|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
library_name: keras |
|
|
tags: |
|
|
- tests |
|
|
- tf_model_zoo |
|
|
--- |
|
|
# MobileNetV2 |
|
|
|
|
|
This model - MobileNetV2 is generated from `tf.keras.applications` |
|
|
using [tf_model_generator.py](https://github.com/syna-astra-dev/iree-synaptics-synpu/blob/main/tests/model_generator/tf_model_generator.py). |
|
|
The dataset for int8 quantization is done using random data. |
|
|
|
|
|
Available formats: int16, int8, float32, float16 |
|
|
|
|
|
The `kaggle.tflite` model is the [original quantized model](https://www.kaggle.com/models/tensorflow/mobilenet-v2/tfLite/1-0-224-quantized) |
|
|
published by Google. This model uses v1 tflite quantization. |
|
|
|
