Upload New File

iot/InspBot/Model_diseases_detection.ipynb

+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "accelerator": "GPU"
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Ie5uLDH4uzAp"
+      },
+      "source": [
+        "# clone YOLOv5 repository\n",
+        "!git clone https://github.com/ultralytics/yolov5  # clone repo\n",
+        "%cd yolov5\n",
+        "!git reset --hard fbe67e465375231474a2ad80a4389efc77ecff99"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "wbvMlHd_QwMG"
+      },
+      "source": [
+        "# install dependencies as necessary\n",
+        "!pip install -qr requirements.txt  # install dependencies (ignore errors)\n",
+        "import torch\n",
+        "\n",
+        "from IPython.display import Image, clear_output  # to display images\n",
+        "from utils.downloads import attempt_download  # to download models/datasets\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'))"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Knxi2ncxWffW"
+      },
+      "source": [
+        "#follow the link below to get the download code from from Roboflow\n",
+        "!pip install -q roboflow\n",
+        "from roboflow import Roboflow\n",
+        "rf = Roboflow(model_format=\"yolov5\", notebook=\"roboflow-yolov5\")"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Ug_PhK1oqwQA"
+      },
+      "source": [
+        "%cd /content/yolov5\n",
+        "!pip install roboflow\n",
+        "\n",
+        "from roboflow import Roboflow\n",
+        "rf = Roboflow(api_key=\"UHsNPABfqFybAyjVrBXT\")\n",
+        "project = rf.workspace(\"agroengine\").project(\"diseases-detection\")\n",
+        "dataset = project.version(2).download(\"yolov5\")"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "ZZ3DmmGQztJj"
+      },
+      "source": [
+        "# this is the YAML file Roboflow wrote for that i am loading into this notebook with our data\n",
+        "%cat {dataset.location}/data.yaml"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# define number of classes based on YAML\n",
+        "import yaml\n",
+        "with open(dataset.location + \"/data.yaml\", 'r') as stream:\n",
+        "    num_classes = str(yaml.safe_load(stream)['nc'])"
+      ],
+      "metadata": {
+        "id": "YN1eri9udgKg"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#this is the model configuration i will use for this model.\n",
+        "%cat /content/yolov5/models/yolov5s.yaml"
+      ],
+      "metadata": {
+        "id": "qFkK2SyZdtQX"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#customize iPython writefile so i can write variables\n",
+        "from IPython.core.magic import register_line_cell_magic\n",
+        "\n",
+        "@register_line_cell_magic\n",
+        "def writetemplate(line, cell):\n",
+        "    with open(line, 'w') as f:\n",
+        "        f.write(cell.format(**globals()))"
+      ],
+      "metadata": {
+        "id": "J2Mwtj4VXQ5W"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "%%writetemplate /content/yolov5/models/custom_yolov5s.yaml\n",
+        "\n",
+        "# parameters\n",
+        "nc: {num_classes}  # number of classes\n",
+        "depth_multiple: 0.33  # model depth multiple\n",
+        "width_multiple: 0.50  # layer channel multiple\n",
+        "\n",
+        "# anchors\n",
+        "anchors:\n",
+        "  - [10,13, 16,30, 33,23]  # P3/8\n",
+        "  - [30,61, 62,45, 59,119]  # P4/16\n",
+        "  - [116,90, 156,198, 373,326]  # P5/32\n",
+        "\n",
+        "# YOLOv5 backbone\n",
+        "backbone:\n",
+        "  # [from, number, module, args]\n",
+        "  [[-1, 1, Focus, [64, 3]],  # 0-P1/2\n",
+        "   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4\n",
+        "   [-1, 3, BottleneckCSP, [128]],\n",
+        "   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8\n",
+        "   [-1, 9, BottleneckCSP, [256]],\n",
+        "   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16\n",
+        "   [-1, 9, BottleneckCSP, [512]],\n",
+        "   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32\n",
+        "   [-1, 1, SPP, [1024, [5, 9, 13]]],\n",
+        "   [-1, 3, BottleneckCSP, [1024, False]],  # 9\n",
+        "  ]\n",
+        "\n",
+        "# YOLOv5 head\n",
+        "head:\n",
+        "  [[-1, 1, Conv, [512, 1, 1]],\n",
+        "   [-1, 1, nn.Upsample, [None, 2, 'nearest']],\n",
+        "   [[-1, 6], 1, Concat, [1]],  # cat backbone P4\n",
+        "   [-1, 3, BottleneckCSP, [512, False]],  # 13\n",
+        "\n",
+        "   [-1, 1, Conv, [256, 1, 1]],\n",
+        "   [-1, 1, nn.Upsample, [None, 2, 'nearest']],\n",
+        "   [[-1, 4], 1, Concat, [1]],  # cat backbone P3\n",
+        "   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)\n",
+        "\n",
+        "   [-1, 1, Conv, [256, 3, 2]],\n",
+        "   [[-1, 14], 1, Concat, [1]],  # cat head P4\n",
+        "   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)\n",
+        "\n",
+        "   [-1, 1, Conv, [512, 3, 2]],\n",
+        "   [[-1, 10], 1, Concat, [1]],  # cat head P5\n",
+        "   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)\n",
+        "\n",
+        "   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)\n",
+        "  ]"
+      ],
+      "metadata": {
+        "id": "JsjNhEHOXUIj"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "1NcFxRcFdJ_O"
+      },
+      "source": [
+        "# train yolov5s on custom data for 100 epochs\n",
+        "# time its performance\n",
+        "%%time\n",
+        "%cd /content/yolov5/\n",
+        "!python train.py --img 416 --batch 16 --epochs 100 --data {dataset.location}/data.yaml --cfg ./models/custom_yolov5s.yaml --weights '' --name yolov5s_results  --cache"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "C60XAsyv6OPe"
+      },
+      "source": [
+        "from utils.plots import plot_results  # plot results.txt as results.png\n",
+        "Image(filename='/content/yolov5/runs/train/yolov5s_results/results.png', width=1000)  # view results.png"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "W40tI99_7BcH"
+      },
+      "source": [
+        "# print out an augmented training example\n",
+        "print(\"GROUND TRUTH AUGMENTED TRAINING DATA:\")\n",
+        "Image(filename='/content/yolov5/runs/train/yolov5s_results/train_batch0.jpg', width=900)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "yIEwt5YLeQ7P"
+      },
+      "source": [
+        "# trained weights are saved by default in our weights folder\n",
+        "%ls runs/"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "4SyOWS80qR32"
+      },
+      "source": [
+        "%ls runs/train/yolov5s_results/weights"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "9nmZZnWOgJ2S"
+      },
+      "source": [
+        "%cd /content/yolov5/\n",
+        "!python detect.py --weights runs/train/yolov5s_results/weights/best.pt --img 416 --conf 0.4 --source /content/yolov5/diseases-detection-2/test/images"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "odKEqYtTgbRc"
+      },
+      "source": [
+        "#display inference on ALL test images\n",
+        "#this looks much better with longer training above\n",
+        "\n",
+        "import glob\n",
+        "from IPython.display import Image, display\n",
+        "\n",
+        "for imageName in glob.glob('/content/yolov5/runs/detect/exp/*.jpg'): #assuming JPG\n",
+        "    display(Image(filename=imageName))\n",
+        "    print(\"\\n\")"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "YH4CTzDRh00g"
+      },
+      "source": [
+        "from google.colab import drive\n",
+        "drive.mount('/content/gdrive')"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "1x_wg3VeiXMW"
+      },
+      "source": [
+        "%cp /content/yolov5/runs/train/yolov5s_results/weights/best.pt /content/gdrive/My\\ Drive"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}
\ No newline at end of file