- Is it impossible to train with new data for sketch-segmentation? HOT 8
- what's type of the segmentation images in training data? HOT 7
- Init model for training HOT 5
- Don't find train.txt HOT 1
- "caffe.ImageDataParameter" has no field named "label_type" HOT 3
- test pretrain model with customized data HOT 3
- no such directory as ssl/human/data/images and so on? HOT 1
- Test results are consistent with the reported values in the paper ?
- error while running run_human.sh
- Could you please provide the corresponding CUDA version number?
- What is the total number of parameters in this model?
- About LIP dataset HOT 1
- How to run on a new image ?
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 lip_ssl.