{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Big massive imports. Not happy with this global import but Jeremy likes it and so all of the examples follow this style."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastcore.all import *\n",
    "from fastai.vision.all import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Set up the path and check the files."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "All images: 97\n",
      "Verification failed: 0\n"
     ]
    },
    {
     "data": {
      "image/jpeg": "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",
      "image/png": "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",
      "text/plain": [
       "<PIL.Image.Image image mode=RGB size=256x255>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "path = Path('/Users/przemek/projects/labs/street-art/training')\n",
    "image_files = get_image_files(path)\n",
    "failed = verify_images(image_files)\n",
    "print(f'All images: {len(image_files)}')\n",
    "print(f'Verification failed: {len(failed)}')\n",
    "\n",
    "im = Image.open(get_image_files(path)[0])\n",
    "im.to_thumb(256,256)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "OK let's get to it. Preparing the data block."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "env: PYTORCH_ENABLE_MPS_FALLBACK=1\n",
      "Could not do one pass in your dataloader, there is something wrong in it. Please see the stack trace below:\n"
     ]
    },
    {
     "ename": "NotImplementedError",
     "evalue": "The operator 'aten::_linalg_solve_ex.result' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on https://github.com/pytorch/pytorch/issues/77764. As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNotImplementedError\u001b[0m                       Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[3], line 13\u001b[0m\n\u001b[1;32m      3\u001b[0m data_block \u001b[38;5;241m=\u001b[39m DataBlock(\n\u001b[1;32m      4\u001b[0m     blocks\u001b[38;5;241m=\u001b[39m(ImageBlock, CategoryBlock), \n\u001b[1;32m      5\u001b[0m     get_items\u001b[38;5;241m=\u001b[39mget_image_files, \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      8\u001b[0m     item_tfms\u001b[38;5;241m=\u001b[39m[Resize(\u001b[38;5;241m512\u001b[39m, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124msquish\u001b[39m\u001b[38;5;124m'\u001b[39m)]\n\u001b[1;32m      9\u001b[0m )\n\u001b[1;32m     11\u001b[0m data_block \u001b[38;5;241m=\u001b[39m data_block\u001b[38;5;241m.\u001b[39mnew(item_tfms\u001b[38;5;241m=\u001b[39mRandomResizedCrop(\u001b[38;5;241m256\u001b[39m, min_scale\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.6\u001b[39m), batch_tfms\u001b[38;5;241m=\u001b[39maug_transforms())\n\u001b[0;32m---> 13\u001b[0m dls \u001b[38;5;241m=\u001b[39m \u001b[43mdata_block\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataloaders\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m6\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     14\u001b[0m dls\u001b[38;5;241m.\u001b[39mshow_batch(max_n\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m6\u001b[39m)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/data/block.py:157\u001b[0m, in \u001b[0;36mDataBlock.dataloaders\u001b[0;34m(self, source, path, verbose, **kwargs)\u001b[0m\n\u001b[1;32m    155\u001b[0m dsets \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdatasets(source, verbose\u001b[38;5;241m=\u001b[39mverbose)\n\u001b[1;32m    156\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdls_kwargs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mverbose\u001b[39m\u001b[38;5;124m'\u001b[39m: verbose}\n\u001b[0;32m--> 157\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mdsets\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataloaders\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mafter_item\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitem_tfms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mafter_batch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbatch_tfms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/data/core.py:337\u001b[0m, in \u001b[0;36mFilteredBase.dataloaders\u001b[0;34m(self, bs, shuffle_train, shuffle, val_shuffle, n, path, dl_type, dl_kwargs, device, drop_last, val_bs, **kwargs)\u001b[0m\n\u001b[1;32m    335\u001b[0m dl \u001b[38;5;241m=\u001b[39m dl_type(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubset(\u001b[38;5;241m0\u001b[39m), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmerge(kwargs,def_kwargs, dl_kwargs[\u001b[38;5;241m0\u001b[39m]))\n\u001b[1;32m    336\u001b[0m def_kwargs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbs\u001b[39m\u001b[38;5;124m'\u001b[39m:bs \u001b[38;5;28;01mif\u001b[39;00m val_bs \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m val_bs,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mshuffle\u001b[39m\u001b[38;5;124m'\u001b[39m:val_shuffle,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mn\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;28;01mNone\u001b[39;00m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdrop_last\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;28;01mFalse\u001b[39;00m}\n\u001b[0;32m--> 337\u001b[0m dls \u001b[38;5;241m=\u001b[39m [dl] \u001b[38;5;241m+\u001b[39m \u001b[43m[\u001b[49m\u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnew\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msubset\u001b[49m\u001b[43m(\u001b[49m\u001b[43mi\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmerge\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdef_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mval_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdl_kwargs\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    338\u001b[0m \u001b[43m              \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mrange\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mn_subsets\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m    339\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dbunch_type(\u001b[38;5;241m*\u001b[39mdls, path\u001b[38;5;241m=\u001b[39mpath, device\u001b[38;5;241m=\u001b[39mdevice)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/data/core.py:337\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m    335\u001b[0m dl \u001b[38;5;241m=\u001b[39m dl_type(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msubset(\u001b[38;5;241m0\u001b[39m), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmerge(kwargs,def_kwargs, dl_kwargs[\u001b[38;5;241m0\u001b[39m]))\n\u001b[1;32m    336\u001b[0m def_kwargs \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbs\u001b[39m\u001b[38;5;124m'\u001b[39m:bs \u001b[38;5;28;01mif\u001b[39;00m val_bs \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m val_bs,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mshuffle\u001b[39m\u001b[38;5;124m'\u001b[39m:val_shuffle,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mn\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;28;01mNone\u001b[39;00m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdrop_last\u001b[39m\u001b[38;5;124m'\u001b[39m:\u001b[38;5;28;01mFalse\u001b[39;00m}\n\u001b[0;32m--> 337\u001b[0m dls \u001b[38;5;241m=\u001b[39m [dl] \u001b[38;5;241m+\u001b[39m [\u001b[43mdl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnew\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msubset\u001b[49m\u001b[43m(\u001b[49m\u001b[43mi\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmerge\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdef_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mval_kwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdl_kwargs\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    338\u001b[0m               \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_subsets)]\n\u001b[1;32m    339\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dbunch_type(\u001b[38;5;241m*\u001b[39mdls, path\u001b[38;5;241m=\u001b[39mpath, device\u001b[38;5;241m=\u001b[39mdevice)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/data/core.py:97\u001b[0m, in \u001b[0;36mTfmdDL.new\u001b[0;34m(self, dataset, cls, **kwargs)\u001b[0m\n\u001b[1;32m     95\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_n_inp\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m_types\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m     96\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 97\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_one_pass\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     98\u001b[0m         res\u001b[38;5;241m.\u001b[39m_n_inp,res\u001b[38;5;241m.\u001b[39m_types \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_inp,\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_types\n\u001b[1;32m     99\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e: \n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/data/core.py:80\u001b[0m, in \u001b[0;36mTfmdDL._one_pass\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     78\u001b[0m b \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdo_batch([\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdo_item(\u001b[38;5;28;01mNone\u001b[39;00m)])\n\u001b[1;32m     79\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: b \u001b[38;5;241m=\u001b[39m to_device(b, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[0;32m---> 80\u001b[0m its \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mafter_batch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     81\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_inp \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(its, (\u001b[38;5;28mlist\u001b[39m,\u001b[38;5;28mtuple\u001b[39m)) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(its)\u001b[38;5;241m==\u001b[39m\u001b[38;5;241m1\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(its)\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[1;32m     82\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_types \u001b[38;5;241m=\u001b[39m explode_types(its)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:208\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[0;34m(self, o)\u001b[0m\n\u001b[0;32m--> 208\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, o): \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mcompose_tfms\u001b[49m\u001b[43m(\u001b[49m\u001b[43mo\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtfms\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit_idx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit_idx\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:158\u001b[0m, in \u001b[0;36mcompose_tfms\u001b[0;34m(x, tfms, is_enc, reverse, **kwargs)\u001b[0m\n\u001b[1;32m    156\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m f \u001b[38;5;129;01min\u001b[39;00m tfms:\n\u001b[1;32m    157\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_enc: f \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mdecode\n\u001b[0;32m--> 158\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    159\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m x\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:49\u001b[0m, in \u001b[0;36mRandTransform.__call__\u001b[0;34m(self, b, split_idx, **kwargs)\u001b[0m\n\u001b[1;32m     43\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, \n\u001b[1;32m     44\u001b[0m     b, \n\u001b[1;32m     45\u001b[0m     split_idx:\u001b[38;5;28mint\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;66;03m# Index of the train/valid dataset\u001b[39;00m\n\u001b[1;32m     46\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs\n\u001b[1;32m     47\u001b[0m ):\n\u001b[1;32m     48\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbefore_call(b, split_idx\u001b[38;5;241m=\u001b[39msplit_idx)\n\u001b[0;32m---> 49\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mb\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msplit_idx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msplit_idx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdo \u001b[38;5;28;01melse\u001b[39;00m b\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:81\u001b[0m, in \u001b[0;36mTransform.__call__\u001b[0;34m(self, x, **kwargs)\u001b[0m\n\u001b[0;32m---> 81\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, x, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs): \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mencodes\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:91\u001b[0m, in \u001b[0;36mTransform._call\u001b[0;34m(self, fn, x, split_idx, **kwargs)\u001b[0m\n\u001b[1;32m     89\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\u001b[38;5;28mself\u001b[39m, fn, x, split_idx\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m     90\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m split_idx\u001b[38;5;241m!=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msplit_idx \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msplit_idx \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: \u001b[38;5;28;01mreturn\u001b[39;00m x\n\u001b[0;32m---> 91\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_do_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfn\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:98\u001b[0m, in \u001b[0;36mTransform._do_call\u001b[0;34m(self, f, x, **kwargs)\u001b[0m\n\u001b[1;32m     96\u001b[0m     ret \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mreturns(x) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(f,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreturns\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m     97\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(f(x, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs), x, ret)\n\u001b[0;32m---> 98\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_do_call(f, x_, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;28;01mfor\u001b[39;00m x_ \u001b[38;5;129;01min\u001b[39;00m x)\n\u001b[1;32m     99\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(res, x)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:98\u001b[0m, in \u001b[0;36m<genexpr>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     96\u001b[0m     ret \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mreturns(x) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(f,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreturns\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m     97\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(f(x, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs), x, ret)\n\u001b[0;32m---> 98\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_do_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx_\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m x_ \u001b[38;5;129;01min\u001b[39;00m x)\n\u001b[1;32m     99\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(res, x)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:97\u001b[0m, in \u001b[0;36mTransform._do_call\u001b[0;34m(self, f, x, **kwargs)\u001b[0m\n\u001b[1;32m     95\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m f \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: \u001b[38;5;28;01mreturn\u001b[39;00m x\n\u001b[1;32m     96\u001b[0m     ret \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mreturns(x) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(f,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mreturns\u001b[39m\u001b[38;5;124m'\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m---> 97\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(\u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m, x, ret)\n\u001b[1;32m     98\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_do_call(f, x_, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;28;01mfor\u001b[39;00m x_ \u001b[38;5;129;01min\u001b[39;00m x)\n\u001b[1;32m     99\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m retain_type(res, x)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/dispatch.py:120\u001b[0m, in \u001b[0;36mTypeDispatch.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    118\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minst \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: f \u001b[38;5;241m=\u001b[39m MethodType(f, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minst)\n\u001b[1;32m    119\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mowner \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: f \u001b[38;5;241m=\u001b[39m MethodType(f, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mowner)\n\u001b[0;32m--> 120\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:501\u001b[0m, in \u001b[0;36mAffineCoordTfm.encodes\u001b[0;34m(self, x)\u001b[0m\n\u001b[0;32m--> 501\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mencodes\u001b[39m(\u001b[38;5;28mself\u001b[39m, x:TensorImage): \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_encode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:499\u001b[0m, in \u001b[0;36mAffineCoordTfm._encode\u001b[0;34m(self, x, mode, reverse)\u001b[0m\n\u001b[1;32m    497\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_encode\u001b[39m(\u001b[38;5;28mself\u001b[39m, x, mode, reverse\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m    498\u001b[0m     coord_func \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcoord_fs)\u001b[38;5;241m==\u001b[39m\u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msplit_idx \u001b[38;5;28;01melse\u001b[39;00m partial(compose_tfms, tfms\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcoord_fs, reverse\u001b[38;5;241m=\u001b[39mreverse)\n\u001b[0;32m--> 499\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43maffine_coord\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmat\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcoord_func\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msz\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msize\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpad_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpad_mode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43malign_corners\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43malign_corners\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:390\u001b[0m, in \u001b[0;36maffine_coord\u001b[0;34m(x, mat, coord_tfm, sz, mode, pad_mode, align_corners)\u001b[0m\n\u001b[1;32m    388\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m mat \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: mat \u001b[38;5;241m=\u001b[39m _init_mat(x)[:,:\u001b[38;5;241m2\u001b[39m]\n\u001b[1;32m    389\u001b[0m coords \u001b[38;5;241m=\u001b[39m affine_grid(mat, x\u001b[38;5;241m.\u001b[39mshape[:\u001b[38;5;241m2\u001b[39m] \u001b[38;5;241m+\u001b[39m size, align_corners\u001b[38;5;241m=\u001b[39malign_corners)\n\u001b[0;32m--> 390\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m coord_tfm \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m: coords \u001b[38;5;241m=\u001b[39m \u001b[43mcoord_tfm\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcoords\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m TensorImage(_grid_sample(x, coords, mode\u001b[38;5;241m=\u001b[39mmode, padding_mode\u001b[38;5;241m=\u001b[39mpad_mode, align_corners\u001b[38;5;241m=\u001b[39malign_corners))\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastcore/transform.py:158\u001b[0m, in \u001b[0;36mcompose_tfms\u001b[0;34m(x, tfms, is_enc, reverse, **kwargs)\u001b[0m\n\u001b[1;32m    156\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m f \u001b[38;5;129;01min\u001b[39;00m tfms:\n\u001b[1;32m    157\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_enc: f \u001b[38;5;241m=\u001b[39m f\u001b[38;5;241m.\u001b[39mdecode\n\u001b[0;32m--> 158\u001b[0m     x \u001b[38;5;241m=\u001b[39m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    159\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m x\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:870\u001b[0m, in \u001b[0;36m_WarpCoord.__call__\u001b[0;34m(self, x, invert)\u001b[0m\n\u001b[1;32m    869\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m, x, invert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m--> 870\u001b[0m     coeffs \u001b[38;5;241m=\u001b[39m find_coeffs(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtarg_pts, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39morig_pts) \u001b[38;5;28;01mif\u001b[39;00m invert \u001b[38;5;28;01melse\u001b[39;00m \u001b[43mfind_coeffs\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43morig_pts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtarg_pts\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    871\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m apply_perspective(x, coeffs)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:834\u001b[0m, in \u001b[0;36mfind_coeffs\u001b[0;34m(p1, p2)\u001b[0m\n\u001b[1;32m    832\u001b[0m A \u001b[38;5;241m=\u001b[39m stack(m)\u001b[38;5;241m.\u001b[39mpermute(\u001b[38;5;241m2\u001b[39m, \u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m    833\u001b[0m B \u001b[38;5;241m=\u001b[39m p1\u001b[38;5;241m.\u001b[39mview(p1\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m], \u001b[38;5;241m8\u001b[39m, \u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m--> 834\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43msolve\u001b[49m\u001b[43m(\u001b[49m\u001b[43mA\u001b[49m\u001b[43m,\u001b[49m\u001b[43mB\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/vision/augment.py:817\u001b[0m, in \u001b[0;36msolve\u001b[0;34m(A, B)\u001b[0m\n\u001b[1;32m    816\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msolve\u001b[39m(A,B):\n\u001b[0;32m--> 817\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinalg\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msolve\u001b[49m\u001b[43m(\u001b[49m\u001b[43mA\u001b[49m\u001b[43m,\u001b[49m\u001b[43mB\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/fastai/torch_core.py:382\u001b[0m, in \u001b[0;36mTensorBase.__torch_function__\u001b[0;34m(cls, func, types, args, kwargs)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mdebug \u001b[38;5;129;01mand\u001b[39;00m func\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__str__\u001b[39m\u001b[38;5;124m'\u001b[39m,\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__repr__\u001b[39m\u001b[38;5;124m'\u001b[39m): \u001b[38;5;28mprint\u001b[39m(func, types, args, kwargs)\n\u001b[1;32m    381\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _torch_handled(args, \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_opt, func): types \u001b[38;5;241m=\u001b[39m (torch\u001b[38;5;241m.\u001b[39mTensor,)\n\u001b[0;32m--> 382\u001b[0m res \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__torch_function__\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtypes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mifnone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    383\u001b[0m dict_objs \u001b[38;5;241m=\u001b[39m _find_args(args) \u001b[38;5;28;01mif\u001b[39;00m args \u001b[38;5;28;01melse\u001b[39;00m _find_args(\u001b[38;5;28mlist\u001b[39m(kwargs\u001b[38;5;241m.\u001b[39mvalues()))\n\u001b[1;32m    384\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28missubclass\u001b[39m(\u001b[38;5;28mtype\u001b[39m(res),TensorBase) \u001b[38;5;129;01mand\u001b[39;00m dict_objs: res\u001b[38;5;241m.\u001b[39mset_meta(dict_objs[\u001b[38;5;241m0\u001b[39m],as_copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
      "File \u001b[0;32m~/projects/street-art/.env/lib/python3.11/site-packages/torch/_tensor.py:1386\u001b[0m, in \u001b[0;36mTensor.__torch_function__\u001b[0;34m(cls, func, types, args, kwargs)\u001b[0m\n\u001b[1;32m   1383\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mNotImplemented\u001b[39m\n\u001b[1;32m   1385\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m _C\u001b[38;5;241m.\u001b[39mDisableTorchFunctionSubclass():\n\u001b[0;32m-> 1386\u001b[0m     ret \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1387\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m func \u001b[38;5;129;01min\u001b[39;00m get_default_nowrap_functions():\n\u001b[1;32m   1388\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m ret\n",
      "\u001b[0;31mNotImplementedError\u001b[0m: The operator 'aten::_linalg_solve_ex.result' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on https://github.com/pytorch/pytorch/issues/77764. As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS."
     ]
    }
   ],
   "source": [
    "%env PYTORCH_ENABLE_MPS_FALLBACK=1\n",
    "\n",
    "data_block = DataBlock(\n",
    "    blocks=(ImageBlock, CategoryBlock), \n",
    "    get_items=get_image_files, \n",
    "    splitter=RandomSplitter(valid_pct=0.2, seed=44),\n",
    "    get_y=parent_label,\n",
    "    item_tfms=[Resize(512, method='squish')]\n",
    ")\n",
    "\n",
    "data_block = data_block.new(item_tfms=RandomResizedCrop(256, min_scale=0.6), batch_tfms=aug_transforms())\n",
    "\n",
    "dls = data_block.dataloaders(path, bs=6)\n",
    "dls.show_batch(max_n=6)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's fine tune the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn = vision_learner(dls, resnet18, metrics=error_rate)\n",
    "learn.fine_tune(7)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can glean some insights from the learner"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "interp = ClassificationInterpretation.from_learner(learn)\n",
    "interp.plot_confusion_matrix()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "interp.plot_top_losses(5, nrows=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's see how it does on test data (separate from training OFC)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import IPython.display as display\n",
    "\n",
    "test_path = Path('/Users/przemek/projects/labs/street-art/test')\n",
    "test_files = get_image_files(test_path)\n",
    "for test_file in test_files:\n",
    "    label,index,probs = learn.predict(PILImage.create(test_file))\n",
    "    print(f\"This is: {label}, confidence: {probs[index]:.4f}\")\n",
    "    im = Image.open(test_file)\n",
    "    display.display(im.to_thumb(256,256))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ready to save the resulting model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn.export('model.pkl')"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}