我想用Tensorflow进行三种不同图像类别的图像识别。我现在的问题是如何为我的训练集标记图像并将其存储在一个二维数组中，以便在识别中使用。我已经使用了一种方法来存储两个类别（在代码示例中是X和Y），但现在我想也为第三个类别（在代码中命名为Z）这样做。

import cv2                 # 处理图像，主要是调整大小
import numpy as np         # 处理数组
import os                  # 处理目录
from random import shuffle # 混合当前数据
from tqdm import tqdm      # 任务进度条
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 # 学习率
LR = 1e-5
MODEL_NAME = 'name-{}-{}.model'.format(LR, '2conv-basic')
# 将图像和标签信息转换为数组信息
def label_img(img):
    #分割图像
    word_label = img.split('.')[-3]
    if word_label == 'X': return [1,0]
    elif word_label == 'Y': return [0,1]
    elif word_label == 'Z' : return [???]
# 创建训练数据数组
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()
# 如果你已经有训练数据：
#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)
# 如果你需要创建数据：
test_data = process_test_data()
# 如果你已经保存了一些数据：
#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()

回答：

要添加一个类别，只需扩展你的图像标签数组的维度：

# 将图像和标签信息转换为数组信息
def label_img(img):
    #分割图像
    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]

你还需要更新softmax分类器以处理3个类别：

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

你还需要禁用旧模型的加载。旧模型只适用于旧的图形，但由于我们正在更改它，我们必须从头开始。

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