tflite
ARMv8 Cortex-A78E testing with a NVIDIA Jetson AGX Orin Developer Kit (36.3.0-gcid-36191598 BIOS) and Orin on Ubuntu 22.04 via the Phoronix Test Suite.


all of them: 

	Processor: ARMv8 Cortex-A78E @ 2.20GHz (12 Cores), Motherboard: NVIDIA Jetson AGX Orin Developer Kit (36.3.0-gcid-36191598 BIOS), Memory: 30GB, Disk: 1000GB Samsung SSD 960 EVO 1TB + 64GB G1M15M, Graphics: Orin, Network: Realtek RTL8822CE 802.11ac PCIe

	OS: Ubuntu 22.04, Kernel: 5.15.136-tegra (aarch64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA, Vulkan: 1.3.251, Compiler: GCC 11.4.0 + CUDA 12.2, File-System: ext4, Screen Resolution: 6582x1234


TensorFlow Lite 2022-05-18
Model: SqueezeNet
Microseconds < Lower Is Better
all of them . 6212.21 |========================================================


TensorFlow Lite 2022-05-18
Model: Inception V4
Microseconds < Lower Is Better
all of them . 84257.5 |========================================================


TensorFlow Lite 2022-05-18
Model: NASNet Mobile
Microseconds < Lower Is Better
all of them . 21324.4 |========================================================


TensorFlow Lite 2022-05-18
Model: Mobilenet Float
Microseconds < Lower Is Better
all of them . 4698.18 |========================================================


TensorFlow Lite 2022-05-18
Model: Mobilenet Quant
Microseconds < Lower Is Better
all of them . 2522.19 |========================================================


TensorFlow Lite 2022-05-18
Model: Inception ResNet V2
Microseconds < Lower Is Better
all of them . 78285.9 |========================================================