Comments (11)
I only tried predict.py for a single image. I get "out of memory" error with Titan X.
from dilation.
I also started to play around with the code a bit and wanted to test it on the cityscapes testimage. Not training, just the predict.py.
And it shows me there out of memory when I try it on my gpu with --gpu 0. Did you guys find a solution for it? Is really 18GB of GPU memory required for it? If so - is there any possibility to reduce the memory footprint at testing time? I use cudnn v5.1 and CUDA 8.0.
By the way: It works on KITTI with GPU and on cityscapes with CPU only.
from dilation.
I have a similar issue. I can only run the program in CPU mode because it requires about 18 Gb in memory.
from dilation.
@Timo-hab @chenqifeng22 test_batch has to be 0 for cityscape joint training. Was it set correctly?
from dilation.
@chenqifeng22 You have to check your setup. A lot of people have confirmed to me that predict.py can work well.
from dilation.
@fyu I need to install cuDNN to make it work.
from dilation.
@fyu thank you for your answer. test_batch wasnt set to 0. Now i can start the training, but dont see test results of course.
Is it possible to test the model on validation dataset while training, so i can see accuracy and loss, without the need for more GPU memory?
from dilation.
@manuelschmidt Depending on the model of GPU, the dilation network needs different amount of memory (which is quite strange to me).
There is a simple solution. Just make the input image size smaller in the prototype file. Also you need to change " if dataset.zoom > 1:" to "if dataset.zoom >= 1:" in the predict.py to prevent a bug.
from dilation.
@fyu I am training the ADE20K dataset on the Dilation network with the frontend mode in GPU with 8 GB memory and I get the error message 'out of memory'. Is 8 GB enough for the training?
My training batch is set as 10 and test batch 0.
Thank you
from dilation.
@qualia0000 Besides the batch size, the memory consumption also depends on the crop size.
from dilation.
@fyu Thank you for your reply. The crop size is set as 500. I'll try methods to make the consumption smaller.
from dilation.
Related Issues (20)
- ResNet as a front-end HOT 2
- Learnable interpolation for upsampling
- Some questions in "multi-scale context aggregation by dilated convolution"
- Front-end domain adaptation code HOT 2
- Image and label mismatch while training
- How can we use 3D dilated Convolution in Lasagne HOT 2
- How do you use the Cityscape for training? HOT 2
- train context HOT 1
- Random Crops during training
- how to set the dilation? HOT 1
- CPU Training and Net architecture
- How can I get frontend_vgg prototxt?
- questions about the initiate of the contextual module
- How much GPU Memory is required/recommended to run the demo?
- unable to download pretrained weights HOT 2
- //
- Relu problem
- How to reduce number of class on this model?
- What to put inside of training/testing image/label text files?
- five years later,a question
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 dilation.