Merge branch 'master' of https://github.com/zergtant/pytorch-handbook

Author: zergtant

chapter5/5.3-Fashion-MNIST.ipynb

@@ -8,7 +8,7 @@
     {
      "data": {
       "text/plain": [
-       "'1.3.0'"
+       "'1.2.0'"
       ]
      },
      "execution_count": 1,
@@ -827,7 +827,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -866,9 +866,28 @@
     "    print(header_data)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "如下是训练的图片的二进制格式\n",
+    "\n",
+    "    [offset] [type]          [value]          [description]\n",
+    "    0000     32 bit integer  0x00000803(2051) magic number\n",
+    "    0004     32 bit integer  60000            number of images\n",
+    "    0008     32 bit integer  28               number of rows\n",
+    "    0012     32 bit integer  28               number of columns\n",
+    "    0016     unsigned byte   ??               pixel\n",
+    "    0017     unsigned byte   ??               pixel\n",
+    "    ........\n",
+    "    xxxx     unsigned byte   ??               pixel\n",
+    "    \n",
+    "有四字节的header_data，故使用`unpack_from`进行二进制转换时，偏置offset=16"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -880,7 +899,7 @@
     },
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAPsAAAD4CAYAAAAq5pAIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAASbElEQVR4nO3dbYyV5ZkH8P8FjA4wCIyADDABLBA0vgw6EiNo1GpD+QJVa8oHZaMujWmTNqlxjfuhJmYj0bXdmpAmUyXQpbVpUogYRUsICduglSNhB9zZXYFgGZjMCCjlTZiXaz/MYTPCPNd1OM85z3Pa6/9LJjNzrrnPuefM/OecM9dzP7eoKojo79+IvCdARNlg2ImCYNiJgmDYiYJg2ImCGJXljYlIqn/9i0hirdpdhVtvvTWx1tnZaY49fvx4pafzNXV1dYm13t7e3G47i9uny6nqsEGRNCERkSUAfgFgJIDXVXW18/WpEllfX59Y836p+vv709w0enp6EmvPPvusOXbdunWpbtszY8aMxJr3h6iat53F7dPlksJe9tN4ERkJYA2AbwO4EcAKEbmx3OsjoupK85p9IYD9qnpQVS8A+B2AZZWZFhFVWpqwTwdweMjnncXLvkZEVolIQUQKKW6LiFJK8w+64V4XXPaaXFXbALQB6V+zE1H50jyydwJoHvL5DABH002HiKolTdh3AZgrIrNF5CoA3wOwuTLTIqJKS9t6Wwrg3zDYelurqv/ifD2fxhNVWVX67FeKYSeqvor32YnobwvDThQEw04UBMNOFATDThQEw04UBMNOFATDThQEw04UBMNOFATDThQEw04UBMNOFATDThQEw04UBMNOFATDThQEw04UBMNOFATDThQEw04URKZbNgPV23Z53LhxZn3x4sVmfcuWLWXftvU9AcDIkSPNel9fX9m3nZY3d0+WZyemdPjIThQEw04UBMNOFATDThQEw04UBMNOFATDThRE5n32ESOS/7709/ebY+fMmZNYe+qpp8yx586dM+tnzpwx61999VVi7aOPPjLHpu2je71w6z71xqadm3cMgfczpeykCruIHAJwCkA/gD5Vba3EpIio8irxyH6fqh6rwPUQURXxNTtREGnDrgD+KCIfi8iq4b5ARFaJSEFECilvi4hSSPs0fpGqHhWRKQC2ish/q+qOoV+gqm0A2gBARLhqgignqR7ZVfVo8X0PgE0AFlZiUkRUeWWHXUTGisi4ix8D+BaAfZWaGBFVVpqn8dcB2FTs444C8FtVfc8aICJmX9bryd5///2JtQceeMAc29nZadavvvpqsz5mzJjE2oMPPmiOff311816d3e3WffWjKfpZTc0NJj1gYEBs3727Nmyb5uyVXbYVfUggFsrOBciqiK23oiCYNiJgmDYiYJg2ImCYNiJgsh0iauq4sKFC2WPv+OOOxJrs2bNMsd6SzGtZaIA8P777yfWFixYYI59+eWXzXqhYB9JvHfvXrPe0dGRWFu40D7OybpPAWDnzp1m/YMPPjDrJ0+eNOt05co9HTsf2YmCYNiJgmDYiYJg2ImCYNiJgmDYiYJg2ImCkCy33PXOVOMtFbX61RMmTDDH9vb2mnVvKadl165dZn3//v1mPc2xBwDQ1NSUWPO+b2/ujzzyiFlfs2aNWd++fbtZjyrtVtlJVBWqOuyV85GdKAiGnSgIhp0oCIadKAiGnSgIhp0oCIadKIia6rN/+OGH5nhvzbpz22bd27o4TS/c2u4Z8Hv8u3fvNutWH9/7vpYsWWLWr7/+erM+ffp0s07ZY5+dKDiGnSgIhp0oCIadKAiGnSgIhp0oCIadKIhMzxvv+eKLL8y6tW773Llz5lhvS+ZRo+y7wtra2Oujjx492qx7ffa7777brN91112JNe98+FOmTDHr771n7sJNf0PcR3YRWSsiPSKyb8hljSKyVUQ+Lb6fWN1pElFapTyNXwfg0sOsngOwTVXnAthW/JyIapgbdlXdAeDEJRcvA7C++PF6AMsrPC8iqrByX7Nfp6pdAKCqXSKS+MJPRFYBWFXm7RBRhVT9H3Sq2gagDfAXwhBR9ZTbeusWkSYAKL7vqdyUiKgayg37ZgArix+vBPBWZaZDRNXiPo0XkTcB3Atgkoh0AvgpgNUAfi8iTwL4C4DvVmIyY8aMMetWz9jrJ589e9ase/uIHz9+PLHmrbP3zhngrbX3vjfrfuvv7zfHej3+5uZms07lsX7m3s/b+5kmccOuqisSSt8s6xaJKBc8XJYoCIadKAiGnSgIhp0oCIadKIhMl7iOGDHCbBNNmzbNHH/+/PmyaoC/xNU7VbTVuvO2i7badoDfcrzqqqvM+qlTpxJr48ePN8e2t7ebdWtpLwC0traa9UKhYNajstqxI0eONMeW23rjIztREAw7URAMO1EQDDtREAw7URAMO1EQDDtREJn22RsbG7Fs2bLE+tSpU83xn3/+eWIt7emax44da9atpZ5ej97r8ff29pp17zTX1vd+7bXXmmPXrFlj1ltaWsy6NzcannW/pdke3MJHdqIgGHaiIBh2oiAYdqIgGHaiIBh2oiAYdqIgxDvNcSU1NDToTTfdlFh/5513zPHWtsxp1wCPGzfOrFvbMnvr1evq6lLVvWMAvK2uLd5206+88opZ37BhQ9m37fFOse39zK1TMnvX7R374B23kSdVHfab4yM7URAMO1EQDDtREAw7URAMO1EQDDtREAw7URCZLkaeM2cO3n333cT6mTNnzPFWn907t7p3PIG1Vh6we7r19fXmWK9n60nT8/V60bfccotZ97ayTiPtsRF9fX2VnE6m7rnnnsTaww8/bI5dtGhRYu2xxx5LrLmP7CKyVkR6RGTfkMteEJEjIrKn+LbUux4iylcpT+PXAVgyzOU/V9WW4lvywzUR1QQ37Kq6A8CJDOZCRFWU5h90PxSR9uLT/IlJXyQiq0SkICIF7xhyIqqecsP+SwDfANACoAvAq0lfqKptqtqqqq3eyQ+JqHrKCruqdqtqv6oOAPgVgIWVnRYRVVpZYReRpiGffgfAvqSvJaLa4PbZReRNAPcCmCQinQB+CuBeEWkBoAAOAfh+KTc2MDBg7nPuvaa3eune+cu9nq01L8DuCXvnhff68N4xAN7cLN7xB6dPnzbrDz30kFl/++23r3hOF5W7z3ipGhsbE2vTpk0zx86dO9ese+O9+23evHmJtfPnz5tjrXX61u+pG3ZVXTHMxW9444iotvBwWaIgGHaiIBh2oiAYdqIgGHaiIDJd4uq13rwj7I4ePZpY806J7LWgpkyZYtatbXTHjBljjt25c6dZb2hoMOvWckjAXuLqLVH1ls/eeeedZj0N77pffPFFsz558mSzPmHChMSa1/bzlt9++eWXZt1bfnvq1KnEmrdls3UabOt3gY/sREEw7ERBMOxEQTDsREEw7ERBMOxEQTDsREFk2mfv7+83txf2+tGPPvpoYq1QKJhjvS2ZvWWFs2bNMuuWm2++2ax7czt8+LBZt45dGD16tDnW6/HPnDnTrHusfvVrr71mjm1qajLrXq/cqqdZNgz4x214c7NOi+4ZP358Ys1a/spHdqIgGHaiIBh2oiAYdqIgGHaiIBh2oiAYdqIgMu2z19fXY/78+Yn11atXm+Ot3uTTTz9tjrXWwgP+evht27Yl1g4ePGiO9U5L7K3j99Y319XVJdasvivgr2f3trL2PP7444k1r4d/4MABs+4dI2DVrdNMl8K6zwG7Fw7Yx054v6vW+ROs05LzkZ0oCIadKAiGnSgIhp0oCIadKAiGnSgIhp0oiEz77L29veju7k6sr1+/3hy/fPnyxJq3dbC3Ht3r2d5+++2Jtfvuu88c6/W6vT66tyW0t7ba4q279vrJzc3NZr2npyex5q3TT3sOAuv6vZ+3d59ec801Zv3EiRNm/bPPPkuseXOzjjdJdd54EWkWke0i0iEin4jIj4qXN4rIVhH5tPh+onddRJSfUp7G9wH4iareAOBOAD8QkRsBPAdgm6rOBbCt+DkR1Sg37Krapaq7ix+fAtABYDqAZQAuPu9eDyD5OTYR5e6K/kEnIrMALADwZwDXqWoXMPgHAcCwm6WJyCoRKYhIwTr/HBFVV8lhF5EGAH8A8GNV/Wup41S1TVVbVbV14kS+rCfKS0lhF5E6DAb9N6q6sXhxt4g0FetNAJL/7UpEuXNbbzK4P+wbADpU9WdDSpsBrASwuvj+Le+6+vv7cfz48cS6t83tpk2bEmt79+41x3qtN2/Jo9Ue87bv9ZaRet+31U4B7PaYN9ba/hfwW1Dz5s0z60eOHEmsWcsxAaCzs9Osjx071qxPmjQpseb9zI4dO2bWvaW/o0bZ0bLaqV67s76+PrFmtXlL6bMvAvAYgL0isqd42fMYDPnvReRJAH8B8N0SrouIcuKGXVX/BCDpz/83KzsdIqoWHi5LFATDThQEw04UBMNOFATDThREpktcR40ahcmTJyfWvaWgVu/zhhtuMMeeOXPGrHvLLa1Dfb0lqF7PNm0f3hrvbdk8depUs37y5Emz3tLSYtZfffXVxNrGjRsTawDwxBNPmHXvlMvWKb69U4d7y0y9Xrh3v1vHL1jbXAP20t5US1yJ6O8Dw04UBMNOFATDThQEw04UBMNOFATDThREpn32gYEBs7/prW8+e/ZsYq2rq8sc6123d0pla31y2p6tdyppb+21VU/bw589e7ZZt04N7nnppZfM+p49e8z6M888Y9atcxh4xz5497l33IbXK7f67N5aeOu6rd9jPrITBcGwEwXBsBMFwbATBcGwEwXBsBMFwbATBZFpn72vr8/cwtfrhVtriL31xd75z73x3vnV04z1etVen94657133nhvPXt7e7tZ37Bhg1m3zlHgzW3Lli2p6tZW2l6Pf+bMmWZ9/PjxZt07N4PVK/f67FYv3TqXPh/ZiYJg2ImCYNiJgmDYiYJg2ImCYNiJgmDYiYIQr7ctIs0Afg1gKoABAG2q+gsReQHAPwK4uFH186r6rnVdt912m+7YsSOxbvXgAbsPb+0DDvg93dOnT5t1b32yxbuPvTXn1jp+wO7pbt261Rzb0dFh1nfu3GnWo5o/f75Zt/aGB+z18jNmzDDHHjp0yKydO3du2AM7Sjmopg/AT1R1t4iMA/CxiFz8Dfq5qv5rCddBRDkrZX/2LgBdxY9PiUgHgOnVnhgRVdYVvWYXkVkAFgD4c/GiH4pIu4isFZGJCWNWiUhBRAreqYCIqHpKDruINAD4A4Afq+pfAfwSwDcAtGDwkX/YTb1UtU1VW1W11XsdQ0TVU1LYRaQOg0H/japuBABV7VbVflUdAPArAAurN00iSssNuwwu2XoDQIeq/mzI5U1Dvuw7APZVfnpEVCmltN4WA/gPAHsx2HoDgOcBrMDgU3gFcAjA94v/zEtUX1+vVlvhwIEDpc6biBKoanmtN1X9E4DhBps9dSKqLTyCjigIhp0oCIadKAiGnSgIhp0oCIadKAi3z17RGxPJ7saIgkrqs/ORnSgIhp0oCIadKAiGnSgIhp0oCIadKAiGnSiITLdsBnAMwGdDPp9UvKwW1ercanVeAOdWrkrOLXGv6UwPqrnsxkUKqtqa2wQMtTq3Wp0XwLmVK6u58Wk8URAMO1EQeYe9Lefbt9Tq3Gp1XgDnVq5M5pbra3Yiyk7ej+xElBGGnSiIXMIuIktE5H9EZL+IPJfHHJKIyCER2Ssie0SkkPNc1opIj4jsG3JZo4hsFZFPi++H3WMvp7m9ICJHivfdHhFZmtPcmkVku4h0iMgnIvKj4uW53nfGvDK53zJ/zS4iIwH8L4AHAXQC2AVghar+V6YTSSAihwC0qmruB2CIyD0ATgP4tareVLzsZQAnVHV18Q/lRFX9pxqZ2wsATue9jXdxt6KmoduMA1gO4B+Q431nzOtRZHC/5fHIvhDAflU9qKoXAPwOwLIc5lHzVHUHgBOXXLwMwPrix+sx+MuSuYS51QRV7VLV3cWPTwG4uM14rvedMa9M5BH26QAOD/m8E7W137sC+KOIfCwiq/KezDCuu7jNVvH9lJzncyl3G+8sXbLNeM3cd+Vsf55WHmEf7vxYtdT/W6SqtwH4NoAfFJ+uUmlK2sY7K8NsM14Tyt3+PK08wt4JoHnI5zMAHM1hHsNS1aPF9z0ANqH2tqLuvriDbvF9T87z+X+1tI33cNuMowbuuzy3P88j7LsAzBWR2SJyFYDvAdicwzwuIyJji/84gYiMBfAt1N5W1JsBrCx+vBLAWznO5WtqZRvvpG3GkfN9l/v256qa+RuApRj8j/wBAP+cxxwS5nU9gP8svn2S99wAvInBp3W9GHxG9CSAawFsA/Bp8X1jDc3t3zG4tXc7BoPVlNPcFmPwpWE7gD3Ft6V533fGvDK533i4LFEQPIKOKAiGnSgIhp0oCIadKAiGnSgIhp0oCIadKIj/A+CVYyMlYQqWAAAAAElFTkSuQmCC\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -893,13 +912,13 @@
    ],
    "source": [
     "with open(DATA_PATH / \"train-images-idx3-ubyte\", 'rb') as file_object:\n",
-    "    raw_img = file_object.read(28*28)\n",
-    "    img = struct.unpack(\">784B\",raw_img)\n",
-    "    image = np.asarray(img)\n",
-    "    image = image.reshape((28,28))\n",
-    "    print(image.shape)\n",
-    "    plt.imshow(image,cmap = plt.cm.gray)\n",
-    "    plt.show()"
+    "    raw_img=file_object.read()\n",
+    "img = struct.unpack_from(\">784B\",raw_img,16)\n",
+    "image = np.asarray(img)\n",
+    "image = image.reshape((28,28))\n",
+    "print(image.shape)\n",
+    "plt.imshow(image,cmap = plt.cm.gray)\n",
+    "plt.show()"
    ]
   },
   {
@@ -1833,9 +1852,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "deep learning",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "dl"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -1847,7 +1866,20 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.9"
+   "version": "3.7.3"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "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,