{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b2d6f096-6123-4dd0-ae4f-c9abf70889c4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-03T17:21:13.044450Z",
     "iopub.status.busy": "2024-04-03T17:21:13.043912Z",
     "iopub.status.idle": "2024-04-03T17:21:13.374087Z",
     "shell.execute_reply": "2024-04-03T17:21:13.373277Z",
     "shell.execute_reply.started": "2024-04-03T17:21:13.044419Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Reusing dataset mnist (/root/.cache/huggingface/datasets/mnist/mnist/1.0.0/fda16c03c4ecfb13f165ba7e29cf38129ce035011519968cdaf74894ce91c9d4)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cd2dd3c8b22b49718b3c66585ca3559c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "dataset = load_dataset(\"mnist\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7c5ea43d-6a70-4deb-a90e-1d7758c961a3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-03T17:21:27.628082Z",
     "iopub.status.busy": "2024-04-03T17:21:27.627048Z",
     "iopub.status.idle": "2024-04-03T17:21:27.632687Z",
     "shell.execute_reply": "2024-04-03T17:21:27.632002Z",
     "shell.execute_reply.started": "2024-04-03T17:21:27.628051Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from PIL import Image\n",
    "import io\n",
    "\n",
    "def convert(byte_like_str_image):\n",
    "    return np.asarray(Image.open(io.BytesIO(byte_like_str_image['bytes'])))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "daafde17-8100-4f49-b27e-8aad43b129c6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-04-03T17:22:20.343090Z",
     "iopub.status.busy": "2024-04-03T17:22:20.341876Z",
     "iopub.status.idle": "2024-04-03T17:22:27.888815Z",
     "shell.execute_reply": "2024-04-03T17:22:27.887812Z",
     "shell.execute_reply.started": "2024-04-03T17:22:20.343047Z"
    }
   },
   "outputs": [],
   "source": [
    "dataset_train = dataset['train'].to_pandas()\n",
    "dataset_train['image'] = dataset_train['image'].map(convert)\n",
    "\n",
    "dataset_test = dataset['test'].to_pandas()\n",
    "dataset_test['image'] = dataset_test['image'].map(convert)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "72022fd2-000d-4d5c-88d5-9afc62c283d5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}