-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
Real execution frequency on embedded board is considerably lower than 20Hz and changes between drive and algo modes #690
Comments
It looks like OLEDPart is taking a lot of time to finish. Can you turn off those time consuming parts and verify the result? |
@sctse999 - I disable oled and reduced the overhead of Telemetry and PerfMonitor. I am still getting around 4hz with active model:
|
You should try using TensorRT on the Nano or TFLite. Your framerate will improve considerably. I usually get 45Hz with my model. |
@cloud-rocket - if you still see the problem, please re-open this issue with more info. In particular if you run the script |
I am not yet reopening, but
|
@cloud-rocket This is Nano 2GB? |
Nop - 4Gb. I added np.float32 conversion to
I don't think this conversion adds a significant performance penalty |
We saw problems with tf > 2.2.0 in training. But 20 Hz is definitely much too slow. Have you tried the CPU version of TF? |
@DocGarbanzo, WDYM by "CPU version"? With standard TF I am getting 3.5hz - this is why I started this ticket.... BTW added a PR for tflite fix - #762 Also trying to see how to run TensorRT with TF2 - many changes required... Tnx |
@cloud-rocket - I just looked at the issue w/ TF > 2.2.0 on RPi yesterday. Indeed, any newer version causes a significant slowness on RPi, at least when using the |
drive
mode and drops to 3hz inlocal_angle
mode.drive
mode vs 3.5zh inlocal_angle
mode)This is my setup:
The text was updated successfully, but these errors were encountered: