tensorflow 手写数字识别

发布时间:2017-7-1 11:17:49编辑:www.fx114.net 分享查询网我要评论
本篇文章主要介绍了"tensorflow 手写数字识别 ",主要涉及到tensorflow 手写数字识别 方面的内容,对于tensorflow 手写数字识别 感兴趣的同学可以参考一下。

https://www.kaggle.com/kakauandme/tensorflow-deep-nn

本人只是负责将这个kernels的代码整理了一遍,具体还是请看原链接

import numpy as npimport pandas as pdimport tensorflow# settingsLEARNING_RATE = 1e-4# set to 20000 on local environment to get 0.99 accuracyTRAINING_ITERATIONS = 20000    DROPOUT = 0.5BATCH_SIZE = 50# set to 0 to train on all available dataVALIDATION_SIZE = 2000# image number to outputIMAGE_TO_DISPLAY = 10# read training data from CSV file data = pd.read_csv('D://kaggle//DigitRecognizer//data//train.csv')images = data.iloc[:,1:].valuesimages = images.astype(np.float)# convert from [0:255] => [0.0:1.0]images = np.multiply(images, 1.0 / 255.0)image_size = images.shape[1]print ('image_size => {0}'.format(image_size))# in this case all images are squareimage_width = image_height = np.ceil(np.sqrt(image_size)).astype(np.uint8)print ('image_width => {0}\nimage_height => {1}'.format(image_width,image_height))labels_flat = data.iloc[:,0].valuesprint('labels_flat({0})'.format(len(labels_flat)))print ('labels_flat[{0}] => {1}'.format(IMAGE_TO_DISPLAY,labels_flat[IMAGE_TO_DISPLAY]))labels_count = np.unique(labels_flat).shape[0]print('labels_count => {0}'.format(labels_count))def dense_to_one_hot(labels_dense, num_classes):    num_labels = labels_dense.shape[0]    index_offset = np.arange(num_labels) * num_classes    labels_one_hot = np.zeros((num_labels, num_classes))    labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1    return labels_one_hotlabels = dense_to_one_hot(labels_flat, labels_count)labels = labels.astype(np.uint8)print('labels({0[0]},{0[1]})'.format(labels.shape))print ('labels[{0}] => {1}'.format(IMAGE_TO_DISPLAY,labels[IMAGE_TO_DISPLAY]))# split data into training & validationvalidation_images = images[:VALIDATION_SIZE]validation_labels = labels[:VALIDATION_SIZE]train_images = images[VALIDATION_SIZE:]train_labels = labels[VALIDATION_SIZE:]print('train_images({0[0]},{0[1]})'.format(train_images.shape))print('validation_images({0[0]},{0[1]})'.format(validation_images.shape))# weight initializationdef weight_variable(shape):    initial = tensorflow.truncated_normal(shape, stddev=0.1)    return tensorflow.Variable(initial)def bias_variable(shape):    initial = tensorflow.constant(0.1, shape=shape)    return tensorflow.Variable(initial)# convolutiondef conv2d(x, W):    return tensorflow.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')# pooling# [[0,3],#  [4,2]] => 4# [[0,1],#  [1,1]] => 1def max_pool_2x2(x):    return tensorflow.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')# input & output of NN# imagesx = tensorflow.placeholder('float', shape=[None, image_size])# labelsy_ = tensorflow.placeholder('float', shape=[None, labels_count])# first convolutional layerW_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])# (40000,784) => (40000,28,28,1)image = tensorflow.reshape(x, [-1,image_width , image_height,1])#print (image.get_shape()) # =>(40000,28,28,1)h_conv1 = tensorflow.nn.relu(conv2d(image, W_conv1) + b_conv1)#print (h_conv1.get_shape()) # => (40000, 28, 28, 32)h_pool1 = max_pool_2x2(h_conv1)#print (h_pool1.get_shape()) # => (40000, 14, 14, 32)# Prepare for visualization# display 32 fetures in 4 by 8 gridlayer1 = tensorflow.reshape(h_conv1, (-1, image_height, image_width, 4 ,8))  # reorder so the channels are in the first dimension, x and y follow.layer1 = tensorflow.transpose(layer1, (0, 3, 1, 4,2))layer1 = tensorflow.reshape(layer1, (-1, image_height*4, image_width*8)) # second convolutional layerW_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tensorflow.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)#print (h_conv2.get_shape()) # => (40000, 14,14, 64)h_pool2 = max_pool_2x2(h_conv2)#print (h_pool2.get_shape()) # => (40000, 7, 7, 64)# Prepare for visualization# display 64 fetures in 4 by 16 gridlayer2 = tensorflow.reshape(h_conv2, (-1, 14, 14, 4 ,16))  # reorder so the channels are in the first dimension, x and y follow.layer2 = tensorflow.transpose(layer2, (0, 3, 1, 4,2))layer2 = tensorflow.reshape(layer2, (-1, 14*4, 14*16)) # densely connected layerW_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])# (40000, 7, 7, 64) => (40000, 3136)h_pool2_flat = tensorflow.reshape(h_pool2, [-1, 7*7*64])h_fc1 = tensorflow.nn.relu(tensorflow.matmul(h_pool2_flat, W_fc1) + b_fc1)#print (h_fc1.get_shape()) # => (40000, 1024)# dropoutkeep_prob = tensorflow.placeholder('float')h_fc1_drop = tensorflow.nn.dropout(h_fc1, keep_prob)# readout layer for deep netW_fc2 = weight_variable([1024, labels_count])b_fc2 = bias_variable([labels_count])y = tensorflow.nn.softmax(tensorflow.matmul(h_fc1_drop, W_fc2) + b_fc2)#print (y.get_shape()) # => (40000, 10)# cost functioncross_entropy = -tensorflow.reduce_sum(y_*tensorflow.log(y))# optimisation functiontrain_step = tensorflow.train.AdamOptimizer(LEARNING_RATE).minimize(cross_entropy)# evaluationcorrect_prediction = tensorflow.equal(tensorflow.argmax(y,1),tensorflow.argmax(y_,1))accuracy = tensorflow.reduce_mean(tensorflow.cast(correct_prediction, 'float'))# prediction function#[0.1, 0.9, 0.2, 0.1, 0.1 0.3, 0.5, 0.1, 0.2, 0.3] => 1predict = tensorflow.argmax(y,1)epochs_completed = 0index_in_epoch = 0num_examples = train_images.shape[0]# serve data by batchesdef next_batch(batch_size):        global train_images    global train_labels    global index_in_epoch    global epochs_completed        start = index_in_epoch    index_in_epoch += batch_size        # when all trainig data have been already used, it is reorder randomly        if index_in_epoch > num_examples:        # finished epoch        epochs_completed += 1        # shuffle the data        perm = np.arange(num_examples)        np.random.shuffle(perm)        train_images = train_images[perm]        train_labels = train_labels[perm]        # start next epoch        start = 0        index_in_epoch = batch_size        assert batch_size <= num_examples    end = index_in_epoch    return train_images[start:end], train_labels[start:end]# start TensorFlow sessioninit = tensorflow.initialize_all_variables()sess = tensorflow.InteractiveSession()sess.run(init)# visualisation variablestrain_accuracies = []validation_accuracies = []x_range = []display_step=1for i in range(TRAINING_ITERATIONS):    #get new batch    batch_xs, batch_ys = next_batch(BATCH_SIZE)            # check progress on every 1st,2nd,...,10th,20th,...,100th... step    if i%display_step == 0 or (i+1) == TRAINING_ITERATIONS:                train_accuracy = accuracy.eval(feed_dict={x:batch_xs,                                                 y_: batch_ys,                                                 keep_prob: 1.0})               if(VALIDATION_SIZE):            validation_accuracy = accuracy.eval(feed_dict={ x: validation_images[0:BATCH_SIZE],                                                             y_: validation_labels[0:BATCH_SIZE],                                                             keep_prob: 1.0})                                              print('training_accuracy / validation_accuracy => %.2f / %.2f for step %d'%(train_accuracy, validation_accuracy, i))                        validation_accuracies.append(validation_accuracy)                    else:            print('training_accuracy => %.4f for step %d'%(train_accuracy, i))        train_accuracies.append(train_accuracy)        x_range.append(i)                # increase display_step        if i%(display_step*10) == 0 and i:            display_step *= 10    # train on batch    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys, keep_prob: DROPOUT})# read test data from CSV file test_images = pd.read_csv('D://kaggle//DigitRecognizer//data//test.csv').valuestest_images = test_images.astype(np.float)# convert from [0:255] => [0.0:1.0]test_images = np.multiply(test_images, 1.0 / 255.0)print('test_images({0[0]},{0[1]})'.format(test_images.shape))# predict test set#predicted_lables = predict.eval(feed_dict={x: test_images, keep_prob: 1.0})# using batches is more resource efficientpredicted_lables = np.zeros(test_images.shape[0])for i in range(0,test_images.shape[0]//BATCH_SIZE):    predicted_lables[i*BATCH_SIZE : (i+1)*BATCH_SIZE] = predict.eval(feed_dict={x: test_images[i*BATCH_SIZE : (i+1)*BATCH_SIZE],                                                                                 keep_prob: 1.0})print('predicted_lables({0})'.format(len(predicted_lables)))# output test image and prediction#   display(test_images[IMAGE_TO_DISPLAY])print ('predicted_lables[{0}] => {1}'.format(IMAGE_TO_DISPLAY,predicted_lables[IMAGE_TO_DISPLAY]))# save resultsnp.savetxt('D://kaggle//DigitRecognizer//submission_softmax.csv',         np.c_[range(1,len(test_images)+1),predicted_lables],         delimiter=',',         header = 'ImageId,Label',         comments = '',         fmt='%d')layer1_grid = layer1.eval(feed_dict={x: test_images[IMAGE_TO_DISPLAY:IMAGE_TO_DISPLAY+1], keep_prob: 1.0})sess.close()


上一篇:iOS 适用于Pad上的菜单弹出界面-最简单的一种实现记录
下一篇:Objective C 中的BOOL, bool, Boolean理解

相关文章

相关评论

本站评论功能暂时取消,后续此功能例行通知。

一、不得利用本站危害国家安全、泄露国家秘密,不得侵犯国家社会集体的和公民的合法权益,不得利用本站制作、复制和传播不法有害信息!

二、互相尊重,对自己的言论和行为负责。

好贷网好贷款