Tensorflow訓練識別自定義圖片

不少正在入門或剛入門TensorFlow機器學習的同窗但願可以經過本身指定圖片源對模型進行訓練,而後識別和分類本身指定的圖片。可是,在TensorFlow官方入門教程中,並沒有明確給出如何把自定義數據輸入訓練模型的方法。如今,咱們就參考官方入門課程《Deep MNIST for Experts》一節的內容(傳送門:https://www.tensorflow.org/get_started/mnist/pros),介紹如何將自定義圖片輸入到TensorFlow的訓練模型。html

在《Deep MNISTfor Experts》一節的代碼中,程序將TensorFlow自帶的mnist圖片數據集mnist.train.images做爲訓練輸入,將mnist.test.images做爲驗證輸入。當學習了該節內容後,咱們會驚歎卷積神經網絡的超高識別率,但對於剛開始學習TensorFlow的同窗,心裏可能會產生一個問號:如何將mnist數據集替換爲本身指定的圖片源?譬如,我要將圖片源改成本身C盤裏面的圖片,應該怎麼調整代碼?python

咱們先看下該節課程中涉及到mnist圖片調用的代碼:git

from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True) batch = mnist.train.next_batch(50) train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0}) train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) print('test accuracy %g' % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

要實現輸入自定義圖片,須要本身先準備好一套圖片集。爲節省時間,咱們把mnist的手寫體數字集一張一張地解析出來,存放到本身的本地硬盤,保存爲bmp格式,而後再把本地硬盤的手寫體圖片一張一張地讀取出來,組成集合,再輸入神經網絡。mnist手寫體數字集的提取方式詳見《如何從TensorFlow的mnist數據集導出手寫體數字圖片》。數組

將mnist手寫體數字集導出圖片到本地後,就能夠仿照如下python代碼,實現自定義圖片的訓練:網絡

import os import numpy as np import tensorflow as tf from PIL import Image # 第一次遍歷圖片目錄是爲了獲取圖片總數
input_count = 0 for i in range(0, 10): dir = './mnist_digits_images/%s/' % i  # 這裏能夠改爲你本身的圖片目錄,i爲分類標籤
    for rt, dirs, files in os.walk(dir): for filename in files: input_count += 1

# 定義對應維數和各維長度的數組
input_images = np.array([[0] * 784 for i in range(input_count)]) input_labels = np.array([[0] * 10 for i in range(input_count)]) # 第二次遍歷圖片目錄是爲了生成圖片數據和標籤
index = 0 for i in range(0, 10): dir = './mnist_digits_images/%s/' % i  # 這裏能夠改爲你本身的圖片目錄,i爲分類標籤
    for rt, dirs, files in os.walk(dir): for filename in files: filename = dir + filename img = Image.open(filename) width = img.size[0] height = img.size[1] for h in range(0, height): for w in range(0, width): # 經過這樣的處理,使數字的線條變細,有利於提升識別準確率
                    if img.getpixel((w, h)) > 230: input_images[index][w + h * width] = 0  # 以前已經將圖片轉換成了一維
                    else: input_images[index][w + h * width] = 1 input_labels[index][i] = 1 index += 1

# 定義輸入節點,對應於圖片像素值矩陣集合和圖片標籤(即所表明的數字)
x = tf.placeholder(tf.float32, shape=[None, 784]) y_ = tf.placeholder(tf.float32, shape=[None, 10]) x_image = tf.reshape(x, [-1, 28, 28, 1]) # 定義第一個卷積層的variables和ops
W_conv1 = tf.Variable(tf.truncated_normal([7, 7, 1, 32], stddev=0.1)) b_conv1 = tf.Variable(tf.constant(0.1, shape=[32])) L1_conv = tf.nn.conv2d(x_image, W_conv1, strides=[1, 1, 1, 1], padding='SAME') L1_relu = tf.nn.relu(L1_conv + b_conv1) L1_pool = tf.nn.max_pool(L1_relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # 定義第二個卷積層的variables和ops
W_conv2 = tf.Variable(tf.truncated_normal([3, 3, 32, 64], stddev=0.1)) b_conv2 = tf.Variable(tf.constant(0.1, shape=[64])) L2_conv = tf.nn.conv2d(L1_pool, W_conv2, strides=[1, 1, 1, 1], padding='SAME') L2_relu = tf.nn.relu(L2_conv + b_conv2) L2_pool = tf.nn.max_pool(L2_relu, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # 全鏈接層
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1)) b_fc1 = tf.Variable(tf.constant(0.1, shape=[1024])) h_pool2_flat = tf.reshape(L2_pool, [-1, 7 * 7 * 64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) # dropout
keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # readout層
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1)) b_fc2 = tf.Variable(tf.constant(0.1, shape=[10])) y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2 # 定義優化器和訓練op
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)) train_step = tf.train.AdamOptimizer((1e-4)).minimize(cross_entropy) correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) with tf.Session() as sess: sess.run(tf.global_variables_initializer()) print("一共讀取了 %s 個輸入圖像, %s 個標籤" % (input_count, input_count)) # 設置每次訓練op的輸入個數和迭代次數,這裏爲了支持任意圖片總數,定義了一個餘數remainder,譬如,若是每次訓練op的輸入個數爲60,圖片總數爲150張,則前面兩次各輸入60張,最後一次輸入30張(餘數30)
    batch_size = 60 iterations = 100 batches_count = int(input_count / batch_size) remainder = input_count % batch_size print("數據集分紅 %s 批, 前面每批 %s 個數據,最後一批 %s 個數據" % (batches_count + 1, batch_size, remainder)) # 執行訓練迭代
    for it in range(iterations): # 這裏的關鍵是要把輸入數組轉爲np.array
        for n in range(batches_count): train_step.run(feed_dict={x: input_images[n * batch_size:(n + 1) * batch_size], y_: input_labels[n * batch_size:(n + 1) * batch_size], keep_prob: 0.5}) if remainder > 0: start_index = batches_count * batch_size; train_step.run( feed_dict={x: input_images[start_index:input_count - 1], y_: input_labels[start_index:input_count - 1], keep_prob: 0.5}) # 每完成五次迭代,判斷準確度是否已達到100%,達到則退出迭代循環
        iterate_accuracy = 0 if it % 5 == 0: iterate_accuracy = accuracy.eval(feed_dict={x: input_images, y_: input_labels, keep_prob: 1.0}) print('iteration %d: accuracy %s' % (it, iterate_accuracy)) if iterate_accuracy >= 1: break; print('完成訓練!')

 上述python代碼的執行結果截圖以下:機器學習

 

對於上述代碼中與模型構建相關的代碼,請查閱官方《Deep MNIST for Experts》一節的內容進行理解。在本文中,須要重點掌握的是如何將本地圖片源整合成爲feed_dict可接受的格式。其中最關鍵的是這兩行:ide

# 定義對應維數和各維長度的數組
input_images = np.array([[0]*784 for i in range(input_count)]) input_labels = np.array([[0]*10 for i in range(input_count)])

它們對應於feed_dict的兩個placeholder:學習

x = tf.placeholder(tf.float32, shape=[None, 784]) y_ = tf.placeholder(tf.float32, shape=[None, 10])

 

轉自https://www.jb51.net/article/166937.htm優化

相關文章
相關標籤/搜索