-
Notifications
You must be signed in to change notification settings - Fork 414
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
provided DS-CNN accuracy (on board) #47
Comments
In my case, DS-CNN provided very high accuracy on my FRDM-K64 board.(both simple and real-time test are good) |
Hi leejaeuk, I am using the STM32F746G discovery kit, with the on-board microphones. I had to compile the code using mbed-os5 (see #43), but apart from this change I did not change anything. |
is it any problem? when you compile using mbed-os? You should check a process of mbed compile. -cd Deployment or you should using virtual machine ubuntu 16.04 version |
No, compiling with mbed-os does not bring up any problems. I followed the steps you describe (pip install inside a conda environment) before creating the project folder. |
maybe you can modify Deployment/Examples/realtime_test/main.cpp file to |
The simple_test example works alright (predicts "right" with 99% confidence).
The dataset is composed of close talk recorded samples, however there are far field on the board. Could it be that the DNN is simply more robust to ambient noise than the DS-CNN ? |
Hi @sherylll ,
Indeed, but you can for instance translate this value to percentage with In my case, I get 127 for "right" with both DNN and DS-CNN, on a STM32F746G and a STM32F767ZI board. |
Hi @4p0pt0Z Thanks a lot! I realized that I missed one line so I deleted my last comment... I also noticed that the scaled MFCC can exceed -127 in the simple test example, as I set a break point here:
Is DNN robust against such cases, or is my board misbehaving? |
Seems to be fixed by b6e13d6 |
@4p0pt0Z |
Hi,
When testing the provided DS-CNN on my board, the accuracy seems to be very low. Especially in the real time example, the model almost always predicts "left" as soon as there is some sound.
Everything seems fine listening to the audio loopback, and the DNN provides much better results.
Is there specific parameters to use with DS-CNN in order to get high accuracy ?
Thanks
The text was updated successfully, but these errors were encountered: