在 Tensorflow 的二维数组中存储和标记图像

Question

我想用 Tensorflow 对三个不同的图像进行图像识别 classes。我现在的问题是为我的训练集标记图像并将其存储在二维数组中以用于识别。我已经使用方法来存储 2 classes（在代码示例中是 X 和 Y），但现在我想第三个 class 也这样做（在以 Z.

命名的代码中

import cv2                 # working with, mainly resizing, images
import numpy as np         # dealing with arrays
import os                  # dealing with directories
from random import shuffle # mixing up current data
from tqdm import tqdm      # percentage bar for tasks
import time
import matplotlib.pyplot as plt

import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression


TRAIN_DIR = 'MYPATH'
TEST_DIR = 'MYPATH'
IMG_SIZE = 80 
# learning rate
LR = 1e-5

MODEL_NAME = 'name-{}-{}.model'.format(LR, '2conv-basic')

# convert image and label information to array information
def label_img(img):
    #split images
    word_label = img.split('.')[-3]
    if word_label == 'X': return [1,0] 
    elif word_label == 'Y': return [0,1]
    elif word_label == 'Z' : return [???]

# create training data array
def create_train_data():
    training_data = []
    for img in tqdm(os.listdir(TRAIN_DIR)):
        label = label_img(img)
        path = os.path.join(TRAIN_DIR,img)
        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
        img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
        training_data.append([np.array(img),np.array(label)])
    shuffle(training_data)
    np.save('train_data.npy', training_data)
    return training_data

def process_test_data():
    testing_data = []
    for img in tqdm(os.listdir(TEST_DIR)):
        path = os.path.join(TEST_DIR,img)
        img_num = img.split('.')[1]
        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
        img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
        testing_data.append([np.array(img), img_num])

    shuffle(testing_data)
    np.save('test_data.npy', testing_data)
    return testing_data

train_data = create_train_data()
# if you already have train data:
#train_data = np.load('train_data.npy')

import tensorflow as tf
tf.reset_default_graph()

convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')

convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

model = tflearn.DNN(convnet, tensorboard_dir='log')

if os.path.exists('{}.meta'.format(MODEL_NAME)):
    model.load(MODEL_NAME)
    print('model loaded!')

train = train_data[:-500]
test = train_data[-500:]

X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE, IMG_SIZE, 1)
Y = [i[1] for i in train]

test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = [i[1] for i in test]

model.fit({'input': X}, {'targets': Y}, n_epoch=15, validation_set=({'input': test_x}, {'targets': test_y}), 
    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)

model.save(MODEL_NAME)

# if you need to create the data:
test_data = process_test_data()
# if you already have some saved:
#test_data = np.load('test_data.npy')

fig=plt.figure()

for num,data in enumerate(test_data[:12]):

    img_num = data[1]
    img_data = data[0]

    y = fig.add_subplot(3,4,num+1)
    orig = img_data
    data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)
    #model_out = model.predict([data])[0]
    model_out = model.predict([data])[0]

    if np.argmax(model_out) == 1: str_label='X'
    else: str_label='Y'

    y.imshow(orig,cmap='gray')
    plt.title(str_label)
    y.axes.get_xaxis().set_visible(False)
    y.axes.get_yaxis().set_visible(False)
plt.show()

Answer 1

要添加 class，只需扩展图像标签数组的维度：

# convert image and label information to array information
def label_img(img):
    #split images
    word_label = img.split('.')[-3]
    if word_label == 'X': return [1,0,0] 
    elif word_label == 'Y': return [0,1,0]
    elif word_label == 'Z' : return [0,0,1]

您还需要更新 softmax classifier 来处理 3 classes:

convnet = fully_connected(convnet, 3, activation='softmax')

您还需要禁用旧模型的加载。旧模型仅对旧图有效，但由于正在更改我们必须从头开始。

###
if os.path.exists('{}.meta'.format(MODEL_NAME)):
    model.load(MODEL_NAME)
    print('model loaded!')
###

在 Tensorflow 的二维数组中存储和标记图像

Store and label image in a 2D-Array for Tensorflow

python

machine-learning

image-recognition

labeling

tensorflow