yolov5/demo.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# YOLO 目标检测"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### YOLO —— 目标检测中最常用的算法"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### YOLO网络主要由三个主要组件组成。\n",
    "\n",
    "#### 1）Backbone -在不同图像细粒度上聚合并形成图像特征的卷积神经网络。\n",
    "\n",
    "#### 2）Neck：一系列混合和组合图像特征的网络层，并将图像特征传递到预测层。\n",
    "\n",
    "#### 3）Head： 对图像特征进行预测，生成边界框和并预测类别。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![image.png](https://pic.rmb.bdstatic.com/bjh/70af0053d64df5770cbe1ca3b16e2352.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](https://user-images.githubusercontent.com/26833433/82944393-f7644d80-9f4f-11ea-8b87-1a5b04f555f1.jpg?raw=true)"
   ]
  },
  {
   "attachments": {
    "ac7c3c5f-9e5e-4b53-8c2a-ca54b90d52b9.png": {
     "image/png": "iVBORw0KGgoAAAANSUhEUgAACWAAAASwCAYAAAB/pHGBAAAgAElEQVR4Aezdd5BU15n38fXafr2217X/eKt2t1zlqrXXkhAIZZRzjlZyUDIZBAKESAJEViIIEUSQSAJEzkkIJHIc0hAn5xkYJuc8Pc9bz5V71Ldvx+kw3TPfW9XV6d5zz/2cMz2D+qfn/IuwIYBASAWampokMTFRZsyYEdTbrFmzZN68ebJo0SJZvny5bNy4UQ4fPiypqalSUVER0muicQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAIEfBP4FCAQQCK2ABrCOHz8uXbt2Demtd+/eMmLECJk2bZqsWLFCTp8+LZWVlaG9OFpHAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQTauQABrHY+Abj80AuEK4DlGPDSMNa4ceNk/fr1RkWs0F9leM6glg0NDVJXV2e61dfXi81m86sTwWzLrxOzMwIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAgi0KQECWG1qOLmYSBRojQCWPYzVv39/Y5nC5OTkSKTxu09lZWXGMou65KLjbevWrZKRkeFXe8Fsy68TszMCCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIItCkBAlhtaji5mEgUaM0Algax3nrrLSOElZaWFok8fvXpypUr8sUXX1iWchw1apTExMS0Wlt+nZidEUAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQKBNCRDAalPDycVEooCnANY777xjBIp0qUBfbuvWrZPVq1cb1Z8WLVokn3/+uUyYMEEGDBgg3bp1swSTHCthrVixQqqqqiKRyOc+EcDymYodEUAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQCBMAgSwwgTNadqvgKcA1rhx4+Ts2bNSXV3t000DVBUVFVJcXCz5+fmSlZUl58+fl3379smSJUtk2LBhbkNYY8eONc4VzSNBACuaR4++I4AAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAggg0DYFCGC1zXHlqiJIwFMAS6tXxcXFBdxbm80mBQUF8v333xsVseyVrxzv+/btK0uXLo3qKlgEsAKeKjSAAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAkEWIIAVZFCaQ8BZIBwBLPs5tULW/v373VbC+uCDDyQ1NdW+e9TdE8CKuiGjwwgggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCLR5AQJYbX6IucDWFghnAEuvVSthaaUrx+pX9scjR46Uo0ePtjZJi89PAKvFdByIAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAiESIIAVIliaRcAuEO4AVkNDgxw5ckR0yUF78Mp+P3jwYNm5c6e9a1F3TwAr6oaMDiOAAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIINDmBQhgtfkh5gJbWyDcASy93kuXLsnw4cMtAax+/frJmjVrWpukxecngNViOg5EAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAgRAJEMAKESzNImAXaI0AVlJSkowfP95lAGv16tX2rgV0b7PZpKSkxAh7HThwQL799lvZvHmzrF27VjZu3Ci7du2SQ4cOycWLF6W4uFjUwZ9N96+qqjKWVNRlFfWmwbKZM2darkvDZt99951pX92/rKzMOG8w2/LnGnTfUDu56k9jY6OUl5e79XA+prKyUhITE43lKb/55htZt26d6H1qaqrzrjxHAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAScBAlhOIDxFINgCrRHA0jDNuHHjLEGld955xwjWBHKNtbW1kpycLDt27JCFCxfKhx9+KMOGDZMBAwZI7969pXv37tKrVy8ZOHCgUYXrgw8+kEWLFsnu3buN42pqanw6ve536tQpmTdvXvPts88+k6FDh1qu66233hI9j+O++lj7WF1dLcFsy6fOi0i4nFz1RwNvGkhz52E/RperzMjIkA0bNsjkyZNl5MiR0r9/f+nRo4cxdnv37rXvyj0CCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIuBEggOUGhpcRCJZAawSwtOrUkCFDLEElDdgcO3asRZemVZV0CUCtjDRlyhR5++23pVu3bpZzdO3a1fKahrIGDRokU6dOla1bt0p2drbXilhawWnLli2Wtly17+61Tz/9VEpLS41qUMFqyxteuJ1c9efy5csyd+5ci9306dONqmB6TEVFhRw/flxmzJhhhK6cDXX+aGiODQEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQ8CxDA8uzDuwgELBDuAFZdXZ0cPHjQqEblHKqZMGGCJCQk+H1N2mZcXJxRUWnw4MGWYI/zedw918CWVsbScNDJkyeNJQbddSYaA1it4eTKz1sAS5cc1DkyduxYo2KZq/EigOVKltcQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBCwChDAsprwCgJBFQh3AOvq1avG0oDOoRpdFlCXpNOKUP5supTeuXPnjOpVPXv2bHH4yrE/2pfx48eLLnHnbknCaAtgtZaTq7H0FMDS+XH06FEjfOU4Js6PCWC5kuU1BBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEErAIEsKwmvIJAUAXCGcDSykbff/+9uKpSZV9+UPvj66YVnTR89fHHH0uPHj0s4SutaPXWW2/J6NGjZdq0abJo0SJZuXKlLF261KhyNWnSJON953CPPtdlCceMGSOHDx+W+vp6S5eqqqqMKk3ahv2mFZt06UPn9nr37i0jRoxo3s++v/ZFTYLZlqWjItKaTq764y6ApUtA6rKDH3zwgdflIwlguZLlNQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBKwCBLCsJryCQFAFwhHA0nMUFhbKt99+67KykYakNBSlVaV83bTN9PR0mTFjhstl6rSK1cSJE2Xbtm1y+vRpSU5Olry8PCkrK5OioiLJycmRixcvGn2aOXOm9O3b1xKc0lCXhoHOnj1r6VZjY6Pk5+cbbWg7etNl8yZPnmxpR8NC69evN+2r+2dkZEhDQ4MEsy3njra2k3N/9Lm7AJaG8GbPnm0K02mIrk+fPjJ8+HD56KOPjODcV199JWvXrpULFy64ap7XEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQQMBBgACWAwYPEQiFQCgCWDabzVi6T4NOCQkJsmfPHmPZwWHDhlnCSRqU+vTTTyUxMdGvy9O216xZY4RznCtOaRWq+fPnG9WxqqurPbar1aHS0tKMyliuKnNp9aovv/xSSkpKPLajb165ckW++OILyzWOGjVKYmJivB7vuEOw2opEJ3cBLJ0L/fv3b/bT51otTEN06hcfHy/Z2dlGmK+4uNioHuZoxmMEEEAAAQQQQAABBBBAAAEEEEAAAQQQQAABBBBAAAEEEEAAAQQQsAoQwLKa8AoCQRXwFMDSQNLChQtly5YtPt02b94sGzZskFWrVhkVrTSM9Mknn8i7775rqmpkD0xp5SutPqWVjLQSlK+bhqZ0qTqtLGVvy34/YMAA49xZWVmiQTBfNjXQalZaVclVJaz33ntPjhw54rWpYIWm9ETBaCtSndwFsOxjqPcaxJo3b54RoqupqfFqzw4IIIAAAggggAACCCCAAAIIIIAAAggggAACCCCAAAIIIIAAAggg4FqAAJZrF15FIGgCngJY3bt3F61CpEvA+Xrr2bOn6LJxjmEa58e6tJ9WhVq3bp2kpKQYS/D5c0G5ublGVSrndvXc06dPFw1f+bupgx43Z84c
    }
   },
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![image.png](attachment:ac7c3c5f-9e5e-4b53-8c2a-ca54b90d52b9.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<center><h2>YOLOv5 详情</h2></center>\n",
    "<br>\n",
    "\n",
    "| Model | AP<sup>val</sup> | AP<sup>test</sup> | AP<sub>50</sub> | Speed<sub>GPU</sub> | FPS<sub>GPU</sub> || params | FLOPS |\n",
    "|---------- |------ |------ |------ | -------- | ------| ------ |------  |  :------: |\n",
    "| [YOLOv5s](https://github.com/ultralytics/yolov5/releases/tag/v3.0)(our)    | 37.0     | 37.0     | 56.2     | **2.4ms** | **416** || 7.5M   | 13.2B\n",
    "| [YOLOv5m](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | 44.3     | 44.3     | 63.2     | 3.4ms     | 294     || 21.8M  | 39.4B\n",
    "| [YOLOv5l](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | 47.7     | 47.7     | 66.5     | 4.4ms     | 227     || 47.8M  | 88.1B\n",
    "| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/tag/v3.0)(our)    | **49.2** | **49.2** | **67.7** | 6.9ms     | 145     || 89.0M  | 166.4B\n",
    "| | | | | | || |\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 导入相关库"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "colab_type": "code",
    "id": "wbvMlHd_QwMG",
    "outputId": "669566b2-391f-4596-f290-110e2e177946"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Setup complete. Using torch 1.6.0 CPU\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import os\n",
    "from IPython.display import Image, clear_output  # to display images\n",
    "from utils.google_utils import gdrive_download  # to download models/datasets\n",
    "\n",
    "import numpy as np\n",
    "from PIL import Image as PImage\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "clear_output()\n",
    "print('Setup complete. Using torch %s %s' % (torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "N3qM6T0W53gh"
   },
   "source": [
    "## 原始图像展示"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['inference/images/office1.jpg', 'inference/images/zidane.jpg', 'inference/images/2.jpg', 'inference/images/4.jpg', 'inference/images/office2.jpg', 'inference/images/9.jpg', 'inference/images/5.jpg', 'inference/images/1.jpg', 'inference/images/bus.jpg', 'inference/images/7.jpg', 'inference/images/all.jpg', 'inference/images/3.jpg']\n",
      "12\n"
     ]
    }
   ],
   "source": [
    "img_dir = \"inference/images/\"\n",
    "img_name_lits = os.listdir(img_dir)\n",
    "# print(img_name_lits)\n",
    "\n",
    "img_path_lists = [img_dir+img_name for img_name in img_name_lits]\n",
    "print(img_path_lists)\n",
    "\n",
    "img_lists = [PImage.open(img_path) for img_path in img_path_lists]\n",
    "print(len(img_lists))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "正在加载第 1 图像\n",
      "正在加载第 2 图像\n",
      "正在加载第 3 图像\n",
      "正在加载第 4 图像\n",
      "正在加载第 5 图像\n",
      "正在加载第 6 图像\n",
      "正在加载第 7 图像\n",
      "正在加载第 8 图像\n",
      "正在加载第 9 图像\n",
      "正在加载第 10 图像\n",
      "正在加载第 11 图像\n",
      "正在加载第 12 图像\n"
     ]
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 3600x3600 with 12 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(50,50)) #设置窗口大小\n",
    "for idx,img in enumerate(img_lists):\n",
    "    print(f\"正在加载第 {idx+1} 图像\")\n",
    "    plt.subplot(4,4,idx+1)\n",
    "    plt.imshow(img), plt.axis('off')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 模型推理"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.2, device='', img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='inference/images/', update=False, view_img=False, weights=['yolov5x.pt'])\n",
      "Using CPU\n",
      "\n",
      "Fusing layers... \n",
      "Model Summary: 284 layers, 8.89222e+07 parameters, 8.45317e+07 gradients\n",
      "image 1/12 /root/yolov5/inference/images/1.jpg: 512x640 11 persons, 2 backpacks, 3 bottles, 1 cups, 22 chairs, 1 potted plants, 10 tvs, 12 laptops, 3 mouses, 1 remotes, 6 keyboards, 3 cell phones, 1 clocks, Done. (1.663s)\n",
      "image 2/12 /root/yolov5/inference/images/2.jpg: 512x640 1 cups, 1 oranges, 1 potted plants, 1 tvs, 1 laptops, 2 mouses, 1 keyboards, 1 books, Done. (1.635s)\n",
      "image 3/12 /root/yolov5/inference/images/3.jpg: 512x640 5 persons, 1 backpacks, 8 chairs, 3 potted plants, 6 tvs, 4 laptops, 1 keyboards, Done. (1.642s)\n",
      "image 4/12 /root/yolov5/inference/images/4.jpg: 512x640 5 persons, 2 backpacks, 1 handbags, 1 suitcases, 1 cups, 6 chairs, 1 potted plants, 1 dining tables, 5 tvs, 1 laptops, Done. (1.642s)\n",
      "image 5/12 /root/yolov5/inference/images/5.jpg: 512x640 16 persons, 3 cups, 21 chairs, 2 potted plants, 22 tvs, 17 laptops, 1 mouses, 4 keyboards, Done. (1.632s)\n",
      "image 6/12 /root/yolov5/inference/images/7.jpg: 512x640 34 persons, 1 traffic lights, 1 backpacks, 11 handbags, 1 cell phones, Done. (1.655s)\n",
      "image 7/12 /root/yolov5/inference/images/9.jpg: 512x640 3 persons, 1 backpacks, 1 cups, 4 chairs, 2 potted plants, 9 laptops, 1 mouses, 2 keyboards, 1 cell phones, Done. (1.636s)\n",
      "image 8/12 /root/yolov5/inference/images/all.jpg: 512x640 24 persons, 1 ties, Done. (1.630s)\n",
      "image 9/12 /root/yolov5/inference/images/bus.jpg: 640x512 4 persons, 1 bicycles, 1 buss, 1 ties, Done. (1.671s)\n",
      "image 10/12 /root/yolov5/inference/images/office1.jpg: 512x640 10 persons, 4 backpacks, 2 bottles, 7 chairs, 2 potted plants, 1 dining tables, 4 tvs, 6 laptops, 3 keyboards, 1 clocks, Done. (1.679s)\n",
      "image 11/12 /root/yolov5/inference/images/office2.jpg: 512x640 9 persons, 6 backpacks, 1 suitcases, 3 bottles, 13 chairs, 3 potted plants, 5 tvs, 3 laptops, 3 keyboards, Done. (1.671s)\n",
      "image 12/12 /root/yolov5/inference/images/zidane.jpg: 384x640 3 persons, 3 ties, Done. (1.236s)\n",
      "Results saved to inference/output\n",
      "Done. (23.485s)\n"
     ]
    }
   ],
   "source": [
    "!python demo.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 检测完成图像展示"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['inference/output/office1.jpg', 'inference/output/zidane.jpg', 'inference/output/2.jpg', 'inference/output/4.jpg', 'inference/output/office2.jpg', 'inference/output/9.jpg', 'inference/output/5.jpg', 'inference/output/1.jpg', 'inference/output/bus.jpg', 'inference/output/7.jpg', 'inference/output/all.jpg', 'inference/output/3.jpg']\n",
      "12\n",
      "正在加载第 1 结果图像\n",
      "正在加载第 2 结果图像\n",
      "正在加载第 3 结果图像\n",
      "正在加载第 4 结果图像\n",
      "正在加载第 5 结果图像\n",
      "正在加载第 6 结果图像\n",
      "正在加载第 7 结果图像\n",
      "正在加载第 8 结果图像\n",
      "正在加载第 9 结果图像\n",
      "正在加载第 10 结果图像\n",
      "正在加载第 11 结果图像\n",
      "正在加载第 12 结果图像\n",
      "CPU times: user 3.46 s, sys: 292 ms, total: 3.75 s\n",
      "Wall time: 3.74 s\n"
     ]
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 3600x3600 with 12 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "img_dir = \"inference/output/\"\n",
    "img_name_lits = os.listdir(img_dir)\n",
    "# print(img_name_lits)\n",
    "\n",
    "img_path_lists = [img_dir+img_name for img_name in img_name_lits]\n",
    "print(img_path_lists)\n",
    "\n",
    "img_lists = [PImage.open(img_path) for img_path in img_path_lists]\n",
    "print(len(img_lists))\n",
    "plt.figure(figsize=(50,50)) #设置窗口大小\n",
    "for idx,img in enumerate(img_lists):\n",
    "    print(f\"正在加载第 {idx+1} 结果图像\")\n",
    "    plt.subplot(4,4,idx+1)\n",
    "    plt.imshow(img), plt.axis('off')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Image(filename='inference/output/zidane.jpg')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 修改置信度"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### python detect.py --weights yolov5x.pt --conf 0.2 --source inference/images/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='inference/images/zidane.jpg', update=False, view_img=False, weights=['yolov5x.pt'])\n",
      "Using CPU\n",
      "\n",
      "Fusing layers... \n",
      "Model Summary: 284 layers, 8.89222e+07 parameters, 8.45317e+07 gradients\n",
      "image 1/1 /root/yolov5/inference/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (1.394s)\n",
      "Results saved to inference/output\n",
      "Done. (1.428s)\n"
     ]
    }
   ],
   "source": [
    "! python zidane.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/jpeg": "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
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Image(filename='inference/output/zidane.jpg')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 视频检测"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.4, device='', img_size=640, iou_thres=0.5, output='inference/output', save_txt=False, source='inference/videos/videos/ma.mp4', update=False, view_img=False, weights=['yolov5s.pt'])\n",
      "Using CPU\n",
      "\n",
      "Fusing layers... \n",
      "Model Summary: 140 layers, 7.45958e+06 parameters, 6.61683e+06 gradients\n",
      "video 1/1 (1/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.185s)\n",
      "video 1/1 (2/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (3/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (4/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.172s)\n",
      "video 1/1 (5/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (6/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (7/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (8/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.175s)\n",
      "video 1/1 (9/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.172s)\n",
      "video 1/1 (10/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (11/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (12/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (13/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.180s)\n",
      "video 1/1 (14/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (15/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (16/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (17/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (18/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (19/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (20/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 4 horses, Done. (0.171s)\n",
      "video 1/1 (21/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (22/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 4 horses, Done. (0.170s)\n",
      "video 1/1 (23/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 4 horses, Done. (0.170s)\n",
      "video 1/1 (24/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (25/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (26/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.169s)\n",
      "video 1/1 (27/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 2 horses, Done. (0.173s)\n",
      "video 1/1 (28/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.173s)\n",
      "video 1/1 (29/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (30/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (31/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (32/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 4 horses, Done. (0.170s)\n",
      "video 1/1 (33/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (34/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 2 horses, Done. (0.173s)\n",
      "video 1/1 (35/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.172s)\n",
      "video 1/1 (36/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (37/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (38/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (39/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (40/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (41/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.173s)\n",
      "video 1/1 (42/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.174s)\n",
      "video 1/1 (43/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (44/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (45/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (46/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (47/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (48/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (49/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (50/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.169s)\n",
      "video 1/1 (51/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (52/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 4 horses, Done. (0.172s)\n",
      "video 1/1 (53/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 4 horses, Done. (0.172s)\n",
      "video 1/1 (54/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.173s)\n",
      "video 1/1 (55/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (56/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.169s)\n",
      "video 1/1 (57/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (58/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.169s)\n",
      "video 1/1 (59/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (60/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (61/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 3 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (62/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (63/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (64/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (65/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.176s)\n",
      "video 1/1 (66/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.176s)\n",
      "video 1/1 (67/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (68/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.169s)\n",
      "video 1/1 (69/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (70/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (71/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.169s)\n",
      "video 1/1 (72/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.170s)\n",
      "video 1/1 (73/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.176s)\n",
      "video 1/1 (74/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.174s)\n",
      "video 1/1 (75/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (76/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (77/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (78/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (79/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.173s)\n",
      "video 1/1 (80/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.171s)\n",
      "video 1/1 (81/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.171s)\n",
      "video 1/1 (82/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (83/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (84/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (85/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.173s)\n",
      "video 1/1 (86/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.171s)\n",
      "video 1/1 (87/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (88/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (89/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.171s)\n",
      "video 1/1 (90/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (91/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (92/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (93/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (94/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (95/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (96/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (97/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.173s)\n",
      "video 1/1 (98/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.171s)\n",
      "video 1/1 (99/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (100/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (101/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (102/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (103/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (104/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (105/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (106/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 1 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (107/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (108/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (109/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.170s)\n",
      "video 1/1 (110/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.172s)\n",
      "video 1/1 (111/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.172s)\n",
      "video 1/1 (112/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 1 horses, Done. (0.169s)\n",
      "video 1/1 (113/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.172s)\n",
      "video 1/1 (114/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (115/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (116/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "video 1/1 (117/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.173s)\n",
      "video 1/1 (118/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (119/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 2 horses, Done. (0.171s)\n",
      "video 1/1 (120/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.171s)\n",
      "video 1/1 (121/121) /root/yolov5/inference/videos/videos/ma.mp4: 640x384 2 persons, 3 horses, Done. (0.170s)\n",
      "Results saved to inference/output\n",
      "Done. (21.400s)\n"
     ]
    }
   ],
   "source": [
    "!python detect.py --weights yolov5s.pt --conf 0.4 --source inference/videos/videos/ma.mp4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "collapsed_sections": [],
   "include_colab_link": true,
   "name": "YOLOv5 Tutorial",
   "provenance": [],
   "toc_visible": true
  },
  "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}