Comments (4)
It seems that your Matlab does not have the over overloading of imresize for gpuArray.
A simple modification is that, you can commente out
Line 52, 76 in script_faster_rcnn_demo.m
"im = gpuArray(im);"
Thus the operation of image resize will use cpu instead of gpu. A side effect is slower testing speed.
from faster_rcnn.
@ShaoqingRen hi, i also commented Line 28,29, then succeeded. Thanks!
---K40----
001763.jpg (500x375): time 0.268s (resize+conv+proposal: 0.204s, nms+regionwise: 0.064s)
004545.jpg (500x375): time 0.272s (resize+conv+proposal: 0.206s, nms+regionwise: 0.066s)
000542.jpg (500x375): time 0.245s (resize+conv+proposal: 0.207s, nms+regionwise: 0.038s)
000456.jpg (500x375): time 0.269s (resize+conv+proposal: 0.208s, nms+regionwise: 0.061s)
001150.jpg (500x375): time 0.261s (resize+conv+proposal: 0.208s, nms+regionwise: 0.053s)
mean time: 0.263s
from faster_rcnn.
@ShaoqingRen Hi, I also encounter this problem this morning. The reason I wrote this comment is that I found even after I comment line 52,76 and line 28, 29 (as suggest by @xmubingo), there is still an error in the num.m. Actually the error occurs on line 34
nms_gpu_mex(single(boxes)', double(overlap));
and line 43
nms_mex(double(boxes), double(overlap));
both say the function is undefined.
Therefore I thought if I miss some installation steps? I'm using matlab 2013a and I'm sure to execute make matcaffe with no errors (caffe in this repository).
And currently my solution is using this file https://github.com/rbgirshick/fast-rcnn/blob/master/matlab/nms.m to temporarily replace nms.m. (Plus adding a peudo parameter use_gpu) Any suggestions?
Thank you for your time!
from faster_rcnn.
You have this problem because matlab can not find the mex file that contains the function.
so the file in "functions/nms/nms_mex.cpp" and "functions/nms/nms_gpu_mex.cu" need to be compiled!
you can compile them by running the script called: "faster_rcnn_build.m" in the home directory as mentioned in the README.md
See Snapshot
Undefined function 'nms_mex' for input arguments of type 'double'.
from faster_rcnn.
Related Issues (20)
- demo Check failed HOT 3
- No detection on "training image" with a trained net
- GPU memory is not enough(2g),how to deal with it
- A compiling problem with Win10+VS2017+MATLAB R2016b+CUDA9.1: undefined reference
- the error when training with VOC2007 HOT 2
- Error when compiling nms_gpu_mex
- Error '_MSC_VER': value '1600' doesn't match value '1800' in nms_gpu_mex.o running faster_rcnn_build.m file HOT 1
- training faster rcnn on ROI only ?
- Fast RCNN loss doesn't change when trained with my own dateset. Not fine tuned on pretrained model
- error at hNet = caffe_('get_net', model_file, phase_name); HOT 1
- runtime question
- Some problems when i train VOC2007 database HOT 1
- I just finished demo and try to train with pascal_voc dataset. (1) If I command /py-faster-rcnn/experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc ./faster_rcnn_alt_opt.sh: line 46: ./tools/train_faster_rcnn_alt_opt.py: No such file or directory above error message is shown up. HOT 1
- error when run faster rcnn in (stage one of fast rcnn ) win10, GPU 1080 TI, Matlab 2018a ; i RUN demo without error ; any solve ? HOT 1
- Is there validatoin set in faster_rcnn ?
- Concatenate a fixed value to fc7 features
- how can i train faster R-CNN using a new customised network model?
- Failed when running 'faster_rcnn_build.m' HOT 1
- What is the mean image?
- Loss is not changing
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 faster_rcnn.