{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "bac02017aa438779",
   "metadata": {},
   "source": "# Command Line Usage"
  },
  {
   "cell_type": "markdown",
   "id": "736eed409d1d326e",
   "metadata": {},
   "source": [
    "Once the **eIQ Vela** package is installed, you can use it like any other command line tool.\n",
    "The following section demonstrates the basic workflow for converting TF Lite models for use on i.MX 93."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16871d040f4a165e",
   "metadata": {},
   "source": [
    "First, let's prepare the model we want to convert."
   ]
  },
  {
   "cell_type": "code",
   "id": "665aef5b44769bab",
   "metadata": {},
   "source": [
    "from pathlib import Path\n",
    "import requests\n",
    "\n",
    "# Change this if you have your own model.\n",
    "model_path = Path(\"my_path_to_tflite_model.tflite\")"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "code",
   "id": "cc63268fb63e5418",
   "metadata": {},
   "source": [
    "# Alternatively download example model.\n",
    "example_model_url = \"https://eiq.nxp.com/training-materials/_misc/models/mobilenet_v3-small_224_1.0_uint8.tflite\"\n",
    "\n",
    "with open(model_path, \"wb\") as f:\n",
    "    response = requests.get(\n",
    "        url=example_model_url\n",
    "    )\n",
    "    f.write(response.content)\n",
    "\n",
    "    if response.status_code != 200:\n",
    "        print(f\"Failed to download model: {response.content}\")\n",
    "    else:\n",
    "        print(f\"Model downloaded and saved to {model_path} file.\")"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "id": "ab5f67fcb111403",
   "metadata": {},
   "source": [
    "The simplest way to run a Vela conversion is to provide the model you want to convert along with an output directory.\n",
    "After the conversion completes, you’ll find the generated model in the specified directory."
   ]
  },
  {
   "cell_type": "code",
   "id": "48f1f7d3991fd326",
   "metadata": {},
   "source": [
    "# Change this to your path\n",
    "output_dir = Path(\"vela_output_dir\")\n",
    "!vela --output-dir $output_dir $model_path\n",
    "\n",
    "print(f\"Converted model can be found in {output_dir} folder.\")"
   ],
   "outputs": [],
   "execution_count": null
  },
  {
   "cell_type": "markdown",
   "id": "1ec8ab4eccf1a7b5",
   "metadata": {},
   "source": [
    "There are many additional options available for conversion and model performance analysis.\n",
    "To see the full list, check the command’s help flag:"
   ]
  },
  {
   "cell_type": "code",
   "id": "99c538d5-0d45-436a-85e1-1c05edc237a8",
   "metadata": {},
   "source": [
    "!vela -h"
   ],
   "outputs": [],
   "execution_count": null
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}