Comments (22)
Which version of CUDA8.0 is this ?
from darknet.
@prabindh
I use nvidia/cuda:8.0-devel-ubuntu16.04
from this Dockerfile.
https://gitlab.com/nvidia/cuda/blob/ubuntu16.04/8.0/devel/cudnn5/Dockerfile#L1
from darknet.
I strongly feel it may not be related to CUDNN. Did you stop the training in both of them after reasonable accuracies have been obtained in training ? Can you let the CUDNN version run longer epochs and check ?
from darknet.
I have re-trained my face data by CuDNN =1 once.
Following graph shows my train log, (x,y) = (epoch, loss rate). I have tried 29000 epochs.
My CuDNN version is 5.1.10.
The result is unchaged. CuDNN=1 isn't working. But CuDNN=0 works fine.
But I try to do following example, by CuDNN=1 and CuDNN=0, It works fine...
./darknet-cpp detector demo cfg/coco.data cfg/yolo.cfg yolo.weights
from darknet.
@kidapu have you sorted this? I have the same problem. I trained tiny yolo and it only works when CUDNN = 0. But this problem only happens when I try to link libdarknet-cpp-shared.so to my program. The ./darknet binary still works fine.
My environment:
Ubuntu 16
Cuda 8
Cudnn 6
GTX 1050
from darknet.
@bobeo
No. I have not solved. Completely same happens to me!!!
from darknet.
@bobeo Have you ensured your wrapper application (that uses the .so) also has the same options that are used for building the darknet shared lib ?
from darknet.
@kidapu Does inference work with CUDNN=1, with the shared lib ?
from darknet.
In summary, the following happens in my case.
(1) CuDNN == 0 && ( darknet-cpp || darknet-cpp-shared)
coco & my dataset works fine.
(2) CuDNN == 1 && ( darknet-cpp || darknet-cpp-shared)
- coco works fine
- my dataset is not work...
from darknet.
Is this behaviour seen with the latest master as well ? Please check the latest master and confirm
from darknet.
I need to confirm but I have this behaviour on v6.5-1-g372b25d with a GPU machine:
- (CuDNN == 0 || CuDNN == 1) && GPU == 1 && darknet-cpp-shared && arapaho : no detection
- (CuDNN == 0 || CuDNN == 1) && GPU == 0 && darknet-cpp-shared && arapaho : detections
from darknet.
@ooobelix please confirm - that you are building Arapaho, and darknet with same options (for GPU, CUDNN) in both the Makefiles.
from darknet.
I'm working on!
~/darknet$ grep -i "^GPU=|^CUDNN" Makefile arapaho/Makefile
Makefile:GPU=1
Makefile:CUDNN=1
arapaho/Makefile:GPU=1
arapaho/Makefile:CUDNN=1
After that, I'm using my own code with Arapaho to do some predictions.
Thanks for your help!
from darknet.
Could you confirm, what cfg is being used ?
from darknet.
From GIT:
5d442b0e550e6c640068e7e15e498599 yolov3.cfg
With 0.1 threshold
from darknet.
I'm:
- compiling libdarknet-cpp-shared.so with GPU=1 and CUDNN=1
- using your Arapaho code into my application with CFLAGS "-DCUDNN" and link with "cuda cudart cublas curand cudnn"
Results:
- without GPU, it works well
- with GPU, Detect return always 0 detection
from darknet.
I think you already tried with GPU=1, but I observed that in the last comment GPU is not defined.
my application with CFLAGS "-DCUDNN"
from darknet.
Sorry it's a mistake, you are right! I have already tested with GPU=1 and CUDNN=1
from darknet.
I tried the Arapaho build (Windows build from darknet-cpp-windows) with latest code, and the config:- Yolo-tinyv3 cfg, and CUDA91. I am able to see detections with the default yolov3 weights.
from darknet.
Ok, I did a stupid mistake into CMakeFile with the GPU and CUDNN options.
Now it works well with GPU=1 and CUDNN=1 but no need of linking "-lcudnn", is it normal?
from darknet.
"-lcudnn" should be required. Can we close this as the issue is resolved ?
from darknet.
I'm using CMakeList and "CUDNN=1" to "set(LNK_DEP [...] cudnn" and it works well.
For me, you can close this issue.
from darknet.
Related Issues (20)
- Arapaho stream with camera HOT 4
- input.data HOT 2
- Yolo v3 is out, sync with the original code? HOT 3
- 0 prediction with arapaho build (Yolo V3) HOT 2
- upsample_cpu is not defined when GPU=0 HOT 2
- Video of type 8UC1 is not working HOT 9
- After 10 Minutes Arapaho program getting killed HOT 15
- Cuda 9 HOT 6
- darknet-cpp compilation failed on Ubuntu 16.04 HOT 6
- Memory corruption of Arapaho from a library HOT 4
- Cmake compile problem HOT 6
- Differences scores between Darknet and Arapaho HOT 5
- When the width and height of the input picture are not equal, the output box will shift on windows
- Add OpenCV 4.x support HOT 27
- Arapaho build issue HOT 3
- libv4l2: error getting capabilities: Inappropriate ioctl for device HOT 5
- Darknet saved weights are not giving outputs in this HOT 2
- Anyone tested darknet-cpp on Cuda 6.5 (Ubuntu 14.04)? HOT 5
- Trained in two classes the object can't be inference HOT 3
- error "identifier \"ipl_to_image\" is undefined","LineNumber": 234, File: arapaho.cpp HOT 3
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 darknet.