app.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7cd0d8fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|default_exp app"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3ebf880b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting timm\n",
      "  Downloading timm-1.0.9-py3-none-any.whl (2.3 MB)\n",
      "Requirement already satisfied: huggingface_hub in c:\\users\\richard\\anaconda3\\lib\\site-packages (from timm) (0.23.4)\n",
      "Requirement already satisfied: torch in c:\\users\\richard\\anaconda3\\lib\\site-packages (from timm) (2.2.2)\n",
      "Requirement already satisfied: torchvision in c:\\users\\richard\\anaconda3\\lib\\site-packages (from timm) (0.17.2)\n",
      "Requirement already satisfied: pyyaml in c:\\users\\richard\\anaconda3\\lib\\site-packages (from timm) (6.0)\n",
      "Collecting safetensors\n",
      "  Downloading safetensors-0.4.5-cp39-none-win_amd64.whl (286 kB)\n",
      "Requirement already satisfied: requests in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (2.31.0)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (4.11.0)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (4.64.0)\n",
      "Requirement already satisfied: packaging>=20.9 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (21.3)\n",
      "Requirement already satisfied: fsspec>=2023.5.0 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (2024.6.1)\n",
      "Requirement already satisfied: filelock in c:\\users\\richard\\anaconda3\\lib\\site-packages (from huggingface_hub->timm) (3.6.0)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from packaging>=20.9->huggingface_hub->timm) (3.0.4)\n",
      "Requirement already satisfied: colorama in c:\\users\\richard\\anaconda3\\lib\\site-packages (from tqdm>=4.42.1->huggingface_hub->timm) (0.4.6)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from requests->huggingface_hub->timm) (3.3)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from requests->huggingface_hub->timm) (2.0.4)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from requests->huggingface_hub->timm) (2.2.2)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from requests->huggingface_hub->timm) (2021.10.8)\n",
      "Requirement already satisfied: jinja2 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from torch->timm) (2.11.3)\n",
      "Requirement already satisfied: sympy in c:\\users\\richard\\anaconda3\\lib\\site-packages (from torch->timm) (1.10.1)\n",
      "Requirement already satisfied: networkx in c:\\users\\richard\\anaconda3\\lib\\site-packages (from torch->timm) (2.7.1)\n",
      "Requirement already satisfied: MarkupSafe>=0.23 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from jinja2->torch->timm) (2.0.1)\n",
      "Requirement already satisfied: mpmath>=0.19 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from sympy->torch->timm) (1.2.1)\n",
      "Requirement already satisfied: numpy in c:\\users\\richard\\anaconda3\\lib\\site-packages (from torchvision->timm) (1.22.4)\n",
      "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in c:\\users\\richard\\anaconda3\\lib\\site-packages (from torchvision->timm) (10.3.0)\n",
      "Installing collected packages: safetensors, timm\n",
      "Successfully installed safetensors-0.4.5 timm-1.0.9\n"
     ]
    }
   ],
   "source": [
    "!pip install timm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7195af18",
   "metadata": {},
   "source": [
    "## Gradio Pets -try Rdjarbeng"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "44eb0ad3",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "from fastai.vision.all import *\n",
    "import gradio as gr\n",
    "import timm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3295ef11",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/jpeg": "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",
      "image/png": "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",
      "text/plain": [
       "PILImage mode=RGB size=224x160"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "im = PILImage.create('dog.jpeg')\n",
    "im.thumbnail((224,224))\n",
    "im"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9c64822a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from contextlib import contextmanager\n",
    "import pathlib\n",
    "\n",
    "@contextmanager\n",
    "def set_posix_windows():\n",
    "    posix_backup = pathlib.PosixPath\n",
    "    try:\n",
    "        pathlib.PosixPath = pathlib.WindowsPath\n",
    "        yield\n",
    "    finally:\n",
    "        pathlib.PosixPath = posix_backup\n",
    "\n",
    "EXPORT_PATH = pathlib.Path(\"model.pkl\")\n",
    "\n",
    "with set_posix_windows():\n",
    "    learn = load_learner(EXPORT_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "50233d11",
   "metadata": {},
   "outputs": [
    {
     "ename": "NotImplementedError",
     "evalue": "cannot instantiate 'PosixPath' on your system",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNotImplementedError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[1;32mc:\\Users\\Richard\\RD\\Rblue\\myprojects\\pets\\app.ipynb Cell 5\u001b[0m in \u001b[0;36m<cell line: 6>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X20sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m \u001b[39m# Ensure you're using Path, not PosixPath\u001b[39;00m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X20sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m model_path \u001b[39m=\u001b[39m Path(\u001b[39m'\u001b[39m\u001b[39mmodel.pkl\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X20sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m learn \u001b[39m=\u001b[39m load_learner(model_path)\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\fastai\\learner.py:446\u001b[0m, in \u001b[0;36mload_learner\u001b[1;34m(fname, cpu, pickle_module)\u001b[0m\n\u001b[0;32m    444\u001b[0m distrib_barrier()\n\u001b[0;32m    445\u001b[0m map_loc \u001b[39m=\u001b[39m \u001b[39m'\u001b[39m\u001b[39mcpu\u001b[39m\u001b[39m'\u001b[39m \u001b[39mif\u001b[39;00m cpu \u001b[39melse\u001b[39;00m default_device()\n\u001b[1;32m--> 446\u001b[0m \u001b[39mtry\u001b[39;00m: res \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39;49mload(fname, map_location\u001b[39m=\u001b[39;49mmap_loc, pickle_module\u001b[39m=\u001b[39;49mpickle_module)\n\u001b[0;32m    447\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mAttributeError\u001b[39;00m \u001b[39mas\u001b[39;00m e: \n\u001b[0;32m    448\u001b[0m     e\u001b[39m.\u001b[39margs \u001b[39m=\u001b[39m [\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mCustom classes or functions exported with your `Learner` not available in namespace.\u001b[39m\u001b[39m\\\u001b[39m\u001b[39mRe-declare/import before loading:\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m\\t\u001b[39;00m\u001b[39m{\u001b[39;00me\u001b[39m.\u001b[39margs[\u001b[39m0\u001b[39m]\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m]\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\torch\\serialization.py:1026\u001b[0m, in \u001b[0;36mload\u001b[1;34m(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)\u001b[0m\n\u001b[0;32m   1024\u001b[0m             \u001b[39mexcept\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m \u001b[39mas\u001b[39;00m e:\n\u001b[0;32m   1025\u001b[0m                 \u001b[39mraise\u001b[39;00m pickle\u001b[39m.\u001b[39mUnpicklingError(UNSAFE_MESSAGE \u001b[39m+\u001b[39m \u001b[39mstr\u001b[39m(e)) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m-> 1026\u001b[0m         \u001b[39mreturn\u001b[39;00m _load(opened_zipfile,\n\u001b[0;32m   1027\u001b[0m                      map_location,\n\u001b[0;32m   1028\u001b[0m                      pickle_module,\n\u001b[0;32m   1029\u001b[0m                      overall_storage\u001b[39m=\u001b[39moverall_storage,\n\u001b[0;32m   1030\u001b[0m                      \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpickle_load_args)\n\u001b[0;32m   1031\u001b[0m \u001b[39mif\u001b[39;00m mmap:\n\u001b[0;32m   1032\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mmmap can only be used with files saved with \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1033\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39m`torch.save(_use_new_zipfile_serialization=True), \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1034\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39mplease torch.save your checkpoint with this option in order to use mmap.\u001b[39m\u001b[39m\"\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\torch\\serialization.py:1438\u001b[0m, in \u001b[0;36m_load\u001b[1;34m(zip_file, map_location, pickle_module, pickle_file, overall_storage, **pickle_load_args)\u001b[0m\n\u001b[0;32m   1436\u001b[0m unpickler \u001b[39m=\u001b[39m UnpicklerWrapper(data_file, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpickle_load_args)\n\u001b[0;32m   1437\u001b[0m unpickler\u001b[39m.\u001b[39mpersistent_load \u001b[39m=\u001b[39m persistent_load\n\u001b[1;32m-> 1438\u001b[0m result \u001b[39m=\u001b[39m unpickler\u001b[39m.\u001b[39;49mload()\n\u001b[0;32m   1440\u001b[0m torch\u001b[39m.\u001b[39m_utils\u001b[39m.\u001b[39m_validate_loaded_sparse_tensors()\n\u001b[0;32m   1441\u001b[0m torch\u001b[39m.\u001b[39m_C\u001b[39m.\u001b[39m_log_api_usage_metadata(\n\u001b[0;32m   1442\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mtorch.load.metadata\u001b[39m\u001b[39m\"\u001b[39m, {\u001b[39m\"\u001b[39m\u001b[39mserialization_id\u001b[39m\u001b[39m\"\u001b[39m: zip_file\u001b[39m.\u001b[39mserialization_id()}\n\u001b[0;32m   1443\u001b[0m )\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\pathlib.py:1084\u001b[0m, in \u001b[0;36mPath.__new__\u001b[1;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1082\u001b[0m \u001b[39mself\u001b[39m \u001b[39m=\u001b[39m \u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m_from_parts(args, init\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m   1083\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_flavour\u001b[39m.\u001b[39mis_supported:\n\u001b[1;32m-> 1084\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mNotImplementedError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mcannot instantiate \u001b[39m\u001b[39m%r\u001b[39;00m\u001b[39m on your system\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1085\u001b[0m                               \u001b[39m%\u001b[39m (\u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m,))\n\u001b[0;32m   1086\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_init()\n\u001b[0;32m   1087\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\n",
      "\u001b[1;31mNotImplementedError\u001b[0m: cannot instantiate 'PosixPath' on your system"
     ]
    }
   ],
   "source": [
    "#for windows users\n",
    "from pathlib import Path\n",
    "\n",
    "# Ensure you're using Path, not PosixPath\n",
    "model_path = Path('model.pkl')\n",
    "learn = load_learner(model_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ae2bc6ac",
   "metadata": {},
   "outputs": [
    {
     "ename": "NotImplementedError",
     "evalue": "cannot instantiate 'PosixPath' on your system",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNotImplementedError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[1;32mc:\\Users\\Richard\\RD\\Rblue\\myprojects\\pets\\app.ipynb Cell 5\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#W4sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39m#export\u001b[39;00m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#W4sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m learn \u001b[39m=\u001b[39m load_learner(\u001b[39m'\u001b[39;49m\u001b[39mmodel.pkl\u001b[39;49m\u001b[39m'\u001b[39;49m)\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\fastai\\learner.py:446\u001b[0m, in \u001b[0;36mload_learner\u001b[1;34m(fname, cpu, pickle_module)\u001b[0m\n\u001b[0;32m    444\u001b[0m distrib_barrier()\n\u001b[0;32m    445\u001b[0m map_loc \u001b[39m=\u001b[39m \u001b[39m'\u001b[39m\u001b[39mcpu\u001b[39m\u001b[39m'\u001b[39m \u001b[39mif\u001b[39;00m cpu \u001b[39melse\u001b[39;00m default_device()\n\u001b[1;32m--> 446\u001b[0m \u001b[39mtry\u001b[39;00m: res \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39;49mload(fname, map_location\u001b[39m=\u001b[39;49mmap_loc, pickle_module\u001b[39m=\u001b[39;49mpickle_module)\n\u001b[0;32m    447\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mAttributeError\u001b[39;00m \u001b[39mas\u001b[39;00m e: \n\u001b[0;32m    448\u001b[0m     e\u001b[39m.\u001b[39margs \u001b[39m=\u001b[39m [\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mCustom classes or functions exported with your `Learner` not available in namespace.\u001b[39m\u001b[39m\\\u001b[39m\u001b[39mRe-declare/import before loading:\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m\\t\u001b[39;00m\u001b[39m{\u001b[39;00me\u001b[39m.\u001b[39margs[\u001b[39m0\u001b[39m]\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m]\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\torch\\serialization.py:1026\u001b[0m, in \u001b[0;36mload\u001b[1;34m(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)\u001b[0m\n\u001b[0;32m   1024\u001b[0m             \u001b[39mexcept\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m \u001b[39mas\u001b[39;00m e:\n\u001b[0;32m   1025\u001b[0m                 \u001b[39mraise\u001b[39;00m pickle\u001b[39m.\u001b[39mUnpicklingError(UNSAFE_MESSAGE \u001b[39m+\u001b[39m \u001b[39mstr\u001b[39m(e)) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m-> 1026\u001b[0m         \u001b[39mreturn\u001b[39;00m _load(opened_zipfile,\n\u001b[0;32m   1027\u001b[0m                      map_location,\n\u001b[0;32m   1028\u001b[0m                      pickle_module,\n\u001b[0;32m   1029\u001b[0m                      overall_storage\u001b[39m=\u001b[39moverall_storage,\n\u001b[0;32m   1030\u001b[0m                      \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpickle_load_args)\n\u001b[0;32m   1031\u001b[0m \u001b[39mif\u001b[39;00m mmap:\n\u001b[0;32m   1032\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mmmap can only be used with files saved with \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1033\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39m`torch.save(_use_new_zipfile_serialization=True), \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1034\u001b[0m                        \u001b[39m\"\u001b[39m\u001b[39mplease torch.save your checkpoint with this option in order to use mmap.\u001b[39m\u001b[39m\"\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\site-packages\\torch\\serialization.py:1438\u001b[0m, in \u001b[0;36m_load\u001b[1;34m(zip_file, map_location, pickle_module, pickle_file, overall_storage, **pickle_load_args)\u001b[0m\n\u001b[0;32m   1436\u001b[0m unpickler \u001b[39m=\u001b[39m UnpicklerWrapper(data_file, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpickle_load_args)\n\u001b[0;32m   1437\u001b[0m unpickler\u001b[39m.\u001b[39mpersistent_load \u001b[39m=\u001b[39m persistent_load\n\u001b[1;32m-> 1438\u001b[0m result \u001b[39m=\u001b[39m unpickler\u001b[39m.\u001b[39;49mload()\n\u001b[0;32m   1440\u001b[0m torch\u001b[39m.\u001b[39m_utils\u001b[39m.\u001b[39m_validate_loaded_sparse_tensors()\n\u001b[0;32m   1441\u001b[0m torch\u001b[39m.\u001b[39m_C\u001b[39m.\u001b[39m_log_api_usage_metadata(\n\u001b[0;32m   1442\u001b[0m     \u001b[39m\"\u001b[39m\u001b[39mtorch.load.metadata\u001b[39m\u001b[39m\"\u001b[39m, {\u001b[39m\"\u001b[39m\u001b[39mserialization_id\u001b[39m\u001b[39m\"\u001b[39m: zip_file\u001b[39m.\u001b[39mserialization_id()}\n\u001b[0;32m   1443\u001b[0m )\n",
      "File \u001b[1;32mc:\\Users\\Richard\\anaconda3\\lib\\pathlib.py:1084\u001b[0m, in \u001b[0;36mPath.__new__\u001b[1;34m(cls, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1082\u001b[0m \u001b[39mself\u001b[39m \u001b[39m=\u001b[39m \u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m_from_parts(args, init\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m   1083\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_flavour\u001b[39m.\u001b[39mis_supported:\n\u001b[1;32m-> 1084\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mNotImplementedError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mcannot instantiate \u001b[39m\u001b[39m%r\u001b[39;00m\u001b[39m on your system\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m   1085\u001b[0m                               \u001b[39m%\u001b[39m (\u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m,))\n\u001b[0;32m   1086\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_init()\n\u001b[0;32m   1087\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\n",
      "\u001b[1;31mNotImplementedError\u001b[0m: cannot instantiate 'PosixPath' on your system"
     ]
    }
   ],
   "source": [
    "#|export\n",
    "learn = load_learner('model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6e0bf9da",
   "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": [
       "\n",
       "    <div>\n",
       "      <progress value='0' class='' max='1' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      0.00% [0/1 00:00&lt;?]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "('shiba_inu',\n",
       " tensor(33),\n",
       " tensor([6.3936e-03, 3.2048e-03, 1.2916e-04, 4.3909e-04, 1.7997e-04, 4.4896e-05,\n",
       "         4.3241e-03, 5.5350e-04, 2.0063e-04, 6.3684e-04, 2.6128e-03, 3.8972e-04,\n",
       "         1.2791e-03, 2.1973e-02, 4.8422e-04, 4.0919e-04, 2.8233e-04, 2.3786e-02,\n",
       "         2.4201e-03, 3.1371e-03, 8.8251e-03, 1.8994e-02, 2.6371e-03, 3.7404e-04,\n",
       "         9.8885e-02, 3.3950e-01, 1.5954e-02, 3.7081e-04, 3.3307e-03, 8.0765e-04,\n",
       "         3.7152e-04, 1.4447e-03, 1.6448e-03, 4.2526e-01, 1.2580e-03, 1.0812e-03,\n",
       "         6.3783e-03]))"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "learn.predict(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "0419ed3a",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|export\n",
    "categories = learn.dls.vocab\n",
    "\n",
    "def classify_image(img):\n",
    "    pred,idx,probs = learn.predict(img)\n",
    "    return dict(zip(categories, map(float,probs)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "762dec00",
   "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": [
       "\n",
       "    <div>\n",
       "      <progress value='0' class='' max='1' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      0.00% [0/1 00:00&lt;?]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "{'Abyssinian': 0.0063936347141861916,\n",
       " 'Bengal': 0.00320483953692019,\n",
       " 'Birman': 0.00012916297418996692,\n",
       " 'Bombay': 0.00043909461237490177,\n",
       " 'British_Shorthair': 0.0001799702295102179,\n",
       " 'Egyptian_Mau': 4.489603088586591e-05,\n",
       " 'Maine_Coon': 0.00432412838563323,\n",
       " 'Persian': 0.0005535031668841839,\n",
       " 'Ragdoll': 0.0002006347494898364,\n",
       " 'Russian_Blue': 0.0006368352915160358,\n",
       " 'Siamese': 0.002612768206745386,\n",
       " 'Sphynx': 0.00038971565663814545,\n",
       " 'american_bulldog': 0.0012791263870894909,\n",
       " 'american_pit_bull_terrier': 0.021972687914967537,\n",
       " 'basset_hound': 0.00048422443796880543,\n",
       " 'beagle': 0.0004091851587872952,\n",
       " 'boxer': 0.00028232645126990974,\n",
       " 'chihuahua': 0.023786406964063644,\n",
       " 'english_cocker_spaniel': 0.002420125063508749,\n",
       " 'english_setter': 0.0031371056102216244,\n",
       " 'german_shorthaired': 0.00882511492818594,\n",
       " 'great_pyrenees': 0.018993815407156944,\n",
       " 'havanese': 0.002637104131281376,\n",
       " 'japanese_chin': 0.00037404231261461973,\n",
       " 'keeshond': 0.09888476133346558,\n",
       " 'leonberger': 0.3395005762577057,\n",
       " 'miniature_pinscher': 0.015954328700900078,\n",
       " 'newfoundland': 0.0003708111180458218,\n",
       " 'pomeranian': 0.003330691484734416,\n",
       " 'pug': 0.0008076547528617084,\n",
       " 'saint_bernard': 0.00037151729338802397,\n",
       " 'samoyed': 0.001444719615392387,\n",
       " 'scottish_terrier': 0.0016448204405605793,\n",
       " 'shiba_inu': 0.4252621829509735,\n",
       " 'staffordshire_bull_terrier': 0.0012579791946336627,\n",
       " 'wheaten_terrier': 0.0010812017135322094,\n",
       " 'yorkshire_terrier': 0.006378257181495428}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classify_image(im)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "68fbb2a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'4.37.2'"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gr.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "930cf172",
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'gradio' has no attribute 'inputs'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[1;32mc:\\Users\\Richard\\RD\\Rblue\\myprojects\\pets\\app.ipynb Cell 12\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X11sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39m#export\u001b[39;00m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X11sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m image \u001b[39m=\u001b[39m gr\u001b[39m.\u001b[39;49minputs\u001b[39m.\u001b[39mImage(shape\u001b[39m=\u001b[39m(\u001b[39m192\u001b[39m, \u001b[39m192\u001b[39m))\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X11sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m label \u001b[39m=\u001b[39m gr\u001b[39m.\u001b[39moutputs\u001b[39m.\u001b[39mLabel()\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/Richard/RD/Rblue/myprojects/pets/app.ipynb#X11sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m examples \u001b[39m=\u001b[39m [\u001b[39m'\u001b[39m\u001b[39mdog.jpeg\u001b[39m\u001b[39m'\u001b[39m]\n",
      "\u001b[1;31mAttributeError\u001b[0m: module 'gradio' has no attribute 'inputs'"
     ]
    }
   ],
   "source": [
    "#|export\n",
    "image = gr.inputs.Image(shape=(192, 192))\n",
    "label = gr.outputs.Label()\n",
    "examples = ['dog.jpeg']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4f463e23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:3000/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(<fastapi.applications.FastAPI at 0x7f591050c970>,\n",
       " 'http://127.0.0.1:3000/',\n",
       " None)"
      ]
     },
     "execution_count": 9,
     "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-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",
    "intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)\n",
    "intf.launch(inline=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "82774c08",
   "metadata": {
    "scrolled": true,
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Sequential(\n",
       "  (0): TimmBody(\n",
       "    (model): ConvNeXt(\n",
       "      (stem): Sequential(\n",
       "        (0): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4))\n",
       "        (1): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True)\n",
       "      )\n",
       "      (stages): Sequential(\n",
       "        (0): ConvNeXtStage(\n",
       "          (downsample): Identity()\n",
       "          (blocks): Sequential(\n",
       "            (0): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96)\n",
       "              (norm): LayerNorm((96,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=96, out_features=384, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=384, out_features=96, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (1): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96)\n",
       "              (norm): LayerNorm((96,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=96, out_features=384, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=384, out_features=96, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (2): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96)\n",
       "              (norm): LayerNorm((96,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=96, out_features=384, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=384, out_features=96, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "          )\n",
       "        )\n",
       "        (1): ConvNeXtStage(\n",
       "          (downsample): Sequential(\n",
       "            (0): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True)\n",
       "            (1): Conv2d(96, 192, kernel_size=(2, 2), stride=(2, 2))\n",
       "          )\n",
       "          (blocks): Sequential(\n",
       "            (0): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192)\n",
       "              (norm): LayerNorm((192,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=192, out_features=768, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=768, out_features=192, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (1): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192)\n",
       "              (norm): LayerNorm((192,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=192, out_features=768, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=768, out_features=192, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (2): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192)\n",
       "              (norm): LayerNorm((192,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=192, out_features=768, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=768, out_features=192, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "          )\n",
       "        )\n",
       "        (2): ConvNeXtStage(\n",
       "          (downsample): Sequential(\n",
       "            (0): LayerNorm2d((192,), eps=1e-06, elementwise_affine=True)\n",
       "            (1): Conv2d(192, 384, kernel_size=(2, 2), stride=(2, 2))\n",
       "          )\n",
       "          (blocks): Sequential(\n",
       "            (0): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (1): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (2): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (3): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (4): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (5): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (6): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (7): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (8): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384)\n",
       "              (norm): LayerNorm((384,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=384, out_features=1536, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=1536, out_features=384, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "          )\n",
       "        )\n",
       "        (3): ConvNeXtStage(\n",
       "          (downsample): Sequential(\n",
       "            (0): LayerNorm2d((384,), eps=1e-06, elementwise_affine=True)\n",
       "            (1): Conv2d(384, 768, kernel_size=(2, 2), stride=(2, 2))\n",
       "          )\n",
       "          (blocks): Sequential(\n",
       "            (0): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768)\n",
       "              (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=768, out_features=3072, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=3072, out_features=768, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (1): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768)\n",
       "              (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=768, out_features=3072, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=3072, out_features=768, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "            (2): ConvNeXtBlock(\n",
       "              (conv_dw): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768)\n",
       "              (norm): LayerNorm((768,), eps=1e-06, elementwise_affine=True)\n",
       "              (mlp): Mlp(\n",
       "                (fc1): Linear(in_features=768, out_features=3072, bias=True)\n",
       "                (act): GELU()\n",
       "                (drop1): Dropout(p=0.0, inplace=False)\n",
       "                (fc2): Linear(in_features=3072, out_features=768, bias=True)\n",
       "                (drop2): Dropout(p=0.0, inplace=False)\n",
       "              )\n",
       "              (drop_path): Identity()\n",
       "            )\n",
       "          )\n",
       "        )\n",
       "      )\n",
       "      (norm_pre): Identity()\n",
       "      (head): Sequential(\n",
       "        (global_pool): SelectAdaptivePool2d (pool_type=avg, flatten=Identity())\n",
       "        (norm): LayerNorm2d((768,), eps=1e-06, elementwise_affine=True)\n",
       "        (flatten): Flatten(start_dim=1, end_dim=-1)\n",
       "        (drop): Dropout(p=0.0, inplace=False)\n",
       "        (fc): Identity()\n",
       "      )\n",
       "    )\n",
       "  )\n",
       "  (1): Sequential(\n",
       "    (0): AdaptiveConcatPool2d(\n",
       "      (ap): AdaptiveAvgPool2d(output_size=1)\n",
       "      (mp): AdaptiveMaxPool2d(output_size=1)\n",
       "    )\n",
       "    (1): Flatten(full=False)\n",
       "    (2): BatchNorm1d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    (3): Dropout(p=0.25, inplace=False)\n",
       "    (4): Linear(in_features=1536, out_features=512, bias=False)\n",
       "    (5): ReLU(inplace=True)\n",
       "    (6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
       "    (7): Dropout(p=0.5, inplace=False)\n",
       "    (8): Linear(in_features=512, out_features=37, bias=False)\n",
       "  )\n",
       ")"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m = learn.model\n",
    "m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "10d7900d",
   "metadata": {},
   "outputs": [],
   "source": [
    "l = m.get_submodule('0.model.stem.1')\n",
    "list(l.parameters())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "008537b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Parameter containing:\n",
       " tensor([[ 2.2773e-02, -1.6051e-03,  4.0450e-02,  ...,  1.7370e-03,\n",
       "          -4.5070e-02,  8.0949e-03],\n",
       "         [-1.4383e-01,  1.6965e-02,  2.5983e-02,  ...,  1.2606e-02,\n",
       "          -1.0443e-01,  5.6370e-02],\n",
       "         [-6.5471e-02, -3.2719e-02,  5.6796e-03,  ..., -4.1571e-02,\n",
       "           6.5921e-02, -4.0347e-02],\n",
       "         ...,\n",
       "         [-8.8080e-03,  6.9815e-02,  7.1424e-05,  ...,  4.0177e-03,\n",
       "           4.1478e-02, -1.9052e-02],\n",
       "         [ 2.0792e-03,  3.2267e-02,  2.9801e-02,  ..., -2.9897e-02,\n",
       "          -3.0278e-02,  5.5432e-02],\n",
       "         [ 1.2097e-01, -3.5444e-02, -4.6078e-03,  ..., -6.3829e-03,\n",
       "           2.3691e-02, -1.1242e-02]], requires_grad=True),\n",
       " Parameter containing:\n",
       " tensor([-0.4047, -0.7418, -0.4235, -0.1650, -0.3028, -0.1898, -0.5534, -0.6271,\n",
       "         -0.3008, -0.4254, -0.5997, -0.4107, -0.2172, -1.7935, -0.3170, -0.1163,\n",
       "         -0.4482, -0.2846, -0.4342, -0.4945, -0.4065, -1.1402, -0.6754, -1.7237,\n",
       "         -0.2955, -0.2654, -0.2187, -0.3914, -0.4150, -0.4772,  0.2365, -0.7542,\n",
       "         -0.5852, -0.1820, -1.5272, -0.3626, -2.4689, -2.3461, -0.6109, -0.4115,\n",
       "         -0.6964, -0.5764, -0.5878, -0.0318, -2.0354, -0.2859, -0.3953, -0.8402,\n",
       "         -2.2398, -1.0876, -0.2295, -0.9004, -0.7584, -0.8833, -0.3755, -0.4549,\n",
       "         -0.3835, -0.4047, -2.0231, -1.0263, -0.4106, -1.1564, -0.2224, -0.4250,\n",
       "         -0.2494, -0.4222, -0.0975, -1.4017, -0.6887, -0.4370, -0.2932, -0.4641,\n",
       "         -0.4958, -1.2534, -1.0720, -1.2966, -0.6276, -1.4161, -2.3080, -2.4538,\n",
       "         -0.4259, -0.9987, -0.4638, -0.3147, -0.2416, -0.8744, -0.2829, -1.4208,\n",
       "         -0.3257, -0.3202, -0.0602, -0.1896, -0.2497, -0.6129, -0.2976, -2.1465,\n",
       "         -0.4128, -0.3675, -1.9815, -0.3815, -0.3785, -0.2292, -0.3700, -0.3256,\n",
       "         -0.5584, -2.4192, -0.4590, -1.7748, -0.3996, -0.4092, -0.3518, -0.5332,\n",
       "         -1.6534, -1.8191,  0.6263, -0.4058,  0.5872, -2.2074, -0.2438, -2.4540,\n",
       "         -0.2283, -0.6865,  0.6988,  0.6477, -0.6445, -0.3454, -0.3275, -0.5701,\n",
       "         -0.5173, -0.2774, -0.4090, -0.3018, -0.4874, -0.4954, -0.4073, -0.4356,\n",
       "         -0.5103, -0.4128, -2.0919, -0.2825, -0.5830, -1.5834,  0.6139, -0.8506,\n",
       "         -0.4669, -2.1358, -0.3417, -0.3766, -0.3345, -0.3961, -0.3886, -0.5668,\n",
       "         -0.2224, -1.3059, -0.4601, -0.3928, -0.4665, -0.4214, -0.4755, -0.2865,\n",
       "         -1.5804, -0.1787, -0.4368, -0.3173,  1.5732, -0.4046, -0.4839, -0.2576,\n",
       "         -0.5611, -0.4265, -0.2578, -0.3176, -0.4620, -1.9553, -1.9146, -0.3961,\n",
       "          0.3988, -2.3520, -0.9689, -0.2831, -1.9000, -0.4180,  0.0160, -1.1111,\n",
       "         -0.4924, -0.3177, -1.8912, -0.3101, -0.8137, -2.3345, -0.3843, -0.3847,\n",
       "         -0.1974, -0.4444, -1.6233, -2.5485, -0.3178, -1.2715, -1.1479,  0.6149,\n",
       "         -0.3749, -0.3952, -2.0747, -0.4657, -0.3782, -0.4958, -0.3281, -1.9219,\n",
       "         -2.0018, -0.5307, -0.2555, -1.1161, -0.3516, -2.2185, -1.1394,  0.5366,\n",
       "         -0.3218, -2.0387, -0.4656,  0.1850, -0.5830, -0.3129,  0.6182, -0.2124,\n",
       "         -2.3538, -0.9700, -0.9784, -0.3668, -0.4503, -1.9564, -0.2662, -1.1754,\n",
       "         -0.4200, -0.9024, -0.3604, -0.5172, -1.1882, -0.4191, -0.4770, -1.5558,\n",
       "         -0.4011, -0.6518, -0.4817, -0.2422,  0.6909, -0.5080, -0.4303, -0.6068,\n",
       "         -0.4001, -0.3329, -0.3596, -1.6108, -0.2371, -0.2467, -0.4545,  0.1808,\n",
       "         -0.3225, -0.3918, -0.3514, -0.3756, -1.2178, -0.4000, -0.3578, -0.2883,\n",
       "         -1.7485, -0.2364, -0.1599, -0.2640, -0.9769, -1.3066, -0.4148, -0.2663,\n",
       "         -0.3933, -0.4628, -0.2174,  0.2141, -0.5733, -0.2766, -0.3658, -0.5171,\n",
       "         -0.3484, -0.3365, -0.6445,  0.6866, -0.3738, -0.2902, -2.0863, -0.4882,\n",
       "         -0.2597, -1.0497, -1.6616, -0.3399, -0.5111, -0.5661, -0.3029, -0.5048,\n",
       "         -0.2877, -0.2841, -0.1981, -0.6910, -0.2872, -2.1120, -0.8928, -0.2299,\n",
       "         -1.5010, -0.4734, -2.2293, -0.4020, -0.2925, -0.4198,  0.6646, -0.3047,\n",
       "         -0.1687, -0.3750, -0.6434, -2.3348, -0.3102, -1.2732, -0.8192, -1.0592,\n",
       "         -0.0931, -1.6385,  0.3426, -0.8484, -0.4910, -0.5002, -1.0631, -0.3532,\n",
       "         -1.1562, -0.3843, -0.3172, -0.6432, -0.9083, -0.6567, -0.6489,  0.6336,\n",
       "         -0.2663, -1.3203, -1.1623, -1.2032, -2.0576, -0.3001, -1.3597, -0.4614,\n",
       "         -0.5024, -0.4949, -0.3158, -0.3273, -0.2668, -0.4280, -0.3296, -0.3011,\n",
       "         -1.6635,  0.6434, -0.9455,  0.6097, -0.4234,  0.3918, -0.4943, -0.4285,\n",
       "         -0.2588, -0.4951, -2.1992, -0.2601, -0.3935, -0.4564, -0.5817, -0.3487,\n",
       "         -0.7372, -0.3589, -0.4894, -2.0108,  0.4556, -0.8057, -1.7749, -0.3511,\n",
       "         -0.5359, -0.2100, -0.3956, -0.4780, -1.1457, -0.3976, -2.2114, -0.2840],\n",
       "        requires_grad=True)]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l = m.get_submodule('0.model.stages.0.blocks.1.mlp.fc1')\n",
    "list(l.parameters())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc60a215",
   "metadata": {},
   "source": [
    "## Export"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "ff9d5c73",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Export successful\n"
     ]
    }
   ],
   "source": [
    "import nbdev\n",
    "\n",
    "nbdev.export.nb_export('app.ipynb','')\n",
    "print('Export successful')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}