diff --git a/be_image_classification.ipynb b/be_image_classification.ipynb
index 807001d319129c6873c335e6ddb8d95695ba69c4..50ea54d87615dc94b2be3671cb939cd8aa982e1d 100644
--- a/be_image_classification.ipynb
+++ b/be_image_classification.ipynb
@@ -9,7 +9,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
@@ -18,7 +18,7 @@
"((60000, 3072), (60000,))"
]
},
- "execution_count": 1,
+ "execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@@ -32,12 +32,12 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
- "image/png": "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",
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaAAAAGzCAYAAABpdMNsAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAxQ0lEQVR4nO3de3DV9Z3/8de5554QILcSKEgFLUKnVNP8bF0rVKAzjla2o60zi11HRzc4q6xbm92q1e5OXJ2x2v4ozs660M4Wbe0UHZ2trqLEn1ughcoPrbsU2FjCkouguefcv78/XNJfCujnDQmfJDwfM2eGnPPmnc/3cs47JznndUJBEAQCAOAsC/teAADg3MQAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAs6SVCqlu+++W3V1dSosLFRDQ4Neeukl38sCvGEAAWfJjTfeqEceeUQ33HCDHnvsMUUiEX3pS1/S66+/7ntpgBchwkiB8ferX/1KDQ0Nevjhh3XXXXdJkpLJpBYtWqSqqir98pe/9LxC4OzjGRBwFvzsZz9TJBLRLbfcMnJdQUGBbrrpJm3fvl3t7e0eVwf4wQACzoI33nhD559/vsrKykZdf8kll0iS9uzZ42FVgF8MIOAs6OjoUG1t7QnXH7/uyJEjZ3tJgHcMIOAsGB4eViKROOH6goKCkduBcw0DCDgLCgsLlUqlTrg+mUyO3A6caxhAwFlQW1urjo6OE64/fl1dXd3ZXhLgHQMIOAs+9alP6Xe/+536+vpGXb9z586R24FzDQMIOAv+9E//VLlcTv/4j/84cl0qldLGjRvV0NCg+vp6j6sD/Ij6XgBwLmhoaNBXvvIVNTc3q7u7W/Pnz9cPf/hDvfPOO3riiSd8Lw/wgiQE4CxJJpO655579C//8i96//33tXjxYn3nO9/RihUrfC8N8IIBBADwgr8BAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvJhwb0TN5/M6cuSISktLFQqFfC8HAGAUBIH6+/tVV1encPjUz3Mm3AA6cuQIsSQAMAW0t7dr1qxZp7x9wg2g0tJSSdKvfv0rlZSUuP2nkPtvEuPG2PtUNu9cm4jFTL2zmSHn2kgkbuqtvPv7ixNR229iU+mMqT4UiTjXZrJpU+9Y1H2/ZG3LVjTsvm4Z388dCtvqc4bjGQ7ZzsNc4H6OB8qZeitk2E7DNkpSJOJ+3uZkPT6mcmUNa49FbA+7uVTWuTYRNZyzkoaT7neKfOB+3xwYGFDjZxtGHs9PZdwG0Pr16/Xwww+rs7NTS5Ys0fe///2Rjx/+MMd/7VZSUvKRi//DfzIMoKIi51pJimfc73CJuG1IZNPuJ0skeuKHmX2onPuDSkHMdtImU7YhETLcKTIZ6wBy3y/ZjO1BKBo23D0YQCcXcu9tH0Du51VOhnVonAdQ1Hh8DEMiEbU9pEdj7vc3ywA67qP+jDIuL0L4yU9+onXr1um+++7Tb37zGy1ZskQrVqxQd3f3eHw7AMAkNC4D6JFHHtHNN9+sr3/967rwwgv1+OOPq6ioSP/8z/98Qm0qlVJfX9+oCwBg6hvzAZROp7V7924tX778D98kHNby5cu1ffv2E+pbWlpUXl4+cuEFCABwbhjzAXT06FHlcjlVV1ePur66ulqdnZ0n1Dc3N6u3t3fk0t7ePtZLAgBMQN5fBZdIJJRIGP/ADgCY9Mb8GdCMGTMUiUTU1dU16vquri7V1NSM9bcDAExSYz6A4vG4li5dqq1bt45cl8/ntXXrVjU2No71twMATFLj8iu4devWac2aNfrMZz6jSy65RI8++qgGBwf19a9/fTy+HQBgEhqXAXTdddfp3Xff1b333qvOzk596lOf0gsvvHDCCxM+TDqTU9rxTaBBgeMbViUdONTjXCtJUcObxoaTtpeQx2LuWXcxDZp6pwxvukyrwNQ7bHwndyD3d3LL9p5YhQP3/RIxvhs+YihPGBIZJCluvOcFhrUPpYdNvdOGw5MNbPmM2Zz7G1dDlvNEH/xmxZXljbzSaSQnhNxPXGvGZdjwi6pI3vZG4Qvqp7sXD/U7l+bSKae6cXsRwtq1a7V27drxag8AmOT4OAYAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAX3j+O4VSiiUJFE4VOtQe63SNw/rPN9rHgs2tnOtcODLt/drskvTvg/hnrc6uKTb3/+90B59o97cdMvSMR22fax+UePRKJ2H4mqqxwr62Zbjvdq6a5RxTFCm1RPPmYbS2prHvESk/K/bySpMNHe51rO4/ZIqFygfu5Eg7b9okhiUfZnDGKxxjd4xobJkkhucXUHJcPuW9ozBjzU1jkHiE0f7r7sYzm3Gp5BgQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwYsJmwWWyOWUc86/ShrypwWFDgJSkokSRc23IsA5Jau92z9WqKHDPJZOk3gL3LKuBlC2bKhy25U2VGLKvPv6xSlPvC893r58103a6lyfcfz4rjLhnaklSENj2Yb/hGBUnbLl0Ibmft11dtiw4S0ZatDBh6h2OjN/DVz4wZscp61wbzrvXSlLWkpEXsj0GhQwjIDfcb6hNOtXxDAgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4MWEjeKJhANFwm5xGNG8IV7HlsSjwaFh59qYMY4lmss41yb7e0y9I2H3tURCtmiQAkPsiCRdNNs9zujTi6tMvUuK3CNt0oPvm3r3vud+fPqztuiWTN69tyQNJNOGWttJPpRx34eZnmOm3sPudx+VVU4z9VbcPXbGGn2Us53iyqfcj3+QcT+WkpQzRPGE4rbHIBnO23jIfR3xkNs6eAYEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8GLCZsGFcmmFcm6ZSaVR90yo2urptnXE3TOkkmlD8JWkmhpD9lXU9rNCX7973lTUsI2SNKuywFS/+BPu+W4zim3bue/gQefaV159xdT77T1vOtcmBwZMvUsqik31xUWVzrW/bzts6p3O55xrM6FCU++aWRc41164eImpd2mV+z6xpa9JYUP+miRFIu7nbTZjO8ezhmi/SGDLAcyG3deSkSEz0LGWZ0AAAC/GfAB9+9vfVigUGnVZuHDhWH8bAMAkNy6/gvvkJz+pl19++Q/fJDphf9MHAPBkXCZDNBpVTU3NeLQGAEwR4/I3oP3796uurk7z5s3TDTfcoEOHDp2yNpVKqa+vb9QFADD1jfkAamho0KZNm/TCCy9ow4YNamtr0+c//3n19/eftL6lpUXl5eUjl/r6+rFeEgBgAhrzAbRq1Sp95Stf0eLFi7VixQr967/+q3p6evTTn/70pPXNzc3q7e0dubS3t4/1kgAAE9C4vzqgoqJC559/vg4cOHDS2xOJhBKJxHgvAwAwwYz7+4AGBgZ08OBB1dbWjve3AgBMImM+gO666y61trbqnXfe0S9/+Ut9+ctfViQS0Ve/+tWx/lYAgElszH8Fd/jwYX31q1/VsWPHNHPmTH3uc5/Tjh07NHPmTFOfUC5QKBc41cajEee++ZBbz+N6BtzjdRJh90gTSUqnss61qVipqXco5x5PNL04buo9f265qX7aNPe1HDvaber9zoHfOdcmQrbIocoK933+bnLI1DsSct8nklQQd4/ASadswTPDafe1h6K2c3zg/Xedaw8f/r2p9+xC9/t9YVmZqXfEvbUkKV7g/h/SxmMfDtyfJ0RjtucUhiQe5Q2RTXnHSKAxH0BPPfXUWLcEAExBZMEBALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALwY949jOF3xWELxmNvHNOSS7n1jhbaPfgii7rsol7HlgRWWued7JQNjdlihe/38WltGWt1022kTCrsfoHzOlmP22c982rm2cvkyU+981j37qu8UH7h4KgM5t6ys41I5933edfSoqXf/cI9zbW+v4c4mqavLvX4gadwnwynn2kTCvVaSckHGVB9LuOcGxmK2PErHSMz/6W0MsZN780TCPTMynXZ7/OEZEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADAiwkbxZPKZRTPucVhDBjSW/a322JKUpYIHGMUTyTqHpuRTNqiQSpL3COHPr2wztR7ZrEtFigedo+0qameaepd5BjXJElR489b+cA9GqagwLZPSg0RKJI0bDgPi6sqTL0HMoPOtUPDptaK7T/mXNvRZYsziobdI6QyaVsUjwy9JSmdzTrXhkK2yKFszr13OGI7r0Ih9/p02v2BNp12e7ziGRAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADAiwmbBRdOxBVOxJ1q03LPSetN2nKY+tPuWUmhnHu2myTlQu4ZT5GIbd2zytwP7fQy288hBbLlZIXlvl+iYVuWlRzzAiVJgW3dps0M3I+lJMVztuOpwH2/pAy1khQx/Bwai9geMkIh9wy74bR7ZqAklZUUOdeGjfs7CBlzA0PuJ0s4bOsdDruv3ZLt9gH3+mjM/VhGY27nCc+AAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF5M2Cy4dCqrdNwtXysSdt+McMSW1xZLGHqbOkshw7or4mlT7zmV7jlZpe4RT5KkqGyZXZYcMxkytSRbXJuxtal31HheRQz5eJKkvPs+L5It9yxrWEsmZduJQd49Iy9qPD4Rw3kVS9hO8qwxTy+dM9wnDPtEkhLxhHNtKGw7r8KGbL90JmmoddsfPAMCAHhhHkCvvfaarrrqKtXV1SkUCumZZ54ZdXsQBLr33ntVW1urwsJCLV++XPv37x+r9QIApgjzABocHNSSJUu0fv36k97+0EMP6Xvf+54ef/xx7dy5U8XFxVqxYoWSSfenbwCAqc/8N6BVq1Zp1apVJ70tCAI9+uij+ta3vqWrr75akvSjH/1I1dXVeuaZZ3T99def2WoBAFPGmP4NqK2tTZ2dnVq+fPnIdeXl5WpoaND27dtP+n9SqZT6+vpGXQAAU9+YDqDOzk5JUnV19ajrq6urR277Yy0tLSovLx+51NfXj+WSAAATlPdXwTU3N6u3t3fk0t7e7ntJAICzYEwHUE1NjSSpq6tr1PVdXV0jt/2xRCKhsrKyURcAwNQ3pgNo7ty5qqmp0datW0eu6+vr086dO9XY2DiW3woAMMmZXwU3MDCgAwcOjHzd1tamPXv2qLKyUrNnz9Ydd9yhv/u7v9MnPvEJzZ07V/fcc4/q6up0zTXXjOW6AQCTnHkA7dq1S1/4whdGvl63bp0kac2aNdq0aZO+8Y1vaHBwULfccot6enr0uc99Ti+88IIKCgpM3yceiyseizvVBoF7tEXYGPcRDhviPozPJ6MR996zZpabes+aOc25NmFMhQkZo3hCYfcdYz0+lnJjuookw38w9g6suUCGcyuct0XxhAP3EyDrGLFyXDKVMtWPl0jEdueMWM9Dw+NEKmWL4onGCw3rsG1nYDhXYjH3OKNYzG20mAfQ5ZdfruBD7smhUEgPPPCAHnjgAWtrAMA5xPur4AAA5yYGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAtzFM/ZkkoNKx53W14k4pYZJ0kh68g1xGoFuYypdWmBe+BUvSHbTZJKCt0PbSRkW7cxJksy5J5ZI9Isx8fOfTGBcSEhY+hdNOSe1xa1RY0pyLqvfWjQlu02lHQ/t7J5W6BeLjDkmJk6SyFjuF88asnTs/XOZN33YXGJLXMzasjISyWHnWvTqaRTHc+AAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeTNgonkQirkTCLWInP+geyREK2WIwIhH3yJSYsXfdtBLn2upyW8RGIpRzro0YY2RsWynlA/f/Ye0dGOJy8nnbdkai7nePWMQ9ikWSBobdY00kKZVxj8AJQra7dSRwj7IaGrJF8aQy7vs8b8xhyhnOK8s5KElh430iGnX/WT5ifJwYTLmfKxUV5abeYcM9rsAxGk2SMjG3Wp4BAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALyYsFlwqdSwYo7ZQ5GIe06aMW7KpKjAPVNLkqoqip1rE2H3bDdJCuXSzrWBbL3zIdvPLYFhn1uy3SQpCNwzu6Jh2+ne3d3lXPt/tv/S1Hv3m//XVP/+e+851xYWlJp6z1m41Lm2pHahqXfakAWXMwYB5gzZfrmc8f4TtmXB5Q3tg3zW1Dubdl9LNuN+v5dsGXapZNK9NuVWyzMgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXEzaKJx5LKBFLONXmhtzjWyKxmGkdYUM+SHmpLYqnvNh9/ieitoiaRNQQTxQYY0qMcTkKu+/DcN6WxxINuR/Pjv/uMPX+weP/27n25daXTL17+gZM9dlMxrk2nbbFsUSKf+FcO3/x/zL1XnTJF51riyvrTb1zhpiffNh2zoYitseJqCLuvfO2h91cJuVcmxp2j8uRpLwhJytS4P6YEsm4xQ3xDAgA4AUDCADghXkAvfbaa7rqqqtUV1enUCikZ555ZtTtN954o0Kh0KjLypUrx2q9AIApwjyABgcHtWTJEq1fv/6UNStXrlRHR8fI5cknnzyjRQIAph7zixBWrVqlVatWfWhNIpFQTU3NaS8KADD1jcvfgLZt26aqqiotWLBAt912m44dO3bK2lQqpb6+vlEXAMDUN+YDaOXKlfrRj36krVu36h/+4R/U2tqqVatWnfITCVtaWlReXj5yqa+3vRQTADA5jfn7gK6//vqRf1900UVavHixzjvvPG3btk3Lli07ob65uVnr1q0b+bqvr48hBADngHF/Gfa8efM0Y8YMHThw4KS3JxIJlZWVjboAAKa+cR9Ahw8f1rFjx1RbWzve3woAMImYfwU3MDAw6tlMW1ub9uzZo8rKSlVWVur+++/X6tWrVVNTo4MHD+ob3/iG5s+frxUrVozpwgEAk5t5AO3atUtf+MIXRr4+/vebNWvWaMOGDdq7d69++MMfqqenR3V1dbryyiv1ne98R4mEW67bcelURum4W/5VJFzs3DdqfM5XaMgxm1Ziy4ILG/KpjvX0m3r/d697fX9vj6l336BtLUND7vWZlC3LypId98bu3abeW19rda5NukVfjYjEikz14ZB7vlvEPZZMkpTOuOfSvf1r930iSenBYefa6rkXmXqH4+73t6LSQlPvigrbnwIqikuda3M5Y5Zi4P4wHSQHTa1DIfe1DKXc8wiH02615gF0+eWXKwhOfad/8cUXrS0BAOcgsuAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF6M+ecBjZVoPKZoPOZUmx10zz9K9r1nWkdO7llJhwe7Tb07Drrnew339Zp697/nvp3JIfcsMElKGfPaMsmUc20sfPIPLjyV4eGjzrVH3+sy9a5fuNC5trSiztQ7m7Ttw/5jnc61oZytd5DPO9dm87agucCQYZc8ut/UO1LonqeXHrZl7w0PuOdLStJAcYlzbXHClkunSIH7OgLbfTk5MMe5dnqZ2+OxJMWjbrU8AwIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeDFho3hyubRyObcYj1jUPS6ntMQWgzE07B4N09Vhi3oJAvcIlNJSWzRIvMI9NiNlPA2CfJ+pvqao3Lm2TO6xPZL05hH3+JYj+21RL9mIe7zKBYtrTb0D489+7Uc6nGtD6WFT71zGfZ/nDbE9khSE3M+timm2OKOa2fOdayNyj7ORpJjh2EtSoqDMubYwYTv2+bz7Y1AmaYviyabdY5tyGfcYplw241THMyAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFxM2Cy4c/uDiIrCM0VjCtI7kYNa5NpW35U3lDZldwxlbxtPQYI977/73Tb3zySFTfXmRe+177/7e1Dsy0O9cO9z9nqn3+6lu59ru7ndNvRV2zy+UpOywe2ZXyDGH67i8oT6bt/XOGrLghvO2nMbh2DHn2lCBbd2J4kFTfbyr07l2puUOIamycoZzbVGxLcPOkkkYDbtnwUUca3kGBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwYuJG8SiksBzjSkLusSaH/vuwaR3JXLFzbXFhqal3QUHcuTZWaPtZIVpX6VwbD+VMvZPv26J7akN9zrWpuHutJH1sdq1zbVdPr6l3z/59zrW5vG3dQSYw1UcNPyuGQnlT71zYfS22VUuBIb5lzsILTb1nnX+Rc+1w0hbFM2OG+/1HkgosKVyB7f6Wzbo/vlmPfT5wjxpTKGaodVszz4AAAF4wgAAAXpgGUEtLiy6++GKVlpaqqqpK11xzjfbtG/1rimQyqaamJk2fPl0lJSVavXq1urq6xnTRAIDJzzSAWltb1dTUpB07duill15SJpPRlVdeqcHBP0SX33nnnXruuef09NNPq7W1VUeOHNG111475gsHAExuphchvPDCC6O+3rRpk6qqqrR7925ddtll6u3t1RNPPKHNmzfriiuukCRt3LhRF1xwgXbs2KHPfvazJ/RMpVJKpVIjX/f12f6YCwCYnM7ob0C9vR+8qqiy8oNXjOzevVuZTEbLly8fqVm4cKFmz56t7du3n7RHS0uLysvLRy719fVnsiQAwCRx2gMon8/rjjvu0KWXXqpFixZJkjo7OxWPx1VRUTGqtrq6Wp2dJ//EwObmZvX29o5c2tvbT3dJAIBJ5LTfB9TU1KS33npLr7/++hktIJFIKJGwfUw2AGDyO61nQGvXrtXzzz+vV199VbNmzRq5vqamRul0Wj09PaPqu7q6VFNTc0YLBQBMLaYBFASB1q5dqy1btuiVV17R3LlzR92+dOlSxWIxbd26deS6ffv26dChQ2psbBybFQMApgTTr+Campq0efNmPfvssyotLR35u055ebkKCwtVXl6um266SevWrVNlZaXKysp0++23q7Gx8aSvgAMAnLtMA2jDhg2SpMsvv3zU9Rs3btSNN94oSfrud7+rcDis1atXK5VKacWKFfrBD35gXlgo+ODiIm54Ipfsf9e2kIR7VlJxUZmp9fQi95y5eJHtz3X5IPXRRf+j61CbqXem1/ZS+ZrzznOurZ83z9Q7GSSda9/8r0Om3r89+I5zbThnzPfK2+rzhvywvGy5ZzlDwls+b0uDixdWONcWlX7M1Lu03D2vrffdN029237/lqm+uma6c21giFSTpLAh67Kk0BJKJ6X6FzjXZivdj08ucMukMz2qBcFHn3wFBQVav3691q9fb2kNADjHkAUHAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADw4rQ/jmHcRRMfXFy4J1WooLDQtIx81LCLQm7xE8cNJwfcW8ds6+7rec+5NjuUNvWeU1Vnqk/IPXsknLdtZyzi/jPUx2pt644YeqeztmMvY6RNELhHQmVztrVkc+53oLwxR6ayYqZz7fCALeJpoLfLudYawbVn+6um+mjMsA8N55UklRaXONdWz3CPBJKkL33OPSQ6Nv/jzrVRx8dNngEBALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvJiwWXDpbKB01jEvK+y+GeUV5aZ1ZFTgXts/aOqdj7vngfX19Zt6HzzwjnPt/JpaU+9o2JYHpsB9OyMhW+900j0j7cLzF5h6X3rpxc61e94+YOr97rtHTfW5jHu+W9YSjigpWuCeNVY6rcbUO15c4VzbcaTN1Ltshvt2zplVZer9X0VxU30yPexcGwu7P6ZIUiTnXptLZWy9Q4YMu5z7QgLHPEKeAQEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvJiwUTyJREyJhFssS8Qx9kGShvreN60jXjTNubayvNjUuzDqHlHz1n/8ztS7p9c9FuhI5D1T7/gM930iSefXTXeujTge8+NCaffokYKIqbWuveqLzrUXLv6MqffzW39pqj/6vvsxysn9vJKk6rrZ7sUR2zl+5HC3c206mzT17u7qcq6tv2C+qffcueeZ6oeGh5xrC0pLTb1LStyjkmZW2u6bFRXu9bGY+30zGnMbLTwDAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHgxYbPg8umk8mm37KF4yD2jKJSx5U3F5Z419ok580y92w+941wbjdoOVWmle/6aCgtMvbNFtvo+pZxrY8Pu+1uScqmsc204ZOtdVuT+81ld9UxT79nnf8pUHz56zLk2H7jvE0kqKChyrk0l3XMXJSkfjjvXRmK2n4f7+tPOtfsPHjb1jsZteW3FMfe8tmzMltXXn3M/b2NJ90w6ScpHQs616Yz7/s5k3NbMMyAAgBemAdTS0qKLL75YpaWlqqqq0jXXXKN9+/aNqrn88ssVCoVGXW699dYxXTQAYPIzDaDW1lY1NTVpx44deumll5TJZHTllVdqcHB09P/NN9+sjo6OkctDDz00posGAEx+pj8svPDCC6O+3rRpk6qqqrR7925ddtllI9cXFRWppqZmbFYIAJiSzuhvQL29vZKkysrKUdf/+Mc/1owZM7Ro0SI1NzdraOjUfxhLpVLq6+sbdQEATH2n/Sq4fD6vO+64Q5deeqkWLVo0cv3XvvY1zZkzR3V1ddq7d6/uvvtu7du3Tz//+c9P2qelpUX333//6S4DADBJnfYAampq0ltvvaXXX3991PW33HLLyL8vuugi1dbWatmyZTp48KDOO+/Ej7ltbm7WunXrRr7u6+tTfX396S4LADBJnNYAWrt2rZ5//nm99tprmjVr1ofWNjQ0SJIOHDhw0gGUSCSUSCROZxkAgEnMNICCINDtt9+uLVu2aNu2bZo7d+5H/p89e/ZIkmpra09rgQCAqck0gJqamrR582Y9++yzKi0tVWdnpySpvLxchYWFOnjwoDZv3qwvfelLmj59uvbu3as777xTl112mRYvXjwuGwAAmJxMA2jDhg2SPniz6f9v48aNuvHGGxWPx/Xyyy/r0Ucf1eDgoOrr67V69Wp961vfGrMFAwCmBvOv4D5MfX29Wltbz2hBx8XjUcXjbsubZsibOr/GkJEmKRe4v1K9OBEx9R7O5NyLw7be5aXu2VQzp9v2SSZvy1TrODb40UX/oyflXitJ4ZB7rla8sNjUu7N3wLm2rdP29oFhw6GXpGzI/RzP5d3zvSRJGfd9mA/ZeufknkuXz7lnBkpSaNg9A/L37e+ZehfH3XtLUn19nXNtpMx2Hna/554DmI7YHieSeff6eMJ93bG0W2YgWXAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC9O+/OAxls6k1E64xb5kihyjympcC+VJBWUFDrXFsbTpt61Ve6945EyU+9oyP1ni3jMPYpFkjIpt5iN44rj7tupkHt0iyTlI0nn2qCk1NT7/d5h59pokXv0kSTNmWXb5zOmu0fDZDK28zCft63ForK42rk2yNnWHY8WONeGDXFdkpTJ2tYyZ477dk6rtn3eWffRfufasrjtOUXlNPcYruFh9/taMulWyzMgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcTNgsuHo0rHnXLb0olh5z7zqgstq3DkDNXGHPPDpOk86oTzrUfnzbD1FuGeK9QYMsCSxoyoSSp/71B59rCyiJT74ghZ67zaKepd13VNOfainLb8cnnbPswmzVk3pmj3Sz/IWTqHAq7947EbD8Phwx5h0FgW7dtn0jRaMS5trcvZerdkXBfe0Wx7f5TXuA+AhJx9zzCdMytlmdAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvJmwUTzaTVTaTdaqNx91jMM6bXW9aR0Gxe1xOYIzviOTd121sbavP25pbo3v6B9yjkkIR2ykZirivpa5mpql31DEKSpIKC0tMvYNM2lSfNdSHQrbYmXDYvT5iPD7RmHt92FArSYYkHnM+kfnuZvgPA/3u0VSS1D/LvT4adY/LkaSqyjLn2r6eXufaTMotOopnQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvJmwWnMWxd4851xaXFJl6J/vcMo0kqaCw0NQ7lXLP9ypIFJh6J4eH3XvH3TPPJCk1bMsxKy503+eDw+65cZIUj7pn9ZUXlZt6h+SekRZk3XIL/9Db9rNfxLCd0ajtbp3P551rA2umWsa9Np227cNozP34ZHO2czZmzFTLGraztNh2HsZj7se+IOFeK0nvv3fUuTZmyAEMh9zOE54BAQC8MA2gDRs2aPHixSorK1NZWZkaGxv1i1/8YuT2ZDKppqYmTZ8+XSUlJVq9erW6urrGfNEAgMnPNIBmzZqlBx98ULt379auXbt0xRVX6Oqrr9Zvf/tbSdKdd96p5557Tk8//bRaW1t15MgRXXvtteOycADA5Gb6ZfFVV1016uu///u/14YNG7Rjxw7NmjVLTzzxhDZv3qwrrrhCkrRx40ZdcMEF2rFjhz772c+O3aoBAJPeaf8NKJfL6amnntLg4KAaGxu1e/duZTIZLV++fKRm4cKFmj17trZv337KPqlUSn19faMuAICpzzyA3nzzTZWUlCiRSOjWW2/Vli1bdOGFF6qzs1PxeFwVFRWj6qurq9XZ2XnKfi0tLSovLx+51NfbPrEUADA5mQfQggULtGfPHu3cuVO33Xab1qxZo7fffvu0F9Dc3Kze3t6RS3t7+2n3AgBMHub3AcXjcc2fP1+StHTpUv3617/WY489puuuu07pdFo9PT2jngV1dXWppqbmlP0SiYQSxteuAwAmvzN+H1A+n1cqldLSpUsVi8W0devWkdv27dunQ4cOqbGx8Uy/DQBgijE9A2pubtaqVas0e/Zs9ff3a/Pmzdq2bZtefPFFlZeX66abbtK6detUWVmpsrIy3X777WpsbOQVcACAE5gGUHd3t/7sz/5MHR0dKi8v1+LFi/Xiiy/qi1/8oiTpu9/9rsLhsFavXq1UKqUVK1boBz/4wWkt7G//9m8Vi7nFYbz7brdz3xkzZprW0dvb61xbVlFm6j0w1O/eu7TU1Lu/1/3VhCXFxabe1lcqFhW59x/oHzT1Li4qca7NZQx5KZKmTatwro1E3GNhJClsrE8bsl4GB21xRum0e0xN3hjFE424R9pkczlT70TC/eErnUmZesditniqdMp97YkiWxxYr+H+Vlrifn+QpN7333eunT690rk243hfMw2gJ5544kNvLygo0Pr167V+/XpLWwDAOYgsOACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBfmNOzxFvxP1IdrlIMkZbNZ51pL33HvnZmk6zb0tvYfz945Q5yNJKUNvSN5YxRPzhjFk3Nfi/V4ZgznYV62KJ4g716bzRuKJYXD7muxbOMHbMcnk3Vfe3iS3pctvY/XBh8R3RQKPqriLDt8+DAfSgcAU0B7e7tmzZp1ytsn3ADK5/M6cuSISktLFQr94aeQvr4+1dfXq729XWVlttDPyYTtnDrOhW2U2M6pZiy2MwgC9ff3q66uTuHwqf/SM+F+BRcOhz90YpaVlU3pg38c2zl1nAvbKLGdU82Zbmd5eflH1vAiBACAFwwgAIAXk2YAJRIJ3XfffUokEr6XMq7YzqnjXNhGie2cas7mdk64FyEAAM4Nk+YZEABgamEAAQC8YAABALxgAAEAvGAAAQC8mDQDaP369fr4xz+ugoICNTQ06Fe/+pXvJY2pb3/72wqFQqMuCxcu9L2sM/Laa6/pqquuUl1dnUKhkJ555plRtwdBoHvvvVe1tbUqLCzU8uXLtX//fj+LPQMftZ033njjCcd25cqVfhZ7mlpaWnTxxRertLRUVVVVuuaaa7Rv375RNclkUk1NTZo+fbpKSkq0evVqdXV1eVrx6XHZzssvv/yE43nrrbd6WvHp2bBhgxYvXjySdtDY2Khf/OIXI7efrWM5KQbQT37yE61bt0733XeffvOb32jJkiVasWKFuru7fS9tTH3yk59UR0fHyOX111/3vaQzMjg4qCVLlmj9+vUnvf2hhx7S9773PT3++OPauXOniouLtWLFCiWTybO80jPzUdspSStXrhx1bJ988smzuMIz19raqqamJu3YsUMvvfSSMpmMrrzySg0ODo7U3HnnnXruuef09NNPq7W1VUeOHNG1117rcdV2LtspSTfffPOo4/nQQw95WvHpmTVrlh588EHt3r1bu3bt0hVXXKGrr75av/3tbyWdxWMZTAKXXHJJ0NTUNPJ1LpcL6urqgpaWFo+rGlv33XdfsGTJEt/LGDeSgi1btox8nc/ng5qamuDhhx8eua6npydIJBLBk08+6WGFY+OPtzMIgmDNmjXB1Vdf7WU946W7uzuQFLS2tgZB8MGxi8ViwdNPPz1S8x//8R+BpGD79u2+lnnG/ng7gyAI/uRP/iT4y7/8S3+LGifTpk0L/umf/umsHssJ/wwonU5r9+7dWr58+ch14XBYy5cv1/bt2z2ubOzt379fdXV1mjdvnm644QYdOnTI95LGTVtbmzo7O0cd1/LycjU0NEy54ypJ27ZtU1VVlRYsWKDbbrtNx44d872kM9Lb2ytJqqyslCTt3r1bmUxm1PFcuHChZs+ePamP5x9v53E//vGPNWPGDC1atEjNzc0aGhrysbwxkcvl9NRTT2lwcFCNjY1n9VhOuDTsP3b06FHlcjlVV1ePur66ulr/+Z//6WlVY6+hoUGbNm3SggUL1NHRofvvv1+f//zn9dZbb6m0tNT38sZcZ2enJJ30uB6/bapYuXKlrr32Ws2dO1cHDx7U3/zN32jVqlXavn27IpGI7+WZ5fN53XHHHbr00ku1aNEiSR8cz3g8roqKilG1k/l4nmw7JelrX/ua5syZo7q6Ou3du1d333239u3bp5///OceV2v35ptvqrGxUclkUiUlJdqyZYsuvPBC7dmz56wdywk/gM4Vq1atGvn34sWL1dDQoDlz5uinP/2pbrrpJo8rw5m6/vrrR/590UUXafHixTrvvPO0bds2LVu2zOPKTk9TU5PeeuutSf83yo9yqu285ZZbRv590UUXqba2VsuWLdPBgwd13nnnne1lnrYFCxZoz5496u3t1c9+9jOtWbNGra2tZ3UNE/5XcDNmzFAkEjnhFRhdXV2qqanxtKrxV1FRofPPP18HDhzwvZRxcfzYnWvHVZLmzZunGTNmTMpju3btWj3//PN69dVXR31uV01NjdLptHp6ekbVT9bjeartPJmGhgZJmnTHMx6Pa/78+Vq6dKlaWlq0ZMkSPfbYY2f1WE74ARSPx7V06VJt3bp15Lp8Pq+tW7eqsbHR48rG18DAgA4ePKja2lrfSxkXc+fOVU1Nzajj2tfXp507d07p4yp98LHzx44dm1THNggCrV27Vlu2bNErr7yiuXPnjrp96dKlisVio47nvn37dOjQoUl1PD9qO09mz549kjSpjufJ5PN5pVKps3ssx/QlDePkqaeeChKJRLBp06bg7bffDm655ZagoqIi6Ozs9L20MfNXf/VXwbZt24K2trbg3//934Ply5cHM2bMCLq7u30v7bT19/cHb7zxRvDGG28EkoJHHnkkeOONN4Lf//73QRAEwYMPPhhUVFQEzz77bLB3797g6quvDubOnRsMDw97XrnNh21nf39/cNdddwXbt28P2tragpdffjn49Kc/HXziE58Iksmk76U7u+2224Ly8vJg27ZtQUdHx8hlaGhopObWW28NZs+eHbzyyivBrl27gsbGxqCxsdHjqu0+ajsPHDgQPPDAA8GuXbuCtra24Nlnnw3mzZsXXHbZZZ5XbvPNb34zaG1tDdra2oK9e/cG3/zmN4NQKBT827/9WxAEZ+9YTooBFARB8P3vfz+YPXt2EI/Hg0suuSTYsWOH7yWNqeuuuy6ora0N4vF48LGPfSy47rrrggMHDvhe1hl59dVXA0knXNasWRMEwQcvxb7nnnuC6urqIJFIBMuWLQv27dvnd9Gn4cO2c2hoKLjyyiuDmTNnBrFYLJgzZ05w8803T7ofnk62fZKCjRs3jtQMDw8Hf/EXfxFMmzYtKCoqCr785S8HHR0d/hZ9Gj5qOw8dOhRcdtllQWVlZZBIJIL58+cHf/3Xfx309vb6XbjRn//5nwdz5swJ4vF4MHPmzGDZsmUjwycIzt6x5POAAABeTPi/AQEApiYGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADAi/8Hn+dUWJ8RFYYAAAAASUVORK5CYII=",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
@@ -63,7 +63,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
@@ -73,7 +73,7 @@
" [2.82842712, 0. ]])"
]
},
- "execution_count": 3,
+ "execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@@ -99,6 +99,13 @@
" evaluate_knn(train_data, train_labels, test_data, test_labels, 1)"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Get the accuracy of the knn model for each k value"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 6,
@@ -132,7 +139,7 @@
}
],
"source": [
- "if True:\n",
+ "if False:\n",
" data, labels = read_cifar('data/cifar-10-batches-py')\n",
" train_data, train_labels, test_data, test_labels = split_dataset(data, labels, 0.9)\n",
" k_values = list(np.arange(1, 21))\n",
@@ -162,35 +169,43 @@
"source": [
"from utils.process_image import save_plot_as_image\n",
"\n",
- "save_plot_as_image(k_values, accuracies, 'accuracy', 'k', 'images/knn_accuracy.png')"
+ "save_plot_as_image(k_values, accuracies, 'accuracy', 'k','Evolution de l\\'accuracy en fonction de k, 'images/knn_accuracy.png')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "The model have the best result for k = 1 (about 35% accuracy), and the worst with k=2"
]
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "(array([[ 0.328055 , -0.09295718, -0.33842638],\n",
- " [-0.11653052, 0.58325438, -0.13258186],\n",
- " [ 0.18900546, 0.51515747, -0.76910745]]),\n",
- " array([[-0.00083548, -0.00088441, 0.00035065]]),\n",
- " array([[ 0.06636073, 0.91268095],\n",
- " [ 0.24104642, 0.93511262],\n",
- " [-0.10002242, -0.39107094]]),\n",
- " array([[-0.00142651, -0.0036116 ]]),\n",
- " 0.08808324100066224)"
+ "(array([[ 0.79362828, -0.36932403, -0.44283967],\n",
+ " [-0.97139098, -0.75715536, 0.59671452],\n",
+ " [ 0.94666291, -0.32683836, 0.47777268]]),\n",
+ " array([[-0.0014528 , -0.00076639, -0.00166222]]),\n",
+ " array([[0.75131074, 0.52740138],\n",
+ " [0.41564149, 0.30933499],\n",
+ " [0.66218606, 0.72875506]]),\n",
+ " array([[-0.00490338, -0.00496067]]),\n",
+ " 0.1383631074551818)"
]
},
- "execution_count": 8,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from utils.learn_once_mse import learn_once_mse\n",
+ "import numpy as np\n",
"\n",
"N = 30 # number of input data\n",
"d_in = 3 # input dimension\n",
@@ -218,7 +233,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -229,7 +244,7 @@
" [1., 0., 0.]])"
]
},
- "execution_count": 9,
+ "execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -242,24 +257,24 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "(array([[ 0.3256724 , -0.09540915, -0.33746996],\n",
- " [-0.11805462, 0.58166566, -0.13193784],\n",
- " [ 0.18724356, 0.51319216, -0.76834097]]),\n",
- " array([[-0.00488305, -0.00512345, 0.00203958]]),\n",
- " array([[ 0.06319307, 0.90284858],\n",
- " [ 0.23713482, 0.92465898],\n",
- " [-0.1015984 , -0.39743855]]),\n",
- " array([[-0.00710872, -0.02124436]]),\n",
- " 0.7295273614523309)"
+ "(array([[ 0.78981139, -0.37130174, -0.44732111],\n",
+ " [-0.97530139, -0.75912051, 0.59234515],\n",
+ " [ 0.94351845, -0.32849849, 0.47405929]]),\n",
+ " array([[-0.00843903, -0.00445009, -0.00962447]]),\n",
+ " array([[0.73755152, 0.5135263 ],\n",
+ " [0.40785584, 0.30205767],\n",
+ " [0.64830103, 0.71534156]]),\n",
+ " array([[-0.02907245, -0.02827016]]),\n",
+ " 0.8159308284553612)"
]
},
- "execution_count": 10,
+ "execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -271,1414 +286,1426 @@
" "
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Entrainement du modèle\n",
+ "On entraine le modèle contenant une couche cachée de 64 neurones avec 100 epochs, un learning rate de 0.1 et une taille de batch de 512.\n",
+ "\n",
+ "En effet, j'ai rajouté un paramètre `batch_size` pour améliorer les performances lors de l'entrainement."
+ ]
+ },
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.65it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.44it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=0, loss=0.32536565848357263\n"
+ "epoch=0, loss=0.33420675013485945, train_accuracy=0.18577777777777776\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.07it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.16it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=1, loss=0.3121928702945571\n"
+ "epoch=1, loss=0.3188549057785522, train_accuracy=0.21144444444444443\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.83it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.26it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=2, loss=0.30543033970759537\n"
+ "epoch=2, loss=0.3111488909632828, train_accuracy=0.2247962962962963\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.68it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.35it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=3, loss=0.30164690368706953\n"
+ "epoch=3, loss=0.30636305132753144, train_accuracy=0.23548148148148149\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.90it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.06it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=4, loss=0.2988765995063212\n"
+ "epoch=4, loss=0.3032836133855315, train_accuracy=0.24598148148148147\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 49.07it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.06it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=5, loss=0.29671164791713306\n"
+ "epoch=5, loss=0.3010618635390122, train_accuracy=0.2552962962962963\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.40it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.53it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=6, loss=0.29488462530706594\n"
+ "epoch=6, loss=0.29940237009013365, train_accuracy=0.26151851851851854\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.09it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.16it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=7, loss=0.29324902660111213\n"
+ "epoch=7, loss=0.29803387124328845, train_accuracy=0.26681481481481484\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.29it/s]\n"
+ "100%|██████████| 106/106 [00:01<00:00, 53.21it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=8, loss=0.29213942600333603\n"
+ "epoch=8, loss=0.2967996819608651, train_accuracy=0.27246296296296296\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.94it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.26it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=9, loss=0.29089870566858717\n"
+ "epoch=9, loss=0.29573798736004925, train_accuracy=0.2767222222222222\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.40it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.06it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=10, loss=0.2895862699722007\n"
+ "epoch=10, loss=0.29489263888888023, train_accuracy=0.2817222222222222\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.09it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.63it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=11, loss=0.2884022627687656\n"
+ "epoch=11, loss=0.2940597046766028, train_accuracy=0.28583333333333333\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.28it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.67it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=12, loss=0.28733885125291764\n"
+ "epoch=12, loss=0.2930951674728663, train_accuracy=0.2902592592592593\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.49it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.35it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=13, loss=0.28634791216387434\n"
+ "epoch=13, loss=0.2921363403651519, train_accuracy=0.29303703703703704\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.18it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 52.17it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=14, loss=0.2854148514424351\n"
+ "epoch=14, loss=0.2913191804120471, train_accuracy=0.2968148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.90it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.48it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=15, loss=0.28452080362101867\n"
+ "epoch=15, loss=0.2905481194409614, train_accuracy=0.3003148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.99it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.09it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=16, loss=0.2836357456217646\n"
+ "epoch=16, loss=0.2897327618107022, train_accuracy=0.30348148148148146\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.99it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.48it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=17, loss=0.28274151613860843\n"
+ "epoch=17, loss=0.2888923251604361, train_accuracy=0.3059074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.90it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.91it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=18, loss=0.281839854415075\n"
+ "epoch=18, loss=0.288066184871282, train_accuracy=0.3079074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 48.01it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.17it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=19, loss=0.28095542557069053\n"
+ "epoch=19, loss=0.287267772576149, train_accuracy=0.30994444444444447\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.96it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.36it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=20, loss=0.2800934496802053\n"
+ "epoch=20, loss=0.2865018793391632, train_accuracy=0.31192592592592594\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.45it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 52.37it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=21, loss=0.27931142585321705\n"
+ "epoch=21, loss=0.2857739017693884, train_accuracy=0.3141481481481481\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.86it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.92it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=22, loss=0.27862350963341603\n"
+ "epoch=22, loss=0.2850868818943626, train_accuracy=0.31633333333333336\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.84it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.55it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=23, loss=0.2780074274940075\n"
+ "epoch=23, loss=0.28443768606878783, train_accuracy=0.31833333333333336\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.73it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.77it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=24, loss=0.27742971683164996\n"
+ "epoch=24, loss=0.28381835941097344, train_accuracy=0.3201111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.90it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.01it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=25, loss=0.2768283124909597\n"
+ "epoch=25, loss=0.28322076144879466, train_accuracy=0.3212037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.22it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.66it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=26, loss=0.2762288972410761\n"
+ "epoch=26, loss=0.2826426077267652, train_accuracy=0.3226111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.30it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.69it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=27, loss=0.27566807003953936\n"
+ "epoch=27, loss=0.28209041457192024, train_accuracy=0.32401851851851854\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.90it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 44.84it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=28, loss=0.27515791265861705\n"
+ "epoch=28, loss=0.28157442411695865, train_accuracy=0.32587037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.43it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.93it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=29, loss=0.2746960225210329\n"
+ "epoch=29, loss=0.28110218763111233, train_accuracy=0.3269444444444444\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.30it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.82it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=30, loss=0.2742732930281749\n"
+ "epoch=30, loss=0.2806757866602613, train_accuracy=0.32805555555555554\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.47it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.58it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=31, loss=0.2738820269527825\n"
+ "epoch=31, loss=0.28029173232982685, train_accuracy=0.3296851851851852\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.39it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.90it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=32, loss=0.2735185848652638\n"
+ "epoch=32, loss=0.2799433389227303, train_accuracy=0.33135185185185184\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.34it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 43.73it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=33, loss=0.27318125599929644\n"
+ "epoch=33, loss=0.2796231932174876, train_accuracy=0.33331481481481484\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.03it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.66it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=34, loss=0.27286824262978615\n"
+ "epoch=34, loss=0.27932445663304367, train_accuracy=0.3351296296296296\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.17it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.61it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=35, loss=0.2725772806445788\n"
+ "epoch=35, loss=0.27904132143046423, train_accuracy=0.337\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.26it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 42.06it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=36, loss=0.27230585256038187\n"
+ "epoch=36, loss=0.27876895714230787, train_accuracy=0.33820370370370373\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.63it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 44.17it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=37, loss=0.27205124966222294\n"
+ "epoch=37, loss=0.27850322994212867, train_accuracy=0.3394259259259259\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.32it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.85it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=38, loss=0.2718105212711061\n"
+ "epoch=38, loss=0.27824050162221153, train_accuracy=0.3405925925925926\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.01it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.66it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=39, loss=0.2715805048412975\n"
+ "epoch=39, loss=0.2779776936949417, train_accuracy=0.3416111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.55it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.99it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=40, loss=0.2713579421724202\n"
+ "epoch=40, loss=0.2777125812293511, train_accuracy=0.3430185185185185\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.75it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.07it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=41, loss=0.2711396156588283\n"
+ "epoch=41, loss=0.27744409078201326, train_accuracy=0.34424074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.51it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 44.92it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=42, loss=0.2709225155028859\n"
+ "epoch=42, loss=0.27717235824576475, train_accuracy=0.3454814814814815\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.47it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 43.30it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=43, loss=0.2707040834217827\n"
+ "epoch=43, loss=0.2768984772303961, train_accuracy=0.3462037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.42it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 44.31it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=44, loss=0.27048249024427656\n"
+ "epoch=44, loss=0.27662407090256175, train_accuracy=0.3471296296296296\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.65it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.15it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=45, loss=0.2702568222700594\n"
+ "epoch=45, loss=0.27635086651437507, train_accuracy=0.34779629629629627\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.82it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 41.73it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=46, loss=0.27002708728127284\n"
+ "epoch=46, loss=0.27608035980482853, train_accuracy=0.34885185185185186\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.43it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 41.73it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=47, loss=0.2697940526835046\n"
+ "epoch=47, loss=0.2758135960703844, train_accuracy=0.3496111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.13it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.92it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=48, loss=0.2695589991244579\n"
+ "epoch=48, loss=0.27555109288329865, train_accuracy=0.35053703703703704\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.92it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.07it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=49, loss=0.26932347844910215\n"
+ "epoch=49, loss=0.27529289019660375, train_accuracy=0.351462962962963\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.84it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.18it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=50, loss=0.2690891216931801\n"
+ "epoch=50, loss=0.27503866505292973, train_accuracy=0.35224074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.17it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 42.67it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=51, loss=0.26885749099705014\n"
+ "epoch=51, loss=0.2747878517717082, train_accuracy=0.35288888888888886\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.09it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 43.23it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=52, loss=0.26862995216471686\n"
+ "epoch=52, loss=0.27453973893869543, train_accuracy=0.35385185185185186\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.32it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.49it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=53, loss=0.2684075698601837\n"
+ "epoch=53, loss=0.27429353642850424, train_accuracy=0.3544259259259259\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.03it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 44.46it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=54, loss=0.26819105416268263\n"
+ "epoch=54, loss=0.27404841735400715, train_accuracy=0.3552037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.66it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.74it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=55, loss=0.26798077591671593\n"
+ "epoch=55, loss=0.2738035469545913, train_accuracy=0.3562777777777778\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.89it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.99it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=56, loss=0.26777683118236534\n"
+ "epoch=56, loss=0.2735581114679576, train_accuracy=0.356962962962963\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.74it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.93it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=57, loss=0.26757911457047184\n"
+ "epoch=57, loss=0.2733113537174717, train_accuracy=0.35785185185185187\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.86it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.71it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=58, loss=0.2673873741424862\n"
+ "epoch=58, loss=0.27306261312855745, train_accuracy=0.3587037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 44.93it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 42.40it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=59, loss=0.26720124679735535\n"
+ "epoch=59, loss=0.27281136238697473, train_accuracy=0.3594074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.88it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.75it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=60, loss=0.2670202876161004\n"
+ "epoch=60, loss=0.272557233231127, train_accuracy=0.35983333333333334\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.89it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.01it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=61, loss=0.26684400316153295\n"
+ "epoch=61, loss=0.2723000279240422, train_accuracy=0.3605\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.07it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.45it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=62, loss=0.2666718871083877\n"
+ "epoch=62, loss=0.2720397174578739, train_accuracy=0.36077777777777775\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.75it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.18it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=63, loss=0.2665034496901216\n"
+ "epoch=63, loss=0.27177643015041403, train_accuracy=0.3617037037037037\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.97it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.66it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=64, loss=0.26633823551333574\n"
+ "epoch=64, loss=0.2715104341185179, train_accuracy=0.36244444444444446\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.96it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.17it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=65, loss=0.2661758317738733\n"
+ "epoch=65, loss=0.2712421148052744, train_accuracy=0.3631111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.86it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.53it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=66, loss=0.2660158723596366\n"
+ "epoch=66, loss=0.27097194657809753, train_accuracy=0.36362962962962964\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.93it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.75it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=67, loss=0.2658580417813423\n"
+ "epoch=67, loss=0.2707004579663997, train_accuracy=0.3644074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 43.28it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.33it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=68, loss=0.2657020813316263\n"
+ "epoch=68, loss=0.2704281935309972, train_accuracy=0.36464814814814817\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.51it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.53it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=69, loss=0.2655477993399877\n"
+ "epoch=69, loss=0.27015567870185625, train_accuracy=0.3655\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.39it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.36it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=70, loss=0.265395083591377\n"
+ "epoch=70, loss=0.2698833941302225, train_accuracy=0.36616666666666664\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 43.41it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.01it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=71, loss=0.26524390709925844\n"
+ "epoch=71, loss=0.26961176313561314, train_accuracy=0.3668148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.23it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 52.37it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=72, loss=0.26509431618523055\n"
+ "epoch=72, loss=0.2693411520253892, train_accuracy=0.36757407407407405\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.01it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.61it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=73, loss=0.2649463967492245\n"
+ "epoch=73, loss=0.26907188041709956, train_accuracy=0.36827777777777776\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.89it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.58it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=74, loss=0.2648002256355748\n"
+ "epoch=74, loss=0.2688042375904098, train_accuracy=0.36907407407407405\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.63it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.86it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=75, loss=0.26465582150033307\n"
+ "epoch=75, loss=0.26853850076553537, train_accuracy=0.3695925925925926\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.41it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.26it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=76, loss=0.2645131100486962\n"
+ "epoch=76, loss=0.26827495151944597, train_accuracy=0.3698148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.51it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.67it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=77, loss=0.26437191201743476\n"
+ "epoch=77, loss=0.26801388718172725, train_accuracy=0.3703518518518519\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.09it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.16it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=78, loss=0.26423195246053405\n"
+ "epoch=78, loss=0.2677556250379854, train_accuracy=0.37072222222222223\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.63it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.71it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=79, loss=0.2640928834531869\n"
+ "epoch=79, loss=0.26750049843025353, train_accuracy=0.37164814814814817\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.22it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.00it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=80, loss=0.2639543124721884\n"
+ "epoch=80, loss=0.2672488451959534, train_accuracy=0.37187037037037035\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.24it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 48.45it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=81, loss=0.263815831592953\n"
+ "epoch=81, loss=0.2670009902032938, train_accuracy=0.37212962962962964\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.97it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.96it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=82, loss=0.26367704366914124\n"
+ "epoch=82, loss=0.26675722494266635, train_accuracy=0.37287037037037035\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.65it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.86it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=83, loss=0.2635375811525412\n"
+ "epoch=83, loss=0.26651778797618153, train_accuracy=0.37357407407407406\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.35it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 47.66it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=84, loss=0.26339711410007394\n"
+ "epoch=84, loss=0.26628285003398494, train_accuracy=0.3737962962962963\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.96it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.09it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=85, loss=0.263255347272479\n"
+ "epoch=85, loss=0.2660525062566954, train_accuracy=0.3741111111111111\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 45.05it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 46.65it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=86, loss=0.26311201049702554\n"
+ "epoch=86, loss=0.26582677573838703, train_accuracy=0.37437037037037035\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.61it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.45it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=87, loss=0.26296684935829534\n"
+ "epoch=87, loss=0.26560560616964574, train_accuracy=0.37451851851851853\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.74it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 42.67it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=88, loss=0.2628196232828335\n"
+ "epoch=88, loss=0.26538888032876734, train_accuracy=0.37483333333333335\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.33it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 42.00it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=89, loss=0.26267011491754183\n"
+ "epoch=89, loss=0.2651764220974758, train_accuracy=0.37537037037037035\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.72it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 43.30it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=90, loss=0.26251814954775665\n"
+ "epoch=90, loss=0.2649680021029322, train_accuracy=0.3758148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.33it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.35it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=91, loss=0.2623636186728697\n"
+ "epoch=91, loss=0.26476334551407715, train_accuracy=0.3764074074074074\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.63it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.17it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=92, loss=0.26220650033019977\n"
+ "epoch=92, loss=0.264562145144911, train_accuracy=0.37687037037037036\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 43.80it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.28it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=93, loss=0.26204687100089963\n"
+ "epoch=93, loss=0.2643640809247775, train_accuracy=0.37762962962962965\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.25it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.86it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=94, loss=0.26188490805869413\n"
+ "epoch=94, loss=0.26416884304514154, train_accuracy=0.3778148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.99it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.35it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=95, loss=0.26172088492855883\n"
+ "epoch=95, loss=0.26397615328760526, train_accuracy=0.37827777777777777\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.23it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 51.36it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=96, loss=0.26155516191390676\n"
+ "epoch=96, loss=0.2637857791547724, train_accuracy=0.37872222222222224\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.11it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 50.57it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=97, loss=0.2613881745000343\n"
+ "epoch=97, loss=0.2635975381374024, train_accuracy=0.3793888888888889\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 47.19it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 49.07it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=98, loss=0.26122041931305423\n"
+ "epoch=98, loss=0.2634112927800681, train_accuracy=0.3798148148148148\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
- "100%|██████████| 106/106 [00:02<00:00, 46.72it/s]\n"
+ "100%|██████████| 106/106 [00:02<00:00, 45.85it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "epoch=99, loss=0.26105243706027714\n"
+ "epoch=99, loss=0.26322693939818576, train_accuracy=0.3804444444444444\n"
]
}
],
"source": [
"from utils.mlp_training import run_mlp_training\n",
+ "from utils.read_cifar import read_cifar\n",
+ "from utils.split_dataset import split_dataset\n",
"\n",
"split_factor = 0.9\n",
"d_h = 64\n",
@@ -1688,24 +1715,24 @@
"\n",
"data, labels = read_cifar('data/cifar-10-batches-py')\n",
"data_train, labels_train, data_test, labels_test = split_dataset(data, labels, split_factor)\n",
- "losses, test_accuracy = run_mlp_training(data_train, labels_train, data_test, labels_test, d_h, learning_rate, num_epochs, batch_size)"
+ "losses, test_accuracy, train_accuracies = run_mlp_training(data_train, labels_train, data_test, labels_test, d_h, learning_rate, num_epochs, batch_size)"
]
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Test accuracy: 0.3631666666666667\n"
+ "Test accuracy: 0.375\n"
]
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
"<Figure size 1000x500 with 1 Axes>"
]
@@ -1716,20 +1743,54 @@
],
"source": [
"from utils.process_image import save_plot_as_image\n",
+ "import numpy as np\n",
+ "\n",
"print('Test accuracy:', test_accuracy)\n",
- "save_plot_as_image(np.arange(1, len(losses)+1), losses, 'Loss', 'Epoch', 'images/mlp_loss.png')"
+ "save_plot_as_image(np.arange(1, len(losses)+1), losses, 'Loss', 'Epoch', 'Evolution de la loss', 'images/mlp_loss.png')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1000x500 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "save_plot_as_image(np.arange(1, len(train_accuracies)+1), train_accuracies, 'Accuracy', 'Epoch', 'Evolution de l\\'accuracy','images/mlp_accuracy.png')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "#### Bonus: comparaison / vérification avec le même modèle en utilisant la librairie Tensorflow"
+ "### Analyse des performances du modèle\n",
+ "On termine l'entrainement avec une accuracy de 37.5% sur le jeu de test.\n",
+ "\n",
+ "Comme j'ai rajouté un paramètre `batch_size`, les poids du modèle sont mis à jour à chaque `batch_size` images (pour un `batch_size` de 512, cela correspond à 106 batch par epoch), ce qui explique certainement la différence d'accuracy après 100 epochs pour un modèle sans batch_size (ce qui correspond à un seul batch contenant la totalité des images d'entraînement).\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Bonus: comparaison / vérification avec la librairie Tensorflow\n",
+ "On implémente le même modèle avec la même architecture avec la librairie Tensorflow, ainsi qu'avec la même fonction de loss et le même optimiseur.\n",
+ "Cela permet de vérifier que le modèle implémenté manuellement donne des résultats cohérents."
]
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 8,
"metadata": {},
"outputs": [
{
@@ -1737,212 +1798,222 @@
"output_type": "stream",
"text": [
"Epoch 1/100\n",
- "95/95 [==============================] - 3s 12ms/step - loss: 0.3572 - accuracy: 0.1308 - val_loss: 0.3235 - val_accuracy: 0.1633\n",
+ "95/95 [==============================] - 2s 12ms/step - loss: 0.3570 - accuracy: 0.1407 - val_loss: 0.3220 - val_accuracy: 0.1719\n",
"Epoch 2/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3224 - accuracy: 0.1646 - val_loss: 0.3208 - val_accuracy: 0.1948\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3199 - accuracy: 0.1990 - val_loss: 0.3183 - val_accuracy: 0.2235\n",
"Epoch 3/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3197 - accuracy: 0.2022 - val_loss: 0.3179 - val_accuracy: 0.2209\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3166 - accuracy: 0.2252 - val_loss: 0.3154 - val_accuracy: 0.2409\n",
"Epoch 4/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3167 - accuracy: 0.2277 - val_loss: 0.3149 - val_accuracy: 0.2459\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3138 - accuracy: 0.2470 - val_loss: 0.3126 - val_accuracy: 0.2420\n",
"Epoch 5/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3138 - accuracy: 0.2442 - val_loss: 0.3121 - val_accuracy: 0.2604\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3111 - accuracy: 0.2543 - val_loss: 0.3102 - val_accuracy: 0.2533\n",
"Epoch 6/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3111 - accuracy: 0.2553 - val_loss: 0.3096 - val_accuracy: 0.2687\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3087 - accuracy: 0.2646 - val_loss: 0.3079 - val_accuracy: 0.2598\n",
"Epoch 7/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3088 - accuracy: 0.2634 - val_loss: 0.3073 - val_accuracy: 0.2761\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3065 - accuracy: 0.2730 - val_loss: 0.3060 - val_accuracy: 0.2757\n",
"Epoch 8/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3066 - accuracy: 0.2700 - val_loss: 0.3053 - val_accuracy: 0.2830\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3046 - accuracy: 0.2811 - val_loss: 0.3041 - val_accuracy: 0.2870\n",
"Epoch 9/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.3047 - accuracy: 0.2767 - val_loss: 0.3034 - val_accuracy: 0.2874\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.3028 - accuracy: 0.2894 - val_loss: 0.3024 - val_accuracy: 0.2850\n",
"Epoch 10/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.3028 - accuracy: 0.2827 - val_loss: 0.3015 - val_accuracy: 0.2946\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.3011 - accuracy: 0.2912 - val_loss: 0.3009 - val_accuracy: 0.2885\n",
"Epoch 11/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.3011 - accuracy: 0.2890 - val_loss: 0.2998 - val_accuracy: 0.3002\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2997 - accuracy: 0.2963 - val_loss: 0.2995 - val_accuracy: 0.2959\n",
"Epoch 12/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2994 - accuracy: 0.2943 - val_loss: 0.2982 - val_accuracy: 0.3063\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2983 - accuracy: 0.3004 - val_loss: 0.2982 - val_accuracy: 0.3026\n",
"Epoch 13/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2979 - accuracy: 0.3009 - val_loss: 0.2967 - val_accuracy: 0.3107\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2970 - accuracy: 0.3058 - val_loss: 0.2970 - val_accuracy: 0.3022\n",
"Epoch 14/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2965 - accuracy: 0.3026 - val_loss: 0.2954 - val_accuracy: 0.3191\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2957 - accuracy: 0.3105 - val_loss: 0.2958 - val_accuracy: 0.2994\n",
"Epoch 15/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2953 - accuracy: 0.3087 - val_loss: 0.2941 - val_accuracy: 0.3176\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2946 - accuracy: 0.3104 - val_loss: 0.2947 - val_accuracy: 0.3102\n",
"Epoch 16/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2941 - accuracy: 0.3121 - val_loss: 0.2929 - val_accuracy: 0.3213\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2935 - accuracy: 0.3137 - val_loss: 0.2937 - val_accuracy: 0.3163\n",
"Epoch 17/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2931 - accuracy: 0.3150 - val_loss: 0.2919 - val_accuracy: 0.3263\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2925 - accuracy: 0.3191 - val_loss: 0.2928 - val_accuracy: 0.3130\n",
"Epoch 18/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2920 - accuracy: 0.3173 - val_loss: 0.2910 - val_accuracy: 0.3283\n",
+ "95/95 [==============================] - 1s 11ms/step - loss: 0.2915 - accuracy: 0.3200 - val_loss: 0.2918 - val_accuracy: 0.3124\n",
"Epoch 19/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2911 - accuracy: 0.3198 - val_loss: 0.2900 - val_accuracy: 0.3278\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2906 - accuracy: 0.3205 - val_loss: 0.2910 - val_accuracy: 0.3176\n",
"Epoch 20/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2902 - accuracy: 0.3223 - val_loss: 0.2891 - val_accuracy: 0.3306\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2898 - accuracy: 0.3243 - val_loss: 0.2902 - val_accuracy: 0.3150\n",
"Epoch 21/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2894 - accuracy: 0.3255 - val_loss: 0.2882 - val_accuracy: 0.3367\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2890 - accuracy: 0.3259 - val_loss: 0.2895 - val_accuracy: 0.3189\n",
"Epoch 22/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2886 - accuracy: 0.3272 - val_loss: 0.2875 - val_accuracy: 0.3359\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2882 - accuracy: 0.3262 - val_loss: 0.2888 - val_accuracy: 0.3211\n",
"Epoch 23/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2879 - accuracy: 0.3292 - val_loss: 0.2866 - val_accuracy: 0.3404\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2875 - accuracy: 0.3291 - val_loss: 0.2881 - val_accuracy: 0.3231\n",
"Epoch 24/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2872 - accuracy: 0.3316 - val_loss: 0.2859 - val_accuracy: 0.3387\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2868 - accuracy: 0.3295 - val_loss: 0.2874 - val_accuracy: 0.3228\n",
"Epoch 25/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2865 - accuracy: 0.3333 - val_loss: 0.2853 - val_accuracy: 0.3426\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2861 - accuracy: 0.3310 - val_loss: 0.2868 - val_accuracy: 0.3270\n",
"Epoch 26/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2859 - accuracy: 0.3348 - val_loss: 0.2846 - val_accuracy: 0.3420\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2855 - accuracy: 0.3331 - val_loss: 0.2863 - val_accuracy: 0.3270\n",
"Epoch 27/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2853 - accuracy: 0.3363 - val_loss: 0.2840 - val_accuracy: 0.3478\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2849 - accuracy: 0.3351 - val_loss: 0.2857 - val_accuracy: 0.3274\n",
"Epoch 28/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2847 - accuracy: 0.3382 - val_loss: 0.2834 - val_accuracy: 0.3448\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2843 - accuracy: 0.3362 - val_loss: 0.2852 - val_accuracy: 0.3324\n",
"Epoch 29/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2842 - accuracy: 0.3391 - val_loss: 0.2829 - val_accuracy: 0.3491\n",
+ "95/95 [==============================] - 1s 11ms/step - loss: 0.2838 - accuracy: 0.3394 - val_loss: 0.2848 - val_accuracy: 0.3291\n",
"Epoch 30/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2837 - accuracy: 0.3415 - val_loss: 0.2824 - val_accuracy: 0.3465\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2833 - accuracy: 0.3379 - val_loss: 0.2843 - val_accuracy: 0.3331\n",
"Epoch 31/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2832 - accuracy: 0.3424 - val_loss: 0.2818 - val_accuracy: 0.3494\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2828 - accuracy: 0.3404 - val_loss: 0.2838 - val_accuracy: 0.3298\n",
"Epoch 32/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2827 - accuracy: 0.3446 - val_loss: 0.2813 - val_accuracy: 0.3489\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2823 - accuracy: 0.3414 - val_loss: 0.2834 - val_accuracy: 0.3330\n",
"Epoch 33/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2822 - accuracy: 0.3452 - val_loss: 0.2808 - val_accuracy: 0.3535\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2819 - accuracy: 0.3431 - val_loss: 0.2830 - val_accuracy: 0.3328\n",
"Epoch 34/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2818 - accuracy: 0.3465 - val_loss: 0.2804 - val_accuracy: 0.3524\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2814 - accuracy: 0.3435 - val_loss: 0.2826 - val_accuracy: 0.3339\n",
"Epoch 35/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2813 - accuracy: 0.3472 - val_loss: 0.2799 - val_accuracy: 0.3519\n",
+ "95/95 [==============================] - 1s 11ms/step - loss: 0.2810 - accuracy: 0.3444 - val_loss: 0.2822 - val_accuracy: 0.3354\n",
"Epoch 36/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2809 - accuracy: 0.3489 - val_loss: 0.2795 - val_accuracy: 0.3533\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2806 - accuracy: 0.3460 - val_loss: 0.2818 - val_accuracy: 0.3337\n",
"Epoch 37/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2805 - accuracy: 0.3501 - val_loss: 0.2791 - val_accuracy: 0.3530\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2802 - accuracy: 0.3470 - val_loss: 0.2815 - val_accuracy: 0.3346\n",
"Epoch 38/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2801 - accuracy: 0.3502 - val_loss: 0.2787 - val_accuracy: 0.3531\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2798 - accuracy: 0.3476 - val_loss: 0.2811 - val_accuracy: 0.3378\n",
"Epoch 39/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2797 - accuracy: 0.3513 - val_loss: 0.2784 - val_accuracy: 0.3569\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2794 - accuracy: 0.3490 - val_loss: 0.2808 - val_accuracy: 0.3365\n",
"Epoch 40/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2793 - accuracy: 0.3533 - val_loss: 0.2779 - val_accuracy: 0.3593\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2791 - accuracy: 0.3498 - val_loss: 0.2805 - val_accuracy: 0.3411\n",
"Epoch 41/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2790 - accuracy: 0.3531 - val_loss: 0.2776 - val_accuracy: 0.3578\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2787 - accuracy: 0.3502 - val_loss: 0.2802 - val_accuracy: 0.3383\n",
"Epoch 42/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2786 - accuracy: 0.3549 - val_loss: 0.2772 - val_accuracy: 0.3548\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2784 - accuracy: 0.3507 - val_loss: 0.2799 - val_accuracy: 0.3385\n",
"Epoch 43/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2783 - accuracy: 0.3555 - val_loss: 0.2768 - val_accuracy: 0.3580\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2781 - accuracy: 0.3526 - val_loss: 0.2796 - val_accuracy: 0.3396\n",
"Epoch 44/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2779 - accuracy: 0.3565 - val_loss: 0.2765 - val_accuracy: 0.3576\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2777 - accuracy: 0.3541 - val_loss: 0.2793 - val_accuracy: 0.3407\n",
"Epoch 45/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2776 - accuracy: 0.3575 - val_loss: 0.2762 - val_accuracy: 0.3593\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2774 - accuracy: 0.3537 - val_loss: 0.2790 - val_accuracy: 0.3441\n",
"Epoch 46/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2773 - accuracy: 0.3589 - val_loss: 0.2758 - val_accuracy: 0.3574\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2771 - accuracy: 0.3552 - val_loss: 0.2787 - val_accuracy: 0.3441\n",
"Epoch 47/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2770 - accuracy: 0.3592 - val_loss: 0.2756 - val_accuracy: 0.3598\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2768 - accuracy: 0.3554 - val_loss: 0.2785 - val_accuracy: 0.3469\n",
"Epoch 48/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2767 - accuracy: 0.3606 - val_loss: 0.2752 - val_accuracy: 0.3622\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2765 - accuracy: 0.3571 - val_loss: 0.2782 - val_accuracy: 0.3470\n",
"Epoch 49/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2764 - accuracy: 0.3623 - val_loss: 0.2750 - val_accuracy: 0.3578\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2762 - accuracy: 0.3571 - val_loss: 0.2780 - val_accuracy: 0.3450\n",
"Epoch 50/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2761 - accuracy: 0.3621 - val_loss: 0.2747 - val_accuracy: 0.3615\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2760 - accuracy: 0.3584 - val_loss: 0.2777 - val_accuracy: 0.3467\n",
"Epoch 51/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2758 - accuracy: 0.3628 - val_loss: 0.2744 - val_accuracy: 0.3620\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2757 - accuracy: 0.3592 - val_loss: 0.2774 - val_accuracy: 0.3457\n",
"Epoch 52/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2755 - accuracy: 0.3637 - val_loss: 0.2741 - val_accuracy: 0.3609\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2754 - accuracy: 0.3591 - val_loss: 0.2772 - val_accuracy: 0.3461\n",
"Epoch 53/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2752 - accuracy: 0.3647 - val_loss: 0.2739 - val_accuracy: 0.3619\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2751 - accuracy: 0.3605 - val_loss: 0.2769 - val_accuracy: 0.3491\n",
"Epoch 54/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2749 - accuracy: 0.3649 - val_loss: 0.2736 - val_accuracy: 0.3641\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2749 - accuracy: 0.3617 - val_loss: 0.2767 - val_accuracy: 0.3476\n",
"Epoch 55/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2747 - accuracy: 0.3650 - val_loss: 0.2733 - val_accuracy: 0.3652\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2746 - accuracy: 0.3624 - val_loss: 0.2765 - val_accuracy: 0.3480\n",
"Epoch 56/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2744 - accuracy: 0.3666 - val_loss: 0.2731 - val_accuracy: 0.3619\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2743 - accuracy: 0.3628 - val_loss: 0.2762 - val_accuracy: 0.3513\n",
"Epoch 57/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2742 - accuracy: 0.3658 - val_loss: 0.2728 - val_accuracy: 0.3670\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2741 - accuracy: 0.3638 - val_loss: 0.2760 - val_accuracy: 0.3513\n",
"Epoch 58/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2739 - accuracy: 0.3672 - val_loss: 0.2726 - val_accuracy: 0.3665\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2738 - accuracy: 0.3647 - val_loss: 0.2757 - val_accuracy: 0.3519\n",
"Epoch 59/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2736 - accuracy: 0.3671 - val_loss: 0.2724 - val_accuracy: 0.3656\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2736 - accuracy: 0.3659 - val_loss: 0.2755 - val_accuracy: 0.3509\n",
"Epoch 60/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2734 - accuracy: 0.3682 - val_loss: 0.2721 - val_accuracy: 0.3674\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2733 - accuracy: 0.3663 - val_loss: 0.2753 - val_accuracy: 0.3543\n",
"Epoch 61/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2732 - accuracy: 0.3694 - val_loss: 0.2719 - val_accuracy: 0.3665\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2731 - accuracy: 0.3674 - val_loss: 0.2751 - val_accuracy: 0.3531\n",
"Epoch 62/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2729 - accuracy: 0.3701 - val_loss: 0.2716 - val_accuracy: 0.3681\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2729 - accuracy: 0.3664 - val_loss: 0.2749 - val_accuracy: 0.3539\n",
"Epoch 63/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2727 - accuracy: 0.3694 - val_loss: 0.2715 - val_accuracy: 0.3656\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2727 - accuracy: 0.3682 - val_loss: 0.2746 - val_accuracy: 0.3556\n",
"Epoch 64/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2724 - accuracy: 0.3711 - val_loss: 0.2712 - val_accuracy: 0.3700\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2724 - accuracy: 0.3691 - val_loss: 0.2745 - val_accuracy: 0.3537\n",
"Epoch 65/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2722 - accuracy: 0.3710 - val_loss: 0.2710 - val_accuracy: 0.3717\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2722 - accuracy: 0.3686 - val_loss: 0.2742 - val_accuracy: 0.3541\n",
"Epoch 66/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2720 - accuracy: 0.3714 - val_loss: 0.2708 - val_accuracy: 0.3711\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2720 - accuracy: 0.3702 - val_loss: 0.2740 - val_accuracy: 0.3559\n",
"Epoch 67/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2718 - accuracy: 0.3712 - val_loss: 0.2706 - val_accuracy: 0.3706\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2717 - accuracy: 0.3703 - val_loss: 0.2739 - val_accuracy: 0.3543\n",
"Epoch 68/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2716 - accuracy: 0.3729 - val_loss: 0.2704 - val_accuracy: 0.3687\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2715 - accuracy: 0.3711 - val_loss: 0.2737 - val_accuracy: 0.3557\n",
"Epoch 69/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2714 - accuracy: 0.3725 - val_loss: 0.2703 - val_accuracy: 0.3715\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2713 - accuracy: 0.3717 - val_loss: 0.2735 - val_accuracy: 0.3550\n",
"Epoch 70/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2711 - accuracy: 0.3731 - val_loss: 0.2699 - val_accuracy: 0.3739\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2711 - accuracy: 0.3726 - val_loss: 0.2733 - val_accuracy: 0.3570\n",
"Epoch 71/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2709 - accuracy: 0.3743 - val_loss: 0.2699 - val_accuracy: 0.3719\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2709 - accuracy: 0.3730 - val_loss: 0.2731 - val_accuracy: 0.3587\n",
"Epoch 72/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2707 - accuracy: 0.3743 - val_loss: 0.2696 - val_accuracy: 0.3722\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2707 - accuracy: 0.3724 - val_loss: 0.2729 - val_accuracy: 0.3606\n",
"Epoch 73/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2705 - accuracy: 0.3745 - val_loss: 0.2694 - val_accuracy: 0.3733\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2705 - accuracy: 0.3748 - val_loss: 0.2727 - val_accuracy: 0.3589\n",
"Epoch 74/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2703 - accuracy: 0.3750 - val_loss: 0.2693 - val_accuracy: 0.3739\n",
+ "95/95 [==============================] - 1s 10ms/step - loss: 0.2703 - accuracy: 0.3748 - val_loss: 0.2725 - val_accuracy: 0.3596\n",
"Epoch 75/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2701 - accuracy: 0.3766 - val_loss: 0.2690 - val_accuracy: 0.3739\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2701 - accuracy: 0.3751 - val_loss: 0.2723 - val_accuracy: 0.3613\n",
"Epoch 76/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2699 - accuracy: 0.3772 - val_loss: 0.2689 - val_accuracy: 0.3731\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2699 - accuracy: 0.3755 - val_loss: 0.2722 - val_accuracy: 0.3615\n",
"Epoch 77/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2697 - accuracy: 0.3774 - val_loss: 0.2688 - val_accuracy: 0.3743\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2697 - accuracy: 0.3759 - val_loss: 0.2721 - val_accuracy: 0.3607\n",
"Epoch 78/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2695 - accuracy: 0.3771 - val_loss: 0.2686 - val_accuracy: 0.3743\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2695 - accuracy: 0.3775 - val_loss: 0.2718 - val_accuracy: 0.3630\n",
"Epoch 79/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2693 - accuracy: 0.3772 - val_loss: 0.2684 - val_accuracy: 0.3761\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2693 - accuracy: 0.3765 - val_loss: 0.2717 - val_accuracy: 0.3617\n",
"Epoch 80/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2692 - accuracy: 0.3785 - val_loss: 0.2682 - val_accuracy: 0.3752\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2691 - accuracy: 0.3779 - val_loss: 0.2716 - val_accuracy: 0.3643\n",
"Epoch 81/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2690 - accuracy: 0.3792 - val_loss: 0.2681 - val_accuracy: 0.3748\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2690 - accuracy: 0.3777 - val_loss: 0.2714 - val_accuracy: 0.3654\n",
"Epoch 82/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2688 - accuracy: 0.3798 - val_loss: 0.2678 - val_accuracy: 0.3783\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2688 - accuracy: 0.3791 - val_loss: 0.2712 - val_accuracy: 0.3667\n",
"Epoch 83/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2686 - accuracy: 0.3804 - val_loss: 0.2677 - val_accuracy: 0.3774\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2686 - accuracy: 0.3793 - val_loss: 0.2710 - val_accuracy: 0.3672\n",
"Epoch 84/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2684 - accuracy: 0.3801 - val_loss: 0.2675 - val_accuracy: 0.3776\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2684 - accuracy: 0.3796 - val_loss: 0.2709 - val_accuracy: 0.3641\n",
"Epoch 85/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2683 - accuracy: 0.3810 - val_loss: 0.2674 - val_accuracy: 0.3783\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2683 - accuracy: 0.3808 - val_loss: 0.2707 - val_accuracy: 0.3659\n",
"Epoch 86/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2681 - accuracy: 0.3808 - val_loss: 0.2672 - val_accuracy: 0.3772\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2681 - accuracy: 0.3806 - val_loss: 0.2705 - val_accuracy: 0.3676\n",
"Epoch 87/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2679 - accuracy: 0.3821 - val_loss: 0.2671 - val_accuracy: 0.3774\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2679 - accuracy: 0.3809 - val_loss: 0.2704 - val_accuracy: 0.3681\n",
"Epoch 88/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2678 - accuracy: 0.3817 - val_loss: 0.2670 - val_accuracy: 0.3798\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2678 - accuracy: 0.3811 - val_loss: 0.2702 - val_accuracy: 0.3691\n",
"Epoch 89/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2676 - accuracy: 0.3830 - val_loss: 0.2668 - val_accuracy: 0.3789\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2676 - accuracy: 0.3824 - val_loss: 0.2701 - val_accuracy: 0.3700\n",
"Epoch 90/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2674 - accuracy: 0.3829 - val_loss: 0.2666 - val_accuracy: 0.3819\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2674 - accuracy: 0.3833 - val_loss: 0.2700 - val_accuracy: 0.3700\n",
"Epoch 91/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2673 - accuracy: 0.3840 - val_loss: 0.2665 - val_accuracy: 0.3822\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2673 - accuracy: 0.3828 - val_loss: 0.2698 - val_accuracy: 0.3674\n",
"Epoch 92/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2671 - accuracy: 0.3848 - val_loss: 0.2664 - val_accuracy: 0.3813\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2671 - accuracy: 0.3844 - val_loss: 0.2697 - val_accuracy: 0.3691\n",
"Epoch 93/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2669 - accuracy: 0.3848 - val_loss: 0.2662 - val_accuracy: 0.3789\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2669 - accuracy: 0.3835 - val_loss: 0.2695 - val_accuracy: 0.3706\n",
"Epoch 94/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2668 - accuracy: 0.3856 - val_loss: 0.2660 - val_accuracy: 0.3824\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2668 - accuracy: 0.3844 - val_loss: 0.2694 - val_accuracy: 0.3720\n",
"Epoch 95/100\n",
- "95/95 [==============================] - 1s 8ms/step - loss: 0.2666 - accuracy: 0.3864 - val_loss: 0.2659 - val_accuracy: 0.3841\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2666 - accuracy: 0.3850 - val_loss: 0.2692 - val_accuracy: 0.3689\n",
"Epoch 96/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2665 - accuracy: 0.3864 - val_loss: 0.2658 - val_accuracy: 0.3839\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2665 - accuracy: 0.3851 - val_loss: 0.2691 - val_accuracy: 0.3719\n",
"Epoch 97/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2663 - accuracy: 0.3868 - val_loss: 0.2656 - val_accuracy: 0.3819\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2663 - accuracy: 0.3854 - val_loss: 0.2689 - val_accuracy: 0.3750\n",
"Epoch 98/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2662 - accuracy: 0.3868 - val_loss: 0.2655 - val_accuracy: 0.3819\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2662 - accuracy: 0.3863 - val_loss: 0.2688 - val_accuracy: 0.3717\n",
"Epoch 99/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2660 - accuracy: 0.3884 - val_loss: 0.2654 - val_accuracy: 0.3815\n",
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2660 - accuracy: 0.3858 - val_loss: 0.2687 - val_accuracy: 0.3743\n",
"Epoch 100/100\n",
- "95/95 [==============================] - 1s 9ms/step - loss: 0.2658 - accuracy: 0.3877 - val_loss: 0.2652 - val_accuracy: 0.3830\n",
- "188/188 [==============================] - 1s 3ms/step - loss: 0.2656 - accuracy: 0.4020\n",
- "test_accuracy=0.4020000100135803\n"
+ "95/95 [==============================] - 1s 9ms/step - loss: 0.2659 - accuracy: 0.3867 - val_loss: 0.2686 - val_accuracy: 0.3761\n",
+ "188/188 [==============================] - 1s 3ms/step - loss: 0.2653 - accuracy: 0.3880\n",
+ "test_accuracy=0.3880000114440918\n"
]
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
+ "text/plain": [
+ "<Figure size 1000x500 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "image/png": "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",
"text/plain": [
"<Figure size 1000x500 with 1 Axes>"
]
@@ -1955,6 +2026,7 @@
"import tensorflow as tf\n",
"from utils.read_cifar import read_cifar\n",
"from utils.split_dataset import split_dataset\n",
+ "from utils.process_image import save_plot_as_image\n",
"\n",
"split_factor = 0.9\n",
"d_h = 64\n",
@@ -1964,28 +2036,49 @@
"\n",
"data, labels = read_cifar('data/cifar-10-batches-py')\n",
"data_train, labels_train, data_test, labels_test = split_dataset(data, labels, split_factor)\n",
+ "# conversion des labels en one-hot\n",
"labels_train = tf.keras.utils.to_categorical(labels_train)\n",
"labels_test = tf.keras.utils.to_categorical(labels_test)\n",
"\n",
"model = tf.keras.models.Sequential([\n",
" tf.keras.layers.Dense(d_h, activation='sigmoid'),\n",
- " tf.keras.layers.Dense(10, activation='sigmoid')\n",
+ " tf.keras.layers.Dense(10, activation='softmax')\n",
"])\n",
"model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=learning_rate),\n",
" loss=tf.keras.losses.BinaryCrossentropy(),\n",
" metrics=['accuracy'])\n",
+ "\n",
"history = model.fit(data_train, labels_train, epochs=num_epochs, batch_size=batch_size, validation_split=0.1)\n",
+ "\n",
"test_loss, test_accuracy = model.evaluate(data_test, labels_test)\n",
"\n",
"print(f'test_accuracy={test_accuracy}')\n",
"loss = history.history['loss']\n",
+ "accuracy = history.history['accuracy']\n",
"epochs = np.arange(1, len(loss)+1)\n",
- "save_plot_as_image(epochs, loss, 'Loss', 'Epoch', 'images/mlp_loss_tf.png')\n"
+ "save_plot_as_image(epochs, loss, 'Loss', 'Epoch', 'Evolution de la Loss (Tensorflow)','images/mlp_loss_tf.png')\n",
+ "save_plot_as_image(epochs, accuracy, 'Accuracy', 'Epoch', 'Evolution de l\\'accuracy (Tensorflow)','images/mlp_accuracy_tf.png')\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Analyse des résultats\n",
+ "On obtient à peu près les mêmes résultats avec Tensorflow qu'avec notre modèle implémenté manuellement, ce qui est plutôt rassurant."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Matrix of confusion\n",
+ "We plot the matrix of confusion for the model with d_h = 64, a learning rate of 0.1 and 100 epochs to assess the performance of the model."
]
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -1993,7 +2086,7 @@
"output_type": "stream",
"text": [
"(6000, 10)\n",
- "[7 9 4 ... 3 9 0]\n",
+ "[1 2 8 ... 8 9 6]\n",
"188/188 [==============================] - 0s 2ms/step\n"
]
},
@@ -2003,13 +2096,13 @@
"<AxesSubplot: >"
]
},
- "execution_count": 14,
+ "execution_count": 9,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
"<Figure size 640x480 with 2 Axes>"
]
diff --git a/images/mlp_accuracy.png b/images/mlp_accuracy.png
new file mode 100644
index 0000000000000000000000000000000000000000..89141b58146482adeed9491ec7118e76106365c0
Binary files /dev/null and b/images/mlp_accuracy.png differ
diff --git a/images/mlp_accuracy_tf.png b/images/mlp_accuracy_tf.png
new file mode 100644
index 0000000000000000000000000000000000000000..0ec9606b2f14119fd7c2148f7b3e3083c76d3133
Binary files /dev/null and b/images/mlp_accuracy_tf.png differ
diff --git a/images/mlp_loss.png b/images/mlp_loss.png
index 1a9f7dcd4d8b63c61c21e45d46d4d9cc82c4d835..ce7e5b93c797eadf82485143bef53cdb32fbfd24 100644
Binary files a/images/mlp_loss.png and b/images/mlp_loss.png differ
diff --git a/images/mlp_loss_tf.png b/images/mlp_loss_tf.png
index 5a0165fd98fd248e70c795ffac2edfb979b19830..3a81c0356400fc60a67332cd8031fad421009d28 100644
Binary files a/images/mlp_loss_tf.png and b/images/mlp_loss_tf.png differ
diff --git a/utils/forward_pass.py b/utils/forward_pass.py
index b5dad28034570f4604adb00875e96f0789720eef..b3661757fbcfccc6fb25c5e8ea787df99279abbd 100644
--- a/utils/forward_pass.py
+++ b/utils/forward_pass.py
@@ -1,10 +1,11 @@
from utils.sigmoid import sigmoid
import numpy as np
+from scipy.special import softmax
def forward_pass(w1, b1, w2, b2, data):
- # compute the forward pass of the MLP with sigmoid activations
+ # compute the forward pass of the MLP with sigmoid activations for the hidden layer and softmax for the output layer
z1 = np.matmul(data, w1) + b1
a1 = sigmoid(z1)
z2 = np.matmul(a1, w2) + b2
- a2 = sigmoid(z2)
+ a2 = softmax(z2, axis=1)
return a1, a2
\ No newline at end of file
diff --git a/utils/mlp_training.py b/utils/mlp_training.py
index 8d3da4a6a6424ed9264b2a717143c107118263e8..299cbb6ca41a4a8e89d37310a71dca1ee4611983 100644
--- a/utils/mlp_training.py
+++ b/utils/mlp_training.py
@@ -6,16 +6,19 @@ from utils.learn_once_cross_entropy import learn_once_cross_entropy
def train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes):
- # train the MLP for num_epochs epochs, using batches of size batch_size
+ # train the MLP for num_epochs epochs, using batches of size batch_size and return the train accuracies, losses and weights
losses = []
+ train_accuracies = []
for epoch in range(num_epochs):
for i in tqdm.tqdm(range(0, data_train.shape[0], batch_size)):
data = data_train[i:i+batch_size]
targets = one_hot(labels_train[i:i+batch_size], n_classes)
w1, b1, w2, b2, loss = learn_once_cross_entropy(w1, b1, w2, b2, data, targets, learning_rate)
losses.append(loss)
- print(f'epoch={epoch}, loss={loss}')
- return losses, w1, b1, w2, b2
+ train_accuracy = test_mlp(w1, b1, w2, b2, data_train, labels_train)
+ train_accuracies.append(train_accuracy)
+ print(f'epoch={epoch}, loss={loss}, train_accuracy={train_accuracy}')
+ return train_accuracies, losses, w1, b1, w2, b2
def test_mlp(w1, b1, w2, b2, data_test, labels_test):
# test the MLP on data_test, and return the accuracy
@@ -37,6 +40,6 @@ def run_mlp_training(data_train, labels_train, data_test, labels_test, d_h, lear
d_in = data_train.shape[1]
d_out = np.max(labels_train) + 1
w1, b1, w2, b2 = initialize_mlp(d_in, d_h, d_out)
- losses, w1, b1, w2, b2 = train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes)
+ train_accuracies, losses, w1, b1, w2, b2 = train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes)
test_accuracy = test_mlp(w1, b1, w2, b2, data_test, labels_test)
- return losses, test_accuracy
\ No newline at end of file
+ return losses, test_accuracy, train_accuracies
\ No newline at end of file
diff --git a/utils/process_image.py b/utils/process_image.py
index c5537334222589f53aa51c9ae702be8c1751de3d..f7877d60f8d6a60dbeb15d53ffaf94a449599559 100644
--- a/utils/process_image.py
+++ b/utils/process_image.py
@@ -5,10 +5,11 @@ def plot_image_with_label(img, label):
plt.title(label)
plt.show()
-def save_plot_as_image(X, Y, y_label, x_label, save_path):
+def save_plot_as_image(X, Y, y_label, x_label, title, save_path):
# plot and save image as png
plt.figure(figsize=(10,5))
plt.plot(X, Y)
+ plt.title(title)
plt.ylabel(y_label)
plt.xlabel(x_label)
plt.savefig(save_path)