{"cells":[{"metadata":{"trusted":true,"_uuid":"fc024aec0f6f381c521bba8ee4c170587e60ff4b"},"cell_type":"code","source":"#import includes\nimport tensorflow as tf\nfrom tensorflow import keras\nimport numpy as np\nimport matplotlib.pyplot as plt \nimport pandas as pd\n\nfrom sklearn.model_selection import train_test_split","execution_count":1,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0b7b047a68f8f32d0579122740f296e45d9ba6b1"},"cell_type":"code","source":"#read input data\ntrain = pd.read_csv(\"../input/train.csv\")\ntest = pd.read_csv(\"../input/test.csv\") ","execution_count":2,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b43ee192b603b4163c5d35905961b927d86ea352"},"cell_type":"code","source":"y_train = train[\"label\"]\nx_train = train.drop(labels = [\"label\"], axis = 1)\nx_eval = x_train[:4200]","execution_count":3,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a2acb9f5c604de2673fe2e3efb6e7a44e9e3c50b"},"cell_type":"code","source":"x_eval.describe()","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":" pixel0 pixel1 pixel2 ... pixel781 pixel782 pixel783\ncount 4200.0 4200.0 4200.0 ... 4200.0 4200.0 4200.0\nmean 0.0 0.0 0.0 ... 0.0 0.0 0.0\nstd 0.0 0.0 0.0 ... 0.0 0.0 0.0\nmin 0.0 0.0 0.0 ... 0.0 0.0 0.0\n25% 0.0 0.0 0.0 ... 0.0 0.0 0.0\n50% 0.0 0.0 0.0 ... 0.0 0.0 0.0\n75% 0.0 0.0 0.0 ... 0.0 0.0 0.0\nmax 0.0 0.0 0.0 ... 0.0 0.0 0.0\n\n[8 rows x 784 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
pixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8pixel9pixel10pixel11pixel12pixel13pixel14pixel15pixel16pixel17pixel18pixel19pixel20pixel21pixel22pixel23pixel24pixel25pixel26pixel27pixel28pixel29pixel30pixel31pixel32pixel33pixel34pixel35pixel36pixel37pixel38pixel39...pixel744pixel745pixel746pixel747pixel748pixel749pixel750pixel751pixel752pixel753pixel754pixel755pixel756pixel757pixel758pixel759pixel760pixel761pixel762pixel763pixel764pixel765pixel766pixel767pixel768pixel769pixel770pixel771pixel772pixel773pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
count4200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.04200.0000004200.0000004200.000000...4200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.04200.04200.04200.04200.04200.04200.04200.04200.04200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.0000004200.04200.04200.04200.04200.04200.04200.0
mean0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0733330.1364290.134762...3.3438102.5411901.8135711.3447620.6495240.2259520.1692860.0333330.00.00.00.00.00.00.00.00.00.0192860.0966670.1207140.0516670.0430950.2676190.4992860.7335710.6609520.7385710.4738100.2273810.1390480.1950000.1533330.0095240.00.00.00.00.00.00.0
std0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.02.8000535.2076405.430321...24.80333521.76510218.80318216.37719811.1086576.3355146.0157502.1144520.00.00.00.00.00.00.00.00.01.2498574.1384344.9483592.0027241.9613566.7170069.66423712.06196710.34217211.5788919.5267285.6761004.8902896.1763275.5394240.4363840.00.00.00.00.00.00.0
min0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.0
25%0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.0
50%0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.0
75%0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.0
max0.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0132.000000253.000000255.000000...255.000000254.000000255.000000254.000000254.000000254.000000253.000000137.0000000.00.00.00.00.00.00.00.00.081.000000231.000000253.000000112.000000104.000000253.000000253.000000254.000000253.000000255.000000253.000000197.000000252.000000253.000000252.00000020.0000000.00.00.00.00.00.00.0
\n
"},"metadata":{}}]},{"metadata":{"trusted":true,"_uuid":"22f999eadb824992e2b494485c45b5c82045f9e0","scrolled":false},"cell_type":"code","source":"x_train.describe()","execution_count":5,"outputs":[{"output_type":"execute_result","execution_count":5,"data":{"text/plain":" pixel0 pixel1 pixel2 ... pixel781 pixel782 pixel783\ncount 42000.0 42000.0 42000.0 ... 42000.0 42000.0 42000.0\nmean 0.0 0.0 0.0 ... 0.0 0.0 0.0\nstd 0.0 0.0 0.0 ... 0.0 0.0 0.0\nmin 0.0 0.0 0.0 ... 0.0 0.0 0.0\n25% 0.0 0.0 0.0 ... 0.0 0.0 0.0\n50% 0.0 0.0 0.0 ... 0.0 0.0 0.0\n75% 0.0 0.0 0.0 ... 0.0 0.0 0.0\nmax 0.0 0.0 0.0 ... 0.0 0.0 0.0\n\n[8 rows x 784 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
pixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8pixel9pixel10pixel11pixel12pixel13pixel14pixel15pixel16pixel17pixel18pixel19pixel20pixel21pixel22pixel23pixel24pixel25pixel26pixel27pixel28pixel29pixel30pixel31pixel32pixel33pixel34pixel35pixel36pixel37pixel38pixel39...pixel744pixel745pixel746pixel747pixel748pixel749pixel750pixel751pixel752pixel753pixel754pixel755pixel756pixel757pixel758pixel759pixel760pixel761pixel762pixel763pixel764pixel765pixel766pixel767pixel768pixel769pixel770pixel771pixel772pixel773pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
count42000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.0000042000.00000042000.00000042000.00000042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.000000...42000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.042000.042000.042000.042000.042000.042000.042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.00000042000.0000042000.00000042000.00000042000.00000042000.00000042000.00000042000.0000042000.00000042000.00000042000.042000.042000.042000.0
mean0.00.00.00.00.00.00.00.00.00.00.00.00.003000.0111900.0051430.0002140.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0003810.0013100.0105480.0272620.0509050.0664050.1295710.174119...3.7725242.7489051.7964521.0899050.5631900.2395710.0935240.0248330.0008570.0014050.00.00.00.00.00.00.00.0061430.0358330.0823570.1149050.1787140.3014520.4136430.5136670.5588330.6778570.602810.4892380.3402140.2192860.1170950.0590240.020190.0172380.0028570.00.00.00.0
std0.00.00.00.00.00.00.00.00.00.00.00.00.568121.6269271.0539720.0439160.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0780720.2326341.1316612.3103963.1218473.2591284.9928945.810949...26.95782922.87924818.59510914.43443910.5178236.4693153.9763061.8460160.1395560.2878910.00.00.00.00.00.00.00.9498032.3508593.9342804.5435835.8567727.2197428.92828610.00406910.12959511.25493110.696039.4800667.9502516.3128904.6338193.2744881.759871.8944980.4142640.00.00.00.0
min0.00.00.00.00.00.00.00.00.00.00.00.00.000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.00.00.00.0
25%0.00.00.00.00.00.00.00.00.00.00.00.00.000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.00.00.00.0
50%0.00.00.00.00.00.00.00.00.00.00.00.00.000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.00.00.00.0
75%0.00.00.00.00.00.00.00.00.00.00.00.00.000000.0000000.0000000.0000000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000...0.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00.00.00.00.00.00.00.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.0000000.0000000.0000000.000000.0000000.0000000.00.00.00.0
max0.00.00.00.00.00.00.00.00.00.00.00.0116.00000254.000000216.0000009.0000000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.016.00000047.000000157.000000254.000000255.000000243.000000255.000000255.000000...255.000000255.000000255.000000255.000000255.000000255.000000255.000000253.00000028.00000059.0000000.00.00.00.00.00.00.0177.000000231.000000253.000000254.000000254.000000255.000000255.000000255.000000255.000000255.000000255.00000255.000000255.000000254.000000254.000000253.000000253.00000254.00000062.0000000.00.00.00.0
\n
"},"metadata":{}}]},{"metadata":{"trusted":true,"_uuid":"ec0b4433e28894c5ede087ff14e00f1e1912de79"},"cell_type":"code","source":"y_train.describe()","execution_count":6,"outputs":[{"output_type":"execute_result","execution_count":6,"data":{"text/plain":"count 42000.000000\nmean 4.456643\nstd 2.887730\nmin 0.000000\n25% 2.000000\n50% 4.000000\n75% 7.000000\nmax 9.000000\nName: label, dtype: float64"},"metadata":{}}]},{"metadata":{"trusted":true,"_uuid":"96ff0ae2392469569365fcfebb91c5f6f0429e9a"},"cell_type":"code","source":"#data normalization in range 0..1\nx_train /=255\ntest /=255\n","execution_count":7,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7a0d111ec2b65a47fa60476cf0666738c5a0d8dd"},"cell_type":"code","source":"x_train = x_train.values.reshape(-1,28,28,1)\ntest = test.values.reshape(-1,28,28,1)\n","execution_count":8,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_eval = x_train[:4200]\nx_train = x_train[4200:]\ny_eval = y_train[:4200]\ny_train = y_train[4200:]","execution_count":9,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"940b7771754604a93a0d9dc683aba6fa03561f92"},"cell_type":"code","source":"aug_data = keras.preprocessing.image.ImageDataGenerator(\n featurewise_center=False, # set input mean to 0 over the dataset\n samplewise_center=False, # set each sample mean to 0\n featurewise_std_normalization=False, # divide inputs by std of the dataset\n samplewise_std_normalization=False, # divide each input by its std\n zca_whitening=False, # apply ZCA whitening\n rotation_range=10, # randomly rotate images in the range (degrees, 0 to 180)\n zoom_range = 0.1, # Randomly zoom image \n width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)\n height_shift_range=0.1, # randomly shift images vertically (fraction of total height)\n horizontal_flip=False, # randomly flip images\n vertical_flip=False) # randomly flip images)\nbatches = aug_data.flow(x_train, y_train, batch_size = 86)","execution_count":10,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"47e56745672f37ac8e80ae5d4d870493106d8466"},"cell_type":"code","source":"model = keras.Sequential([\n keras.layers.Conv2D(256, (3,3),padding = 'Same', activation=tf.nn.relu, input_shape=(28,28,1)),\n keras.layers.MaxPool2D(pool_size=(2,2)),\n keras.layers.Dropout(0.25),\n keras.layers.Conv2D(128, (3,3),padding = 'Same', activation=tf.nn.relu),\n keras.layers.MaxPool2D(pool_size=(2,2)),\n keras.layers.Flatten(),\n keras.layers.Dropout(0.25),\n keras.layers.Dense(256, activation=tf.nn.relu),\n keras.layers.Dense(10, activation=tf.nn.softmax) \n]) \n\n","execution_count":11,"outputs":[{"output_type":"stream","text":"WARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/resource_variable_ops.py:435: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\nInstructions for updating:\nColocations handled automatically by placer.\nWARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/layers/core.py:143: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.\nInstructions for updating:\nPlease use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = keras.callbacks.ReduceLROnPlateau(monitor='val_acc', \n patience=3, \n verbose=1, \n factor=0.5)","execution_count":12,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"dd2cfbddcabe802eccefb86f44e30c2f001eba26"},"cell_type":"code","source":"model.compile(optimizer=tf.train.AdamOptimizer(),\n loss='sparse_categorical_crossentropy',\n metrics=['accuracy'])\n\n#model.compile(optimizer=keras.optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0),loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n","execution_count":13,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"04f93938f4dba3aa87e50abf01cd66dcbd57e588","scrolled":false},"cell_type":"code","source":"#model.fit(x_train, y_train, epochs=200, validation_split = 0.1)\n#callbacks=[learning_rate_reduction],\nhistory = model.fit_generator(generator=batches,steps_per_epoch=batches.n, epochs=200)","execution_count":14,"outputs":[{"output_type":"stream","text":"Epoch 1/200\n440/440 [==============================] - 13s 29ms/step - loss: 0.3101 - acc: 0.9001\nEpoch 2/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0973 - acc: 0.9703\nEpoch 3/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0717 - acc: 0.9772\nEpoch 4/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0620 - acc: 0.9796\nEpoch 5/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0536 - acc: 0.9835\nEpoch 6/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0484 - acc: 0.9850\nEpoch 7/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0473 - acc: 0.9860\nEpoch 8/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0429 - acc: 0.9861\nEpoch 9/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0393 - acc: 0.9879\nEpoch 10/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0368 - acc: 0.9881\nEpoch 11/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0364 - acc: 0.9883\nEpoch 12/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0355 - acc: 0.9886\nEpoch 13/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0313 - acc: 0.9898\nEpoch 14/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0333 - acc: 0.9894\nEpoch 15/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0315 - acc: 0.9900\nEpoch 16/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0287 - acc: 0.9910\nEpoch 17/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0269 - acc: 0.9913\nEpoch 18/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0275 - acc: 0.9914\nEpoch 19/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0263 - acc: 0.9913\nEpoch 20/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0266 - acc: 0.9913\nEpoch 21/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0259 - acc: 0.9920\nEpoch 22/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0241 - acc: 0.9920\nEpoch 23/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0255 - acc: 0.9916\nEpoch 24/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0249 - acc: 0.9923\nEpoch 25/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0236 - acc: 0.9929\nEpoch 26/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0212 - acc: 0.9931\nEpoch 27/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0215 - acc: 0.9931\nEpoch 28/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0207 - acc: 0.9938\nEpoch 29/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0234 - acc: 0.9925\nEpoch 30/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0220 - acc: 0.9933\nEpoch 31/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0202 - acc: 0.9934\nEpoch 32/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0189 - acc: 0.9941\nEpoch 33/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0189 - acc: 0.9947\nEpoch 34/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0181 - acc: 0.9944\nEpoch 35/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0206 - acc: 0.9939\nEpoch 36/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0175 - acc: 0.9945\nEpoch 37/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0192 - acc: 0.9940\nEpoch 38/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0184 - acc: 0.9943\nEpoch 39/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0191 - acc: 0.9941\nEpoch 40/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0170 - acc: 0.9947\nEpoch 41/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0185 - acc: 0.9940\nEpoch 42/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0193 - acc: 0.9942\nEpoch 43/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0177 - acc: 0.9944\nEpoch 44/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0177 - acc: 0.9947\nEpoch 45/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0177 - acc: 0.9941\nEpoch 46/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0152 - acc: 0.9951\nEpoch 47/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0161 - acc: 0.9950\nEpoch 48/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0170 - acc: 0.9946\nEpoch 49/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0154 - acc: 0.9952\nEpoch 50/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0170 - acc: 0.9945\nEpoch 51/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0167 - acc: 0.9950\nEpoch 52/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0167 - acc: 0.9950\nEpoch 53/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0162 - acc: 0.9947\nEpoch 54/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0154 - acc: 0.9952\nEpoch 55/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0138 - acc: 0.9954\nEpoch 56/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0144 - acc: 0.9953\nEpoch 57/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0170 - acc: 0.9946\nEpoch 58/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0140 - acc: 0.9958\nEpoch 59/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0147 - acc: 0.9952\nEpoch 60/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0138 - acc: 0.9955\nEpoch 61/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0155 - acc: 0.9952\nEpoch 62/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0143 - acc: 0.9954\nEpoch 63/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0153 - acc: 0.9951\nEpoch 64/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0117 - acc: 0.9961\nEpoch 65/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0153 - acc: 0.9954\nEpoch 66/200\n440/440 [==============================] - 12s 28ms/step - loss: 0.0139 - acc: 0.9957\nEpoch 67/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0137 - acc: 0.9953\nEpoch 68/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0149 - acc: 0.9954\nEpoch 69/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0125 - acc: 0.9961\nEpoch 70/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0141 - acc: 0.9956\nEpoch 71/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0115 - acc: 0.9963\nEpoch 72/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0116 - acc: 0.9959\nEpoch 73/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0129 - acc: 0.9963\nEpoch 74/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0168 - acc: 0.9948\nEpoch 75/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0137 - acc: 0.9957\nEpoch 76/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0125 - acc: 0.9962\nEpoch 77/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0135 - acc: 0.9961\nEpoch 78/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0128 - acc: 0.9964\nEpoch 79/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0140 - acc: 0.9956\nEpoch 80/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0120 - acc: 0.9957\nEpoch 81/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0116 - acc: 0.9964\nEpoch 82/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0136 - acc: 0.9957\nEpoch 83/200\n","name":"stdout"},{"output_type":"stream","text":"440/440 [==============================] - 10s 23ms/step - loss: 0.0129 - acc: 0.9962\nEpoch 84/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0139 - acc: 0.9956\nEpoch 85/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0121 - acc: 0.9963\nEpoch 86/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0122 - acc: 0.9960\nEpoch 87/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0117 - acc: 0.9959\nEpoch 88/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0116 - acc: 0.9961\nEpoch 89/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0126 - acc: 0.9963\nEpoch 90/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0113 - acc: 0.9964\nEpoch 91/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0099 - acc: 0.9969\nEpoch 92/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0122 - acc: 0.9960\nEpoch 93/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0131 - acc: 0.9961\nEpoch 94/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0111 - acc: 0.9965\nEpoch 95/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0123 - acc: 0.9964\nEpoch 96/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0099 - acc: 0.9969\nEpoch 97/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0119 - acc: 0.9963\nEpoch 98/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0113 - acc: 0.9965\nEpoch 99/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0117 - acc: 0.9964\nEpoch 100/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0135 - acc: 0.9960\nEpoch 101/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0123 - acc: 0.9964\nEpoch 102/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0127 - acc: 0.9961\nEpoch 103/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0099 - acc: 0.9968\nEpoch 104/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0109 - acc: 0.9968\nEpoch 105/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0101 - acc: 0.9971\nEpoch 106/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0138 - acc: 0.9964\nEpoch 107/200\n440/440 [==============================] - 10s 22ms/step - loss: 0.0102 - acc: 0.9968\nEpoch 108/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0116 - acc: 0.9964\nEpoch 109/200\n440/440 [==============================] - 10s 22ms/step - loss: 0.0118 - acc: 0.9963\nEpoch 110/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0103 - acc: 0.9965\nEpoch 111/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0103 - acc: 0.9969\nEpoch 112/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0102 - acc: 0.9970\nEpoch 113/200\n440/440 [==============================] - 10s 22ms/step - loss: 0.0130 - acc: 0.9960\nEpoch 114/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0107 - acc: 0.9967\nEpoch 115/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0114 - acc: 0.9965\nEpoch 116/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0127 - acc: 0.9965\nEpoch 117/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0085 - acc: 0.9972\nEpoch 118/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0104 - acc: 0.9970\nEpoch 119/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0123 - acc: 0.9961\nEpoch 120/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0121 - acc: 0.9965\nEpoch 121/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0098 - acc: 0.9971\nEpoch 122/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0126 - acc: 0.9962\nEpoch 123/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0119 - acc: 0.9966\nEpoch 124/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0090 - acc: 0.9973\nEpoch 125/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0108 - acc: 0.9969\nEpoch 126/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0113 - acc: 0.9966\nEpoch 127/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0092 - acc: 0.9969\nEpoch 128/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0097 - acc: 0.9967\nEpoch 129/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0089 - acc: 0.9972\nEpoch 130/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0126 - acc: 0.9963\nEpoch 131/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0107 - acc: 0.9968\nEpoch 132/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0110 - acc: 0.9965\nEpoch 133/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0098 - acc: 0.9970\nEpoch 134/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0088 - acc: 0.9974\nEpoch 135/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0113 - acc: 0.9967\nEpoch 136/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0122 - acc: 0.9963\nEpoch 137/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0102 - acc: 0.9971\nEpoch 138/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0105 - acc: 0.9970\nEpoch 139/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0089 - acc: 0.9971\nEpoch 140/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0104 - acc: 0.9970\nEpoch 141/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0111 - acc: 0.9966\nEpoch 142/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0105 - acc: 0.9968\nEpoch 143/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0108 - acc: 0.9967\nEpoch 144/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0112 - acc: 0.9968\nEpoch 145/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0104 - acc: 0.9970\nEpoch 146/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0097 - acc: 0.9969\nEpoch 147/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0099 - acc: 0.9971\nEpoch 148/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0107 - acc: 0.9968\nEpoch 149/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0097 - acc: 0.9971\nEpoch 150/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0099 - acc: 0.9965\nEpoch 151/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0095 - acc: 0.9971\nEpoch 152/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0087 - acc: 0.9971\nEpoch 153/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0099 - acc: 0.9974\nEpoch 154/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0114 - acc: 0.9968\nEpoch 155/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0107 - acc: 0.9967\nEpoch 156/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0119 - acc: 0.9964\nEpoch 157/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0095 - acc: 0.9972\nEpoch 158/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0090 - acc: 0.9976\nEpoch 159/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0120 - acc: 0.9967\nEpoch 160/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0124 - acc: 0.9966\nEpoch 161/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0120 - acc: 0.9966\nEpoch 162/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0092 - acc: 0.9972\nEpoch 163/200\n440/440 [==============================] - 10s 22ms/step - loss: 0.0100 - acc: 0.9971\nEpoch 164/200\n","name":"stdout"},{"output_type":"stream","text":"440/440 [==============================] - 10s 23ms/step - loss: 0.0083 - acc: 0.9974\nEpoch 165/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0091 - acc: 0.9970\nEpoch 166/200\n440/440 [==============================] - 11s 26ms/step - loss: 0.0088 - acc: 0.9972\nEpoch 167/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0086 - acc: 0.9974\nEpoch 168/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0083 - acc: 0.9974\nEpoch 169/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0106 - acc: 0.9971\nEpoch 170/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0094 - acc: 0.9972\nEpoch 171/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0094 - acc: 0.9971\nEpoch 172/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0097 - acc: 0.9971\nEpoch 173/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0084 - acc: 0.9973\nEpoch 174/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0097 - acc: 0.9971 1s - loss: 0.\nEpoch 175/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0100 - acc: 0.9971\nEpoch 176/200\n440/440 [==============================] - 10s 22ms/step - loss: 0.0085 - acc: 0.9973\nEpoch 177/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0106 - acc: 0.9974 0s - loss: 0.0107 - a\nEpoch 178/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0102 - acc: 0.9970\nEpoch 179/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0087 - acc: 0.9974\nEpoch 180/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0106 - acc: 0.9969\nEpoch 181/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0077 - acc: 0.9976\nEpoch 182/200\n440/440 [==============================] - 12s 26ms/step - loss: 0.0084 - acc: 0.9974\nEpoch 183/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0108 - acc: 0.9969\nEpoch 184/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0100 - acc: 0.9974\nEpoch 185/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0077 - acc: 0.9978\nEpoch 186/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0110 - acc: 0.9968\nEpoch 187/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0090 - acc: 0.9969\nEpoch 188/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0082 - acc: 0.9974\nEpoch 189/200\n440/440 [==============================] - 11s 25ms/step - loss: 0.0092 - acc: 0.9974\nEpoch 190/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0115 - acc: 0.9967\nEpoch 191/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0094 - acc: 0.9972\nEpoch 192/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0082 - acc: 0.9976\nEpoch 193/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0079 - acc: 0.9979\nEpoch 194/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0095 - acc: 0.9971\nEpoch 195/200\n440/440 [==============================] - 10s 24ms/step - loss: 0.0090 - acc: 0.9971\nEpoch 196/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0086 - acc: 0.9976\nEpoch 197/200\n440/440 [==============================] - 12s 27ms/step - loss: 0.0092 - acc: 0.9974\nEpoch 198/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0088 - acc: 0.9973\nEpoch 199/200\n440/440 [==============================] - 11s 24ms/step - loss: 0.0109 - acc: 0.9967\nEpoch 200/200\n440/440 [==============================] - 10s 23ms/step - loss: 0.0090 - acc: 0.9972\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['loss'], color='r', label=\"Train Loss\")\nplt.title(\"Train Loss\")\nplt.xlabel(\"Number of Epochs\")\nplt.ylabel(\"Loss\")\nplt.legend()\nplt.show()","execution_count":15,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['acc'], color='g', label='Train Accuracy')\nplt.title('Train Accuracy')\nplt.xlabel('Number of Epochs')\nplt.ylabel('Accuracy')\nplt.legend()\nplt.show()","execution_count":16,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true,"_uuid":"295f9c3b2df5728e1534b8665124a6d676e9b3c3"},"cell_type":"code","source":"\ntest_loss, test_acc = model.evaluate(x_eval, y_eval)\nprint('accuracy:', test_acc)","execution_count":17,"outputs":[{"output_type":"stream","text":"4200/4200 [==============================] - 0s 99us/sample - loss: 0.0286 - acc: 0.9952\naccuracy: 0.99523807\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = model.predict_classes(test, verbose=1)","execution_count":18,"outputs":[{"output_type":"stream","text":"28000/28000 [==============================] - 2s 60us/sample\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"fd2cf0bc8f078601ffb08c16546416ffe99ee343"},"cell_type":"code","source":"\nfile = pd.DataFrame({\"ImageId\":list(range(1,len(output)+1)),\"Label\":output})\n\nfile.to_csv('submission.csv',index=False,header=True)\n\n","execution_count":19,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}