video-classification-pipeline-transformers.ipynb

video-classification-pipeline-transformers.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyM9NSA5ttaEF4FeOYmn86nH",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/nateraw/91dcb961e231276b2023c0aea56776c9/video-classification-pipeline-transformers.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "rp9ru2SfNMxA"
      },
      "outputs": [],
      "source": [
        "%%capture\n",
        "! pip install git+https://github.com/huggingface/transformers@main#egg=transformers[video]"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "You can also load many other models from the Hub. Check them out [here](https://huggingface.co/models?pipeline_tag=video-classification)."
      ],
      "metadata": {
        "id": "BQZo0NyDPdcG"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers import pipeline\n",
        "\n",
        "# 🤗 Load the pipeline\n",
        "pipe = pipeline('video-classification')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CREbsTxgNSMT",
        "outputId": "0b42fb3f-9e61-497e-f383-bf8717b919e2"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "No model was supplied, defaulted to MCG-NJU/videomae-base-finetuned-kinetics and revision 4800870 (https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics).\n",
            "Using a pipeline without specifying a model name and revision in production is not recommended.\n",
            "/usr/local/lib/python3.8/dist-packages/transformers/models/videomae/feature_extraction_videomae.py:28: FutureWarning: The class VideoMAEFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use VideoMAEImageProcessor instead.\n",
            "  warnings.warn(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 🔥 Predict on video URLs or files\n",
        "pipe('https://huggingface.co/datasets/nateraw/video-demo/resolve/main/archery.mp4')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vabAytKIPQnk",
        "outputId": "4319a10a-7b01-43c5-9a56-4e035f9bd0fb"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[{'score': 0.6418353319168091, 'label': 'archery'},\n",
              " {'score': 0.002652964321896434, 'label': 'riding unicycle'},\n",
              " {'score': 0.0025830131489783525, 'label': 'golf driving'},\n",
              " {'score': 0.002545428927987814, 'label': 'throwing ball'},\n",
              " {'score': 0.0023797592148184776, 'label': 'tobogganing'}]"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    }
  ]
}