Comments (7)
I'm using cuda 8 and cudnn 5. I can build with cudnn without any problem. You may want check which cudnn version is ok for your cuda on Caffe site.
from affordance-net.
Currently, some python layers from Faster R-CNN do not support multi gpu training. You may want to check this repo to know how to do this. The integration process may be very complicated. Unfortunately, I don't have access to multi gpu to test it. Good luck!
from affordance-net.
@nqanh what's you're cudnn and cuda version?
I want to make caffe USE_CUDNN := 1
is not working. I think that is cudnn version problem.
from affordance-net.
@nqanh Please forgive me for many questioning.
I using cudnn5,5.1 above, but it doesn't work, then i use cudnn 4 that worked.
and trainig time about 1iterator is almost <1 second.
then training time is almost 30days.
when you training this for 2,000,000iterator, how long did it takes in your computer?
from affordance-net.
@deokisys No problems! Just tell us if you have any problems with the code.
About the training time, it depends on your hardware and how big your dataset is. For example, for IIT-AFF dataset, we have around 6K training images and training for 200000 (not 2, 000, 000 as you said) takes around 2 days on a Titan X.
from affordance-net.
@nqanh thank you I missed it.
and I have loss problem.
I0125 21:00:01.081059 2920 solver.cpp:229] Iteration 160, loss = nan
I0125 21:00:01.081090 2920 solver.cpp:245] Train net output #0: loss_bbox = nan (* 2 = nan loss)
I0125 21:00:01.081097 2920 solver.cpp:245] Train net output #1: loss_cls = 87.3365 (* 3 = 262.01 loss)
I0125 21:00:01.081102 2920 solver.cpp:245] Train net output #2: loss_mask = 25.5312 (* 3 = 76.5937 loss)
I0125 21:00:01.081107 2920 solver.cpp:245] Train net output #3: rpn_cls_loss = 0.538947 (* 1 = 0.538947 loss)
I0125 21:00:01.081112 2920 solver.cpp:245] Train net output #4: rpn_loss_bbox = 0.0324526 (* 1 = 0.0324526 loss)
I0125 21:00:01.081117 2920 sgd_solver.cpp:106] Iteration 160, lr = 0.001
if i make caffe without cudnn , then training speed is down then with cudnn (1 iterator is almos 2s), but loss is going down.
if i make caffe with cudnn, then training speed is going up (1 iterator is almost 0.8s) , but loss is 'nan'.
is not good? loss 'nan' mean about not training?
from affordance-net.
Loss=nan is a serious problem. Sometimes we have this problem due to the numerical explosion in some python layers (from Faster R-CNN). It's quite random and also depends on your GPU (and cuda). You should stop the training and try to avoid this problem because the network is dead if loss=nan. Also, we do not use cuDNN during training.
from affordance-net.
Related Issues (20)
- What is the difference between roi_alignment and roi_alignment2? HOT 2
- A question about .sm file HOT 6
- way to calculate F score HOT 6
- Regarding cudnn version and caffe installation HOT 5
- Sorry, Can you tell me how to create several .sm files in image with pascal voc datasets?
- A question about loss_mask layer
- I get some errors while doing python demo_img.py HOT 1
- src/caffe/layers/cudnn_relu_layer.cu(19): error: identifier "activ_desc_" is undefined HOT 2
- Add cudnn7 support
- How to create several .sm files in an image with pascal voc datasets?
- Camera parameters of IIT dataset HOT 1
- Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type HOT 2
- How to change number of classes
- WARNING: filter_boxes() remove ALL proposal.
- One Object with multiple affordances
- Missing Affordance Masks
- Ros version Problem
- Color-coded affordance label HOT 2
- Caffe Installation
- AffordanceNet architecture implementation
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 affordance-net.