ML Bench

Machine Learning Benchmark Tool (ML Bench) (AI Benchmark Tool)

Supported models :

- MobileNet v1

- MobileNet v2

- Inception v3

- Resnet v2 50

- SSD Mobilenet v1 (Object Detection)

Supported runtime :

- Tensorflow Lite

- Tensorflow Mobile

- Android NN

- SNPE (for Qualcomm)

SideLoad Support:

How to side load your model :

1. Convert your model to tflite (using toco) or dlc (using snpe conversion tool).

2. On your local machine, create [Model Name] directory

3. Copy your model file to the directory created in step 2

4. Create a file called meta-data.json in the [Model Name] directory

example of meta-data.json :

{

"xres" : 299,

"yres" : 299,

"depth" : 3,

"input_type" : "float",

"output_type" : "float",

"input_name" : "input:0",

"output_name" : "InceptionV3/Predictions/Reshape_1:0",

"image_mean" : 0,

"image_std" : 0,

"accelerator":"dsp",

}

5. push [Model Name] directory to the target device using below command

adb push ./[Model Name] /sdcard/Android/data/com.etinum.mlbench/files/models/

Strumento di benchmark Machine Learning (ML Bench) (Strumento di benchmark AI)

Modelli supportati:

 - MobileNet v1

 - MobileNet v2

 - Inception v3

 - Resnet v2 50

 - SSD Mobilenet v1 (Object Detection)

Runtime supportato:

 - Tensorflow Lite

 - Tensorflow Mobile

 - Android NN

 - SNPE (per Qualcomm)

Supporto SideLoad:

      Come caricare sul lato il tuo modello:

1. Converti il ​​tuo modello in tflite (usando toco) o dlc (usando lo strumento di conversione snpe).

2. Sulla macchina locale, creare la directory [Nome modello]

3. Copiare il file del modello nella directory creata nel passaggio 2

4. Creare un file chiamato meta-data.json nella directory [Nome modello]

esempio di meta-data.json:

{

"xres": 299,

"yres": 299,

"profondità": 3,

"input_type": "float",

"output_type": "float",

"input_name": "input: 0",

"output_name": "InceptionV3 / Predictions / Reshape_1: 0",

"image_mean": 0,

"image_std": 0,

"Acceleratore": "DSP",

}

5. premere la directory [Nome modello] sul dispositivo di destinazione usando il comando di sotto

adb push ./[Model Name] /sdcard/Android/data/com.etinum.mlbench/files/models/

Machine Learning Benchmark Tool (ML Bench) (AI Benchmark Tool)

Supported models :

- MobileNet v1

- MobileNet v2

- Inception v3

- Resnet v2 50

- SSD Mobilenet v1 (Object Detection)

Supported runtime :

- Tensorflow Lite

- Tensorflow Mobile

- Android NN

- SNPE (for Qualcomm)

SideLoad Support:

How to side load your model :

1. Convert your model to tflite (using toco) or dlc (using snpe conversion tool).

2. On your local machine, create [Model Name] directory

3. Copy your model file to the directory created in step 2

4. Create a file called meta-data.json in the [Model Name] directory

example of meta-data.json :

{

"xres" : 299,

"yres" : 299,

"depth" : 3,

"input_type" : "float",

"output_type" : "float",

"input_name" : "input:0",

"output_name" : "InceptionV3/Predictions/Reshape_1:0",

"image_mean" : 0,

"image_std" : 0,

"accelerator":"dsp",

}

5. push [Model Name] directory to the target device using below command

adb push ./[Model Name] /sdcard/Android/data/com.etinum.mlbench/files/models/