diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..354a328
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+dataset/
\ No newline at end of file
diff --git a/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
new file mode 100644
index 0000000..9ee776c
--- /dev/null
+++ b/.ipynb_checkpoints/Untitled-checkpoint.ipynb
@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "436898c4-ee2b-47b5-a8a3-e7208a038d07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def unpickle(file):\n",
+    "    import pickle\n",
+    "    with open(file, 'rb') as fo:\n",
+    "        dict = pickle.load(fo, encoding='bytes')\n",
+    "    return dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9d98f5a7-926f-4c29-9e20-3ab7fdf480f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d = unpickle(\"dataset/cifar10/data_batch_1\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "687f639e-1311-4cfe-bdb6-0812d707aadc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict_keys([b'batch_label', b'labels', b'data', b'filenames'])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4e7c5423-41c9-4f8f-bab2-98e501e47b14",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[6, 9, 9, 4, 1]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d[b'labels'][:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e640b099-80b9-4657-9b96-13da64ccab56",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 59,  43,  50, ..., 140,  84,  72],\n",
+       "       [154, 126, 105, ..., 139, 142, 144],\n",
+       "       [255, 253, 253, ...,  83,  83,  84],\n",
+       "       [ 28,  37,  38, ...,  28,  37,  46],\n",
+       "       [170, 168, 177, ...,  82,  78,  80]], dtype=uint8)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d[b'data'][:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1d69d06c-29e6-4b08-ba70-a13a76ccf223",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x216929e6508>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.imshow(d[b'data'][0].reshape((32,32,3)))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python (cs4243)",
+   "language": "python",
+   "name": "cs4243"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Untitled.ipynb b/Untitled.ipynb
new file mode 100644
index 0000000..9ee776c
--- /dev/null
+++ b/Untitled.ipynb
@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "436898c4-ee2b-47b5-a8a3-e7208a038d07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def unpickle(file):\n",
+    "    import pickle\n",
+    "    with open(file, 'rb') as fo:\n",
+    "        dict = pickle.load(fo, encoding='bytes')\n",
+    "    return dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9d98f5a7-926f-4c29-9e20-3ab7fdf480f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d = unpickle(\"dataset/cifar10/data_batch_1\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "687f639e-1311-4cfe-bdb6-0812d707aadc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict_keys([b'batch_label', b'labels', b'data', b'filenames'])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4e7c5423-41c9-4f8f-bab2-98e501e47b14",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[6, 9, 9, 4, 1]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d[b'labels'][:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e640b099-80b9-4657-9b96-13da64ccab56",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 59,  43,  50, ..., 140,  84,  72],\n",
+       "       [154, 126, 105, ..., 139, 142, 144],\n",
+       "       [255, 253, 253, ...,  83,  83,  84],\n",
+       "       [ 28,  37,  38, ...,  28,  37,  46],\n",
+       "       [170, 168, 177, ...,  82,  78,  80]], dtype=uint8)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "d[b'data'][:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1d69d06c-29e6-4b08-ba70-a13a76ccf223",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x216929e6508>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.imshow(d[b'data'][0].reshape((32,32,3)))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python (cs4243)",
+   "language": "python",
+   "name": "cs4243"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}