Comments (8)
@jorgyz Thank you too. The later person who would come across can comment out line 127 and line 128.
from caffe-segnet.
@SpecialM2580 Having the same problem here...were you able to figure it out? Thanks
from caffe-segnet.
@SpecialM2580
Hi, I ran into the same problem, have you guys figured out how to fix this problem? The funny thing is that by changing the net.prototxt the index "number" changes...
from caffe-segnet.
Interestingly, if you comment out that check in the code and recompile, it runs just fine and the results seem to look as expected.
from caffe-segnet.
I'm sorry,I almost forget this issue…It seems that this problem only occurs in CPU mode…I try running it in K40,it works just fine…I choose the batch size =3 (reach the maximum memory)and change the classification type to 32 ,using the Camvid dataset,after 15000 iteration ,and it didn't converge...the result is not good-A-,i'm new in deep learning ,may be my parameter chioce is bad,(batch size)or the iteration is not enough...
from caffe-segnet.
@SpecialM2580 How was this issue resolved I can't make heads nor tails from this message chain.
from caffe-segnet.
@jorgyz Thanks, your solution seems to work!
from caffe-segnet.
@jorgyz Thank you too, for those who came later and want to do that please note that there are 2 spots in the code that is throwing that fatal exception. You have to comment both out. And this seems to be a bug, since it is unlikely that just by switching from GPU to CPU will cause layer shapes to change...
from caffe-segnet.
Related Issues (20)
- About Run In C++
- Separate input concatenation in segnet
- Caffe2 caffe-segnet HOT 2
- make runtest fail HOT 4
- Reducing the noise in a image
- Error occurred when make resource code
- Which file does caffe execute when implementing convolutional operation?
- CUDNN version
- Caffe-SegNet installation on Windows
- All indices of the max locations will be stored and passed to the decoder during pooling?
- Hey - it doesn't make sense to train segnet on a single class. In this situation, segnet will simply learn to predict every pixel as this class, and you will see loss=0. HOT 1
- Help for implementing SegNet for predicting Single class
- Check failed: error == cudaSuccess (77 vs. 0) an illegal memory access was encountered HOT 2
- make problem
- make error
- nvcc fatal: redefinition of argument 'compiler-bindir'
- what is the softmax uncertainty in Bayesian Segnet paper?
- changing the number of classes in segnet produce error: cudaSuccess (700 vs. 0) an illegal memory access was encountered. HOT 1
- Try-demo issues about website http://mi.eng.cam.ac.uk/projects/segnet/demo.php
- why last prediction layer is 3x3 convolution??
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 caffe-segnet.