import tensorflow as tf
import matplotlib.pyplot as plt
import input_datamnist = input_data.read_data_sets('data/', one_hot=True)
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print('MNIST ready')n_input = 784
n_output = 10weights = {'wc1': tf.Variable(tf.truncated_normal([3, 3, 1, 64], stddev=0.1)),'wc2': tf.Variable(tf.truncated_normal([3, 3, 64, 128], stddev=0.1)),'wd1': tf.Variable(tf.truncated_normal([7*7*128, 1024], stddev=0.1)),'wd2': tf.Variable(tf.truncated_normal([1024, n_outpot], stddev=0.1)),
}
biases = {'bc1': tf.Variable(tf.random_normal([64], stddev=0.1)),'bc2': tf.Variable(tf.random_normal([128], stddev=0.1)),'bd1': tf.Variable(tf.random_normal([1024], stddev=0.1)),'bd2': tf.Variable(tf.random_normal([n_outpot], stddev=0.1)),
}def conv_basic(_input, _w, _b, _keepratio):_input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])_conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')_conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))_pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')_pool_dr1 = tf.nn.dropout(_pool1, _keepratio)_conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')_conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))_pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')_pool_dr2 = tf.nn.dropout(_pool2, _keepratio)_densel = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])_fc1 = tf.nn.relu(tf.add(tf.matmul(_densel, _w['wd1']), _b['bd1']))_fc_dr1 = tf.nn.dropout(_fc1, _keepratio)_out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])out = {'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool_dr1': _pool_dr1,'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'densel': _densel,'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out}return outprint('CNN READY')x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)_pred = conv_basic(x, weights, biases, keepratio)['out']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y))
optm = tf.train.AdamOptimizer(learning_rate=0.01).minimize(cost)
_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))
init = tf.global_variables_initializer()print('GRAPH READY')sess = tf.Session()
sess.run(init)
training_epochs = 15
batch_size = 16
display_step = 1for epoch in range(training_epochs):avg_cost = 0.total_batch = 10for i in range(total_batch):batch_xs, batch_ys = mnist.train.next_batch(batch_size)sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio: 0.7})avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.0})/total_batchif epoch % display_step == 0:print('Epoch: %03d/%03d cost: %.9f' % (epoch, training_epochs, avg_cost))train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.})print('Training accuracy: %.3f' % (train_acc))res_dict = {'weight': sess.run(weights), 'biases': sess.run(biases)}import pickle
with open('res_dict.pkl', 'wb') as f:pickle.dump(res_dict, f, pickle.HIGHEST_PROTOCOL)

import pickle
import numpy as npdef load_file(path, name):with open(path+''+name+'.pkl', 'rb') as f:return pickle.load(f)res_dict = load_file('', 'res_dict')
print(res_dict['weight']['wc1'])index = 0import input_data
mnist = input_data.read_data_sets('data/', one_hot=True)test_image = mnist.test.images
test_label = mnist.test.labelsimport tensorflow as tfdef conv_basic(_input, _w, _b, _keepratio):_input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])_conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')_conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))_pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')_pool_dr1 = tf.nn.dropout(_pool1, _keepratio)_conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')_conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))_pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')_pool_dr2 = tf.nn.dropout(_pool2, _keepratio)_densel = tf.reshape(_pool_dr2, [-1, _w['wd1'].shape[0]])_fc1 = tf.nn.relu(tf.add(tf.matmul(_densel, _w['wd1']), _b['bd1']))_fc_dr1 = tf.nn.dropout(_fc1, _keepratio)_out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])out = {'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool_dr1': _pool_dr1,'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'densel': _densel,'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out}return outn_input = 784
n_output = 10x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])keepratio = tf.placeholder(tf.float32)_pred = conv_basic(x, res_dict['weight'], res_dict['biases'], keepratio)['out']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y))_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))init = tf.global_variables_initializer()sess = tf.Session()
sess.run(init)
training_epochs = 1
batch_size = 1
display_step = 1for epoch in range(training_epochs):avg_cost = 0.total_batch = 10for i in range(total_batch):batch_xs, batch_ys = mnist.train.next_batch(batch_size)if epoch % display_step == 0:print('_pre:', np.argmax(sess.run(_pred, feed_dict={x: batch_xs, keepratio: 1. })))print('answer:', np.argmax(batch_ys))