我制作了一个模型，可以使用大约10500张图像的数据集对82个数字进行分类。
数据集分为两个文件夹：
第一个文件夹是训练文件夹，包含8000张图像，分为82个文件夹
第二个文件夹是测试文件夹，包含2000张图像，分为82个文件夹
在进入主要数据集文件夹之前，我已经在另外两个文件夹上测试了模型，效果很好
但在这里我不知道为什么准确率无法提高
请注意，我的数据库中并非所有文件夹都包含相同数量的图像，且图像的分辨率也不相同，但大致都在210×50左右
另外请注意，在我的第一次尝试中，当我使用模型在两个文件夹上进行测试时，我创建了一个包含两个类的小数据集，每个文件夹中的图像数量相同（验证文件夹也是如此）
下面是我用来创建模型的代码：

from keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Densefrom keras import backend as K# dimensions of our images.img_width, img_height = 251, 54#img_width, img_height = 150, 33train_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/train'validation_data_dir = 'C:/Users/ADEM/Desktop/msi_youssef/PFE/test/numbers/data/valid'nb_train_samples = 10435nb_validation_samples = 2051epochs = 20 # how much time you want to train your model on the databatch_size = 16if K.image_data_format() == 'channels_first':    input_shape = (3, img_width, img_height)else:    input_shape = (img_width, img_height, 3)model = Sequential()model.add(Conv2D(32, (3, 3), input_shape=input_shape))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Conv2D(32, (3, 3)))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Conv2D(64, (3, 3)))model.add(Activation('relu'))model.add(MaxPooling2D(pool_size=(2, 2)))model.add(Flatten())model.add(Dense(64))model.add(Activation('relu'))model.add(Dropout(0.5))model.add(Dense(1))model.add(Activation('sigmoid'))model.compile(loss='binary_crossentropy',optimizer='rmsprop',metrics=['accuracy'])# this is the augmentation configuration we will use for trainingtrain_datagen = ImageDataGenerator(    rescale=1. / 255,    shear_range=0.1,    zoom_range=0.05,    horizontal_flip=False)# this is the augmentation configuration we will use for testing:# only rescalingtest_datagen = ImageDataGenerator(rescale=1. / 255)train_generator = train_datagen.flow_from_directory(    train_data_dir,    target_size=(img_width, img_height),    batch_size=batch_size,    class_mode='binary')validation_generator = test_datagen.flow_from_directory(    validation_data_dir,    target_size=(img_width, img_height),    batch_size=batch_size,    class_mode='binary')model.fit_generator(    train_generator,    steps_per_epoch=nb_train_samples // batch_size,    epochs=epochs,    validation_data=validation_generator,    validation_steps=nb_validation_samples // batch_size)model.save('first_try.h5')  

结果如下：

WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3976: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:133: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.Instructions for updating:Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3376: The name tf.log is deprecated. Please use tf.math.log instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\tensorflow_core\python\ops\nn_impl.py:183: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.Instructions for updating:Use tf.where in 2.0, which has the same broadcast rule as np.whereFound 10435 images belonging to 82 classes.Found 2051 images belonging to 82 classes.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:973: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:2741: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.Epoch 1/20WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:190: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:199: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead.WARNING:tensorflow:From C:\Users\ADEM\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:206: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead.652/652 [==============================] - 43s 65ms/step - loss: -625.7214 - acc: 0.0143 - val_loss: -632.8458 - val_acc: 0.0112Epoch 2/20652/652 [==============================] - 47s 72ms/step - loss: -627.1426 - acc: 0.0143 - val_loss: -632.6816 - val_acc: 0.0113Epoch 3/20652/652 [==============================] - 42s 65ms/step - loss: -627.8743 - acc: 0.0143 - val_loss: -633.1438 - val_acc: 0.0113Epoch 4/20652/652 [==============================] - 45s 69ms/step - loss: -627.0466 - acc: 0.0142 - val_loss: -632.6816 - val_acc: 0.0108Epoch 5/20652/652 [==============================] - 47s 73ms/step - loss: -628.4401 - acc: 0.0143 - val_loss: -632.7599 - val_acc: 0.0118Epoch 6/20652/652 [==============================] - 45s 69ms/step - loss: -626.8264 - acc: 0.0143 - val_loss: -631.9844 - val_acc: 0.0108Epoch 7/20652/652 [==============================] - 55s 85ms/step - loss: -627.8007 - acc: 0.0141 - val_loss: -636.2931 - val_acc: 0.0103Epoch 8/20652/652 [==============================] - 46s 71ms/step - loss: -626.7282 - acc: 0.0144 - val_loss: -633.0968 - val_acc: 0.0123Epoch 9/20652/652 [==============================] - 47s 72ms/step - loss: -628.2569 - acc: 0.0143 - val_loss: -633.8959 - val_acc: 0.0113Epoch 10/20652/652 [==============================] - 46s 71ms/step - loss: -627.1006 - acc: 0.0144 - val_loss: -629.7360 - val_acc: 0.0113Epoch 11/20652/652 [==============================] - 54s 83ms/step - loss: -627.1028 - acc: 0.0142 - val_loss: -636.8650 - val_acc: 0.0098Epoch 12/20652/652 [==============================] - 45s 70ms/step - loss: -627.8524 - acc: 0.0143 - val_loss: -627.5894 - val_acc: 0.0118Epoch 13/20652/652 [==============================] - 46s 70ms/step - loss: -627.1357 - acc: 0.0142 - val_loss: -631.9687 - val_acc: 0.0118Epoch 14/20652/652 [==============================] - 48s 73ms/step - loss: -627.5105 - acc: 0.0146 - val_loss: -638.9724 - val_acc: 0.0118Epoch 15/20652/652 [==============================] - 46s 70ms/step - loss: -629.0591 - acc: 0.0136 - val_loss: -630.7622 - val_acc: 0.0103Epoch 16/20652/652 [==============================] - 46s 71ms/step - loss: -625.9115 - acc: 0.0147 - val_loss: -630.3392 - val_acc: 0.0098Epoch 17/20652/652 [==============================] - 45s 70ms/step - loss: -627.0184 - acc: 0.0144 - val_loss: -636.2304 - val_acc: 0.0123Epoch 18/20652/652 [==============================] - 47s 72ms/step - loss: -626.8828 - acc: 0.0144 - val_loss: -634.5618 - val_acc: 0.0118Epoch 19/20652/652 [==============================] - 45s 70ms/step - loss: -627.3642 - acc: 0.0140 - val_loss: -629.8300 - val_acc: 0.0118Epoch 20/20652/652 [==============================] - 46s 71ms/step - loss: -627.4297 - acc: 0.0142 - val_loss: -637.6797 - val_acc: 0.0108  

回答：

由于您的模型现在处理的是多类问题，需要进行一些更改：

• 损失函数应为categorical_crossentropy而不是binary_crossentropy
• 最后的激活函数应为softmax而不是sigmoid
• 如果有82个类别，最后一层应有82个神经元（Dense(82)而不是Dense(1)）

祝好运！