{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "cellUniqueIdByVincent": "6f020"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting gradio\n",
      "  Using cached gradio-5.34.2-py3-none-any.whl.metadata (16 kB)\n",
      "Collecting aiofiles<25.0,>=22.0 (from gradio)\n",
      "  Using cached aiofiles-24.1.0-py3-none-any.whl.metadata (10 kB)\n",
      "Collecting anyio<5.0,>=3.0 (from gradio)\n",
      "  Using cached anyio-4.9.0-py3-none-any.whl.metadata (4.7 kB)\n",
      "Collecting fastapi<1.0,>=0.115.2 (from gradio)\n",
      "  Using cached fastapi-0.115.13-py3-none-any.whl.metadata (27 kB)\n",
      "Collecting ffmpy (from gradio)\n",
      "  Using cached ffmpy-0.6.0-py3-none-any.whl.metadata (2.9 kB)\n",
      "Collecting gradio-client==1.10.3 (from gradio)\n",
      "  Using cached gradio_client-1.10.3-py3-none-any.whl.metadata (7.1 kB)\n",
      "Collecting groovy~=0.1 (from gradio)\n",
      "  Using cached groovy-0.1.2-py3-none-any.whl.metadata (6.1 kB)\n",
      "Collecting httpx>=0.24.1 (from gradio)\n",
      "  Using cached httpx-0.28.1-py3-none-any.whl.metadata (7.1 kB)\n",
      "Collecting huggingface-hub>=0.28.1 (from gradio)\n",
      "  Using cached huggingface_hub-0.33.0-py3-none-any.whl.metadata (14 kB)\n",
      "Requirement already satisfied: jinja2<4.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (3.1.4)\n",
      "Requirement already satisfied: markupsafe<4.0,>=2.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (2.1.5)\n",
      "Requirement already satisfied: numpy<3.0,>=1.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (2.1.2)\n",
      "Collecting orjson~=3.0 (from gradio)\n",
      "  Downloading orjson-3.10.18-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (41 kB)\n",
      "Requirement already satisfied: packaging in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (25.0)\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (2.3.0)\n",
      "Requirement already satisfied: pillow<12.0,>=8.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (11.0.0)\n",
      "Requirement already satisfied: pydantic<2.12,>=2.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (2.11.7)\n",
      "Collecting pydub (from gradio)\n",
      "  Using cached pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Collecting python-multipart>=0.0.18 (from gradio)\n",
      "  Using cached python_multipart-0.0.20-py3-none-any.whl.metadata (1.8 kB)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (6.0.2)\n",
      "Collecting ruff>=0.9.3 (from gradio)\n",
      "  Using cached ruff-0.12.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
      "Collecting safehttpx<0.2.0,>=0.1.6 (from gradio)\n",
      "  Using cached safehttpx-0.1.6-py3-none-any.whl.metadata (4.2 kB)\n",
      "Collecting semantic-version~=2.0 (from gradio)\n",
      "  Using cached semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Using cached starlette-0.47.0-py3-none-any.whl.metadata (6.2 kB)\n",
      "Collecting tomlkit<0.14.0,>=0.12.0 (from gradio)\n",
      "  Using cached tomlkit-0.13.3-py3-none-any.whl.metadata (2.8 kB)\n",
      "Requirement already satisfied: typer<1.0,>=0.12 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (0.16.0)\n",
      "Requirement already satisfied: typing-extensions~=4.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from gradio) (4.12.2)\n",
      "Collecting uvicorn>=0.14.0 (from gradio)\n",
      "  Using cached uvicorn-0.34.3-py3-none-any.whl.metadata (6.5 kB)\n",
      "Collecting fsspec (from gradio-client==1.10.3->gradio)\n",
      "  Downloading fsspec-2025.5.1-py3-none-any.whl.metadata (11 kB)\n",
      "Collecting websockets<16.0,>=10.0 (from gradio-client==1.10.3->gradio)\n",
      "  Downloading websockets-15.0.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.8 kB)\n",
      "Requirement already satisfied: idna>=2.8 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from anyio<5.0,>=3.0->gradio) (3.4)\n",
      "Collecting sniffio>=1.1 (from anyio<5.0,>=3.0->gradio)\n",
      "  Using cached sniffio-1.3.1-py3-none-any.whl.metadata (3.9 kB)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Using cached starlette-0.46.2-py3-none-any.whl.metadata (6.2 kB)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pandas<3.0,>=1.0->gradio) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
      "Requirement already satisfied: annotated-types>=0.6.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pydantic<2.12,>=2.0->gradio) (0.7.0)\n",
      "Requirement already satisfied: pydantic-core==2.33.2 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pydantic<2.12,>=2.0->gradio) (2.33.2)\n",
      "Requirement already satisfied: typing-inspection>=0.4.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from pydantic<2.12,>=2.0->gradio) (0.4.1)\n",
      "Requirement already satisfied: click>=8.0.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from typer<1.0,>=0.12->gradio) (8.2.1)\n",
      "Requirement already satisfied: shellingham>=1.3.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
      "Requirement already satisfied: rich>=10.11.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from typer<1.0,>=0.12->gradio) (14.0.0)\n",
      "Requirement already satisfied: certifi in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from httpx>=0.24.1->gradio) (2022.12.7)\n",
      "Collecting httpcore==1.* (from httpx>=0.24.1->gradio)\n",
      "  Using cached httpcore-1.0.9-py3-none-any.whl.metadata (21 kB)\n",
      "Collecting h11>=0.16 (from httpcore==1.*->httpx>=0.24.1->gradio)\n",
      "  Using cached h11-0.16.0-py3-none-any.whl.metadata (8.3 kB)\n",
      "Requirement already satisfied: filelock in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from huggingface-hub>=0.28.1->gradio) (3.13.1)\n",
      "Requirement already satisfied: requests in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from huggingface-hub>=0.28.1->gradio) (2.28.1)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from huggingface-hub>=0.28.1->gradio) (4.67.1)\n",
      "Collecting hf-xet<2.0.0,>=1.1.2 (from huggingface-hub>=0.28.1->gradio)\n",
      "  Using cached hf_xet-1.1.4-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (879 bytes)\n",
      "Requirement already satisfied: six>=1.5 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.17.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.19.1)\n",
      "Requirement already satisfied: mdurl~=0.1 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
      "Requirement already satisfied: charset-normalizer<3,>=2 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from requests->huggingface-hub>=0.28.1->gradio) (2.1.1)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages (from requests->huggingface-hub>=0.28.1->gradio) (1.26.13)\n",
      "Using cached gradio-5.34.2-py3-none-any.whl (54.3 MB)\n",
      "Using cached gradio_client-1.10.3-py3-none-any.whl (323 kB)\n",
      "Using cached aiofiles-24.1.0-py3-none-any.whl (15 kB)\n",
      "Using cached anyio-4.9.0-py3-none-any.whl (100 kB)\n",
      "Using cached fastapi-0.115.13-py3-none-any.whl (95 kB)\n",
      "Using cached groovy-0.1.2-py3-none-any.whl (14 kB)\n",
      "Downloading orjson-3.10.18-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (132 kB)\n",
      "Using cached safehttpx-0.1.6-py3-none-any.whl (8.7 kB)\n",
      "Using cached semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Using cached starlette-0.46.2-py3-none-any.whl (72 kB)\n",
      "Using cached tomlkit-0.13.3-py3-none-any.whl (38 kB)\n",
      "Downloading websockets-15.0.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (182 kB)\n",
      "Using cached httpx-0.28.1-py3-none-any.whl (73 kB)\n",
      "Using cached httpcore-1.0.9-py3-none-any.whl (78 kB)\n",
      "Using cached h11-0.16.0-py3-none-any.whl (37 kB)\n",
      "Using cached huggingface_hub-0.33.0-py3-none-any.whl (514 kB)\n",
      "Using cached hf_xet-1.1.4-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
      "Downloading fsspec-2025.5.1-py3-none-any.whl (199 kB)\n",
      "Using cached python_multipart-0.0.20-py3-none-any.whl (24 kB)\n",
      "Using cached ruff-0.12.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
      "Using cached sniffio-1.3.1-py3-none-any.whl (10 kB)\n",
      "Using cached uvicorn-0.34.3-py3-none-any.whl (62 kB)\n",
      "Using cached ffmpy-0.6.0-py3-none-any.whl (5.5 kB)\n",
      "Using cached pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
      "Installing collected packages: pydub, websockets, tomlkit, sniffio, semantic-version, ruff, python-multipart, orjson, hf-xet, h11, groovy, fsspec, ffmpy, aiofiles, uvicorn, huggingface-hub, httpcore, anyio, starlette, httpx, safehttpx, gradio-client, fastapi, gradio\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24/24\u001b[0m [gradio]23/24\u001b[0m [gradio]]e]e-hub]]\n",
      "\u001b[1A\u001b[2KSuccessfully installed aiofiles-24.1.0 anyio-4.9.0 fastapi-0.115.13 ffmpy-0.6.0 fsspec-2025.5.1 gradio-5.34.2 gradio-client-1.10.3 groovy-0.1.2 h11-0.16.0 hf-xet-1.1.4 httpcore-1.0.9 httpx-0.28.1 huggingface-hub-0.33.0 orjson-3.10.18 pydub-0.25.1 python-multipart-0.0.20 ruff-0.12.0 safehttpx-0.1.6 semantic-version-2.10.0 sniffio-1.3.1 starlette-0.46.2 tomlkit-0.13.3 uvicorn-0.34.3 websockets-15.0.1\n"
     ]
    }
   ],
   "source": [
    "#|default_exp app"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f12611e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "cellUniqueIdByVincent": "33d1b"
   },
   "outputs": [],
   "source": [
    "# Make sure we've got the latest version of fastai:\n",
    "!pip install -Uqq fastai"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "38b34840",
   "metadata": {
    "cellUniqueIdByVincent": "61135"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "#|export\n",
    "from fastai.vision.all import *\n",
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ac27342c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "def is_cat(x): return x[0].isupper() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ba485ace",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/jpeg": "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",
      "image/png": "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",
      "text/plain": [
       "PILImage mode=RGB size=151x192"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "im = PILImage.create('cat.jpg')\n",
    "im.thumbnail((192, 192))\n",
    "im"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3ce00796",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "learn = load_learner('model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "cd9783cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "('True', tensor(1), tensor([0.2406, 0.7594]))"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "learn.predict(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ca891050",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 356 ms, sys: 0 ns, total: 356 ms\n",
      "Wall time: 63 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "('True', tensor(1), tensor([0.2406, 0.7594]))"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%time learn.predict(im) # %time will time the prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3a8cba7a",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "categories = ('Dog', 'Cat')\n",
    "\n",
    "def classify_image(img):\n",
    "    pred, idx, probs = learn.predict(img)\n",
    "    return dict(zip(categories, map(float, probs)))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c629306d",
   "metadata": {},
   "source": [
    "### Explanation of the `classify_image` function step by step with a concrete example to show how it transforms data.\n",
    "\n",
    "### What the code does:\n",
    "\n",
    "````python\n",
    "categories = ('Dog', 'Cat')\n",
    "\n",
    "def classify_image(img):\n",
    "    pred, idx, probs = learn.predict(img)\n",
    "    return dict(zip(categories, map(float, probs)))\n",
    "````\n",
    "\n",
    "### Step-by-step breakdown with example data:\n",
    "\n",
    "Let's say you pass in an image of a cat to this function.\n",
    "\n",
    "#### Step 1: `learn.predict(img)` returns three values:\n",
    "```python\n",
    "# Example output from learn.predict():\n",
    "pred = 'Cat'           # The predicted class name\n",
    "idx = tensor(1)        # Index of predicted class (0=Dog, 1=Cat)  \n",
    "probs = tensor([0.1234, 0.8766])  # Probabilities for [Dog, Cat]\n",
    "```\n",
    "\n",
    "#### Step 2: `map(float, probs)` converts tensor probabilities to Python floats:\n",
    "```python\n",
    "# Before: tensor([0.1234, 0.8766])\n",
    "# After:  [0.1234, 0.8766]\n",
    "```\n",
    "\n",
    "#### Step 3: `zip(categories, ...)` pairs category names with probabilities:\n",
    "```python\n",
    "categories = ('Dog', 'Cat')\n",
    "probs_as_floats = [0.1234, 0.8766]\n",
    "\n",
    "# zip creates pairs:\n",
    "# ('Dog', 0.1234)\n",
    "# ('Cat', 0.8766)\n",
    "```\n",
    "\n",
    "#### Step 4: `dict()` converts the pairs into a dictionary:\n",
    "```python\n",
    "# Final result:\n",
    "{\n",
    "    'Dog': 0.1234,\n",
    "    'Cat': 0.8766\n",
    "}\n",
    "```\n",
    "\n",
    "### Complete example flow:\n",
    "\n",
    "```python\n",
    "# Input: An image of a cat\n",
    "img = PILImage.create('cat.jpg')\n",
    "\n",
    "# Function call:\n",
    "result = classify_image(img)\n",
    "\n",
    "# Output:\n",
    "print(result)\n",
    "# {'Dog': 0.1234, 'Cat': 0.8766}\n",
    "```\n",
    "\n",
    "This dictionary format is perfect for displaying confidence scores in a user interface - it clearly shows the model is 87.66% confident it's a cat and 12.34% confident it's a dog."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "0aafdd46",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "{'Dog': 0.240604966878891, 'Cat': 0.7593950629234314}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classify_image(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d8b831ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "* Running on local URL:  http://127.0.0.1:7861\n",
      "* To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#|export\n",
    "image = gr.Image()\n",
    "label = gr.Label()\n",
    "examples = ['dog.jpg', 'cat.jpg', 'dunno.jpg']\n",
    "\n",
    "intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)\n",
    "intf.launch(inline=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "02b06af2",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "5457bcf9",
   "metadata": {},
   "source": [
    "### Export script"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "bdbfc99c",
   "metadata": {},
   "outputs": [
    {
     "ename": "ImportError",
     "evalue": "cannot import name 'notebook2script' from 'nbdev.export' (/home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages/nbdev/export.py)",
     "output_type": "error",
     "traceback": [
      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
      "\u001b[31mImportError\u001b[39m                               Traceback (most recent call last)",
      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[14]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mnbdev\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mexport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m notebook2script\n",
      "\u001b[31mImportError\u001b[39m: cannot import name 'notebook2script' from 'nbdev.export' (/home/shammun/fastai_course/.venv_fastai_py311/lib/python3.11/site-packages/nbdev/export.py)"
     ]
    }
   ],
   "source": [
    "from nbdev.export import notebook2script"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a9f85856",
   "metadata": {},
   "outputs": [],
   "source": [
    "notebook2script('app.ipynb')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f19e422",
   "metadata": {},
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (.venv_fastai_py311) - fastai GPU (Py3.11)",
   "language": "python",
   "name": ".venv_fastai_py311"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.13"
  },
  "vincent": {
   "sessionId": "8adba71bbda083393a2475e2_2025-06-19T11-20-40-461Z"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}