{"id":928,"date":"2020-09-26T21:47:44","date_gmt":"2020-09-26T12:47:44","guid":{"rendered":"http:\/\/leenux.kr\/?p=928"},"modified":"2020-10-10T03:33:19","modified_gmt":"2020-10-09T18:33:19","slug":"tensorflow-keras-mnist-image-training","status":"publish","type":"post","link":"https:\/\/leenux.kr\/?p=928","title":{"rendered":"Tensorflow keras MNIST image of Optimization & Training (beginner)"},"content":{"rendered":"\n

Tensorflow \uacf5\uc2dd \uc0ac\uc774\ud2b8 \uc774\ubbf8\uc9c0 \ubd84\uc11d \ucd08\ubcf4\uc790 \uc608\uc81c <\/strong><\/p>\n\n\n\n

\ucd08\ubcf4\uc790 \uc608\uc81c <\/strong><\/p>\n\n\n\n

https:\/\/www.tensorflow.org\/tutorials\/quickstart\/beginner<\/strong><\/a><\/p>\n\n\n\n

\ud559\uc2b5\uacfc\uc815<\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Import tensorflow keras layers And MNIST<\/strong><\/p>\n\n\n\n

import tensorflow as tf\nfrom tensorflow.keras import layers\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras import datasets\n\n(train_x, train_y), (test_x, test_y) = datasets.mnist.load_data()<\/code><\/pre>\n\n\n\n
\n\n\n\n
Build Model<\/strong><\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
inputs = layers.Input((28, 28, 1))\nnet = layers.Conv2D(32, (3, 3), padding='SAME')(inputs)\nnet = layers.Activation('relu')(net)\nnet = layers.Conv2D(32, (3, 3), padding='SAME')(net)\nnet = layers.Activation('relu')(net)\nnet = layers.MaxPooling2D(pool_size=(2, 2))(net)\nnet = layers.Dropout(0.25)(net)\n\nnet = layers.Conv2D(64, (3, 3), padding='SAME')(net)\nnet = layers.Activation('relu')(net)\nnet = layers.Conv2D(64, (3, 3), padding='SAME')(net)\nnet = layers.Activation('relu')(net)\nnet = layers.MaxPooling2D(pool_size=(2, 2))(net)\nnet = layers.Dropout(0.25)(net)\n\nnet = layers.Flatten()(net)\nnet = layers.Dense(512)(net)\nnet = layers.Activation('relu')(net)\nnet = layers.Dropout(0.5)(net)\nnet = layers.Dense(10)(net)  # num_classes\nnet = layers.Activation('softmax')(net)\n\nmodel = tf.keras.Model(inputs=inputs, outputs=net, name='Basic_CNN')<\/code><\/pre>\n\n\n\n
\n\n\n\n
Model Compile<\/strong><\/p>\n\n\n\n
Loss Function
Optimization
Metrics<\/strong><\/p>\n\n\n\n
Optimization<\/strong><\/p>\n\n\n\n
\ubaa8\ub378\uc744 \ud559\uc2b5\ud558\uae30 \uc804 \uc124\uc815<\/p>\n\n\n\n