Comments (6)
Hi,
it could. Could you attach a stack trace?
from cn24.
> test
DBG [ Trainer::Reset(80) ] Resetting Trainer state
DBG [ DatasetInputLayer::SetTestingMode(242) ] Enabled testing mode.
DBG [ Trainer::Test(90) ]
Program received signal SIGBUS, Bus error.
0x00007ffff7b7be43 in Conv::Tensor::CopyMap(Conv::Tensor const&, unsigned long, unsigned long, Conv::Tensor&, unsigned long, unsigned long) () from /home/ubuntu/cn24/libcn24.so
(gdb) bt
#0 0x00007ffff7b7be43 in Conv::Tensor::CopyMap(Conv::Tensor const&, unsigned long, unsigned long, Conv::Tensor&, unsigned long, unsigned long) () from /home/ubuntu/cn24/libcn24.so
#1 0x00007ffff7b7bcab in Conv::Tensor::CopySample(Conv::Tensor const&, unsigned long, Conv::Tensor&, unsigned long) () from /home/ubuntu/cn24/libcn24.so
#2 0x00007ffff7b6d398 in Conv::TensorStreamDataset::GetTestingSample(Conv::Tensor&, Conv::Tensor&, Conv::Tensor&, Conv::Tensor&, unsigned int, unsigned int) () from /home/ubuntu/cn24/libcn24.so
#3 0x00007ffff7ba8baa in Conv::DatasetInputLayer::FeedForward() () from /home/ubuntu/cn24/libcn24.so
#4 0x00007ffff7b8bec3 in Conv::NetGraph::FeedForward(Conv::NetGraphNode*) ()
from /home/ubuntu/cn24/libcn24.so
#5 0x00007ffff7b8bd89 in Conv::NetGraph::FeedForward(std::vector<Conv::NetGraphNode*, std::allocator<Conv::NetGraphNode*> >&, bool) () from /home/ubuntu/cn24/libcn24.so
#6 0x00007ffff7b8bcb4 in Conv::NetGraph::FeedForward() () from /home/ubuntu/cn24/libcn24.so
#7 0x00007ffff7b84d1b in Conv::Trainer::Test() () from /home/ubuntu/cn24/libcn24.so
#8 0x000000000040d04d in parseCommand(Conv::NetGraph&, Conv::NetGraph&, Conv::Trainer&, Conv::Trainer&, bool, std::string&) ()
#9 0x000000000040bdf9 in main ()
from cn24.
Confirmed that it has to do with test set size. Well, I guess one just has to use small sets for testing.
from cn24.
Just for reference, we have no problems using >70GB datasets without any special measures. You may want to check your system configuration because CN24 does not do anything out of the ordinary in terms of system calls.
from cn24.
@clrokr What kind of hardware (in terms of main and GPU memory) do you use for those datasets?
from cn24.
Training usually takes place on a Xeon E3-1231v3 workstation with 16GB main memory and an R9 290X with 4GB of VRAM.
from cn24.
Related Issues (20)
- Error moving to GPU HOT 2
- Multidimensional Labels HOT 2
- Minimal working example for training net. HOT 2
- ERR [ ErrorLayer::CreateOutputs(48) ] Inputs need the same number of elements! HOT 3
- High CPU, no GPU utilization in training HOT 2
- Commenting out #method=patch doesn't work in arch file
- ERR [ Tensor::Deserialize(303) ] Memory map failed: 12 / bad alloc HOT 4
- questions: batch size in hybrid mode; training and testing tensors
- CN24 reports incorrect metrics when using test images different in size (WxH) from train images HOT 4
- Multiple GPUs HOT 1
- License in OpenCL kernels are GPL3, while main project is BSD 3-clause HOT 1
- Problem about HOT 3
- Problem with bad_alloc error HOT 2
- Network from the cn24 paper HOT 1
- Licensing issue with libreadline HOT 1
- FATAL: Layer has dynamic input but doesn't support it: Confusion Matrix Layer HOT 1
- Training with more than four channels HOT 2
- Compilation issue on windows 10
- how to set GPU HOT 1
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 cn24.