Torq Models Sources
Collection
Compiler inputs used to generate models in the Torq Models collection โข 7 items โข Updated โข 1
How to use Synaptics/MobileNetV2 with Keras:
# !pip install -U keras tensorflow huggingface_hub
# Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here;
# "jax" and "torch" also work for computation once TensorFlow is installed.
import os
os.environ["KERAS_BACKEND"] = "tensorflow"
import keras
model = keras.saving.load_model("hf://Synaptics/MobileNetV2")
This model - MobileNetV2 is generated from tf.keras.applications
using 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
published by Google. This model uses v1 tflite quantization.