Fix the tensorflow prediction (using models.load instead serving)

[david-hdn]

No description provided.

[FeiduoduoPeng]

this exactly fixed my problem

[acschristoph]

hey, when I use this fix, then fps drops from 15 to 3 FPS it looks like no gpu is using, any idea ?
great project thanks

[glenbhermon]

hey, when I use this fix, then fps drops from 15 to 3 FPS it looks like no gpu is using, any idea ? great project thanks

Same here!

[david-hdn]

Hi, you should check line 11 to choose which GPU(s) are suite best for you. By default, I choose the first one, you can replace it by using all GPUs that you have by this:
tf.config.experimental.set_memory_growth(physical_devices, True)

[glenbhermon]

Hi, you should check line 11 to choose which GPU(s) are suite best for you. By default, I choose the first one, you can replace it by using all GPUs that you have by this: tf.config.experimental.set_memory_growth(physical_devices, True)

Gives an error:
ValueError: Unrecognized device: [PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
the physical_devices[0] works, but is terribly slow at around 2 FPS (I'm using the Jetson AGX Orin)