A collection of machine learning models optimized for Arm IP.
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (AUC) |
---|---|---|---|---|---|---|---|
MicroNet Large INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.968 |
MicroNet Medium INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.963 |
MicroNet Small INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.955 |
Dataset: Dcase 2020 Task 2 Slide Rail
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (Top 1 Accuracy) |
---|---|---|---|---|---|---|---|
MobileNet v2 1.0 224 INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.697 |
MobileNet v2 1.0 224 UINT8 | UINT8 | TensorFlow Lite | ✖️ | ✖️ | ✔️ | ✔️ | 0.708 |
Dataset: ILSVRC 2012
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (Accuracy) |
---|---|---|---|---|---|---|---|
CNN Large INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.931 |
CNN Medium INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.911 |
CNN Small INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.912 |
DNN Large INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.863 |
DNN Medium INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.844 |
DNN Small INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.825 |
DS-CNN Clustered FP32 * | FP32 | TensorFlow Lite | ✔️ | ✖️ | ✔️ | ✖️ | 0.950 |
DS-CNN Clustered INT8 * | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.940 |
DS-CNN Large INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ HERO | ✔️ | ✔️ | 0.946 |
DS-CNN Medium INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ HERO | ✔️ | ✔️ | 0.941 |
DS-CNN Small INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ HERO | ✔️ | ✔️ | 0.935 |
MicroNet Large INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.965 |
MicroNet Medium INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.958 |
MicroNet Small INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.953 |
Dataset: Google Speech Commands Test Set
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (Average Pesq) |
---|---|---|---|---|---|---|---|
RNNoise INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 2.945 |
Dataset: Noisy Speech Database For Training Speech Enhancement Algorithms And Tts Models
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (mAP) |
---|---|---|---|---|---|---|---|
SSD MobileNet v1 FP32 * | FP32 | TensorFlow Lite | ✔️ | ✖️ | ✔️ | ✖️ | 0.210 |
SSD MobileNet v1 INT8 * | INT8 | TensorFlow Lite | ✔️ | ✖️ | ✔️ | ✖️ | 0.234 |
SSD MobileNet v1 UINT8 * | UINT8 | TensorFlow Lite | ✖️ | ✖️ | ✔️ | ✖️ | 0.180 |
YOLO v3 Tiny FP32 * | FP32 | TensorFlow Lite | ✔️ | ✖️ | ✔️ | ✖️ | 0.331 |
Dataset: COCO Validation 2017
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (LER) |
---|---|---|---|---|---|---|---|
Wav2letter INT8 | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.0877 |
Wav2letter Pruned INT8 * | INT8 | TensorFlow Lite | ✔️ | ✔️ | ✔️ | ✔️ | 0.0783 |
Dataset: LibriSpeech
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (PSNR) |
---|---|---|---|---|---|---|---|
SESR INT8 ** | INT8 | TensorFlow Lite | ✔️ | ✖️ | ✔️ HERO | ✖️ | 35.00dB |
Dataset: DIV2K
Network | Type | Framework | Cortex-A | Cortex-M | Mali GPU | Ethos U | Score (Accuracy) |
---|---|---|---|---|---|---|---|
MicroNet VWW-2 INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.768 |
MicroNet VWW-3 INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.855 |
MicroNet VWW-4 INT8 | INT8 | TensorFlow Lite | ✖️ | ✔️ | ✔️ | ✔️ | 0.822 |
Dataset: Visual Wake Words
- ✔️ - Will run on this platform.
- ✖️ - Will not run on this platform.
*
- Code to recreate model available.**
- This model has a large memory footprint – it will not run on all platforms.
Apache-2.0 unless otherwise explicitly stated.