Skip to content

Instantly share code, notes, and snippets.

@karthick965938
Created December 21, 2020 06:08
Show Gist options
  • Save karthick965938/ad204df98a8da4954fde7ffd161d53a4 to your computer and use it in GitHub Desktop.
Save karthick965938/ad204df98a8da4954fde7ffd161d53a4 to your computer and use it in GitHub Desktop.
short.ipynb
Display the source blob
Display the rendered blob
Raw
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "short.ipynb",
"provenance": [],
"authorship_tag": "ABX9TyOj4fpuELdA/4bwqqcc9IzE",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/karthick965938/ad204df98a8da4954fde7ffd161d53a4/short.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ZsRD4tlLtzaF"
},
"source": [
"Install Detecto"
]
},
{
"cell_type": "code",
"metadata": {
"id": "w9L_9znAUzym"
},
"source": [
"import os\n",
"from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"os.chdir('/content/drive/My Drive/object_detection')\n",
"!pip install detecto"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "lTgoEj11uAc3"
},
"source": [
"Start the train your model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "6LfC3qnltVxO"
},
"source": [
"#train your model\n",
"from detecto import core, utils, visualize\n",
"#mention you dataset path\n",
"dataset = core.Dataset('images/')\n",
"#mention you object label here\n",
"model = core.Model(['cat'])\n",
"model.fit(dataset)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "AgxMIuo4uI3a"
},
"source": [
"Test your trained model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "1vMGKpSFtV_q"
},
"source": [
"# Specify the path to your image\n",
"from detecto import core, utils, visualize\n",
"image = utils.read_image('animals/cat48.jpg')\n",
"predictions = model.predict(image)\n",
"# predictions format: (labels, boxes, scores)\n",
"labels, boxes, scores = predictions\n",
"# ['alien', 'bat', 'bat']\n",
"print(labels) \n",
"print(boxes)\n",
"# tensor([0.9952, 0.9837, 0.5153])\n",
"print(scores)\n",
"visualize.show_labeled_image(image, boxes, labels)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "1A2z_X-GuXKb"
},
"source": [
"Save your trained model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "zusZcJXussBA"
},
"source": [
"model.save('cat_model_weights.pth')\n",
"#use this comment to save the custom model file"
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment