{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**step 1:** 安装PyTorch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install torch==1.5.1+cpu torchvision==0.6.1+cpu -f https://download.pytorch.org/whl/torch_stable.html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**step 2:** 安装模型运行相关依赖"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -U -r requirements.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "TACO数据集可以从本人该平台的taco项目从操作获得，所生成的数据集直接放置在根目录下即可**(此处已上传一份本地运行完的数据集)**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "本人还在该项目根目录下存放了taco.zip文件，使用如下语句即可完成解压"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!unzip taco.zip"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**step 3:** 配置文件配置\n",
    "- 将解压后的taco文件夹下taco.yaml文件拷贝至data文件夹下\n",
    "- 修改models文件夹下yolov5s.yaml文件中的nc属性值改为对象类型总数"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**step 4:** 模型训练，训练过程所产生的输出将自动存放于runs文件夹下"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!python train.py --img 320 --batch 4 --epochs 100 --data ./data/taco.yaml --cfg ./models/yolov5s.yaml --device cpu --weights yolov5s.pt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**step 5:** 效果测试，主要利用detect.py对inference/images文件夹下的目标图像进行测试，其结果存放在inference/output文件夹中；在测试前，注意要将runs中的best.pt权重文件放置项目根目录下"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!python detect.py --weights best.pt --img 320 --conf 0.4"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}