Python Tensorflow模型验证精度不增加

我已经建立了一个tensorflow模型，在不同的时期，我的验证准确度没有变化，这让我相信我的设置有问题。下面是我的代码

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import regularizers
import tensorflow as tf

model = Sequential()
model.add(Conv2D(16, (3, 3), input_shape=(299, 299,3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(32, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

# this converts our 3D feature maps to 1D feature vectors
model.add(Flatten())  

model.add(Dense(512))
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'])

batch_size=32

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
        rescale=1./255,
        # shear_range=0.2,
        # zoom_range=0.2,
        horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)

# this is a generator that will read pictures found in
# subfolers of 'data/train', and indefinitely generate
# batches of augmented image data
train_generator = train_datagen.flow_from_directory(
        'Documents/Training',  # this is the target directory
         target_size=(299, 299),  #all images will be resized to 299
        batch_size=batch_size,
        class_mode='binary')  # since we use binary_crossentropy loss, we need binary labels

# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(
        'Documents/Dev',
        target_size=(299, 299),
        batch_size=batch_size,
        class_mode='binary')
#w1 =  tf.Variable(tf.truncated_normal([784, 30], stddev=0.1))
model.fit_generator(
        train_generator,
        steps_per_epoch=50 // batch_size,
        verbose = 1,
        epochs=10,
        validation_data=validation_generator,
        validation_steps=8 // batch_size)

当我运行时，会产生以下输出。就我的架构或数据生成步骤而言，这里缺少什么？我已经提到了，但没有用

Epoch 1/10
3/3 [==============================] - 2s 593ms/step - loss: 0.6719 - accuracy: 0.6250 - val_loss: 0.8198 - val_accuracy: 0.5000
Epoch 2/10
3/3 [==============================] - 2s 607ms/step - loss: 0.6521 - accuracy: 0.6667 - val_loss: 0.8518 - val_accuracy: 0.5000
Epoch 3/10
3/3 [==============================] - 2s 609ms/step - loss: 0.6752 - accuracy: 0.6250 - val_loss: 0.7129 - val_accuracy: 0.5000
Epoch 4/10
3/3 [==============================] - 2s 611ms/step - loss: 0.6841 - accuracy: 0.6250 - val_loss: 0.7010 - val_accuracy: 0.5000
Epoch 5/10
3/3 [==============================] - 2s 608ms/step - loss: 0.6977 - accuracy: 0.5417 - val_loss: 0.6551 - val_accuracy: 0.5000
Epoch 6/10
3/3 [==============================] - 2s 607ms/step - loss: 0.6508 - accuracy: 0.7083 - val_loss: 0.5752 - val_accuracy: 0.5000
Epoch 7/10
3/3 [==============================] - 2s 615ms/step - loss: 0.6596 - accuracy: 0.6875 - val_loss: 0.9326 - val_accuracy: 0.5000
Epoch 8/10
3/3 [==============================] - 2s 604ms/step - loss: 0.7022 - accuracy: 0.6458 - val_loss: 0.6976 - val_accuracy: 0.5000
Epoch 9/10
3/3 [==============================] - 2s 591ms/step - loss: 0.6331 - accuracy: 0.7292 - val_loss: 0.9571 - val_accuracy: 0.5000
Epoch 10/10
3/3 [==============================] - 2s 595ms/step - loss: 0.6085 - accuracy: 0.7292 - val_loss: 0.6029 - val_accuracy: 0.5000
Out[24]: <keras.callbacks.callbacks.History at 0x1ee4e3a8f08>

1/10纪元
3/3[=====================================================================2s 593ms/步-损耗：0.6719-精度：0.6250-val_损耗：0.8198-val_精度：0.5000
纪元2/10
3/3[=====================================================================2s 607ms/步-损耗：0.6521-精度：0.6667-val_损耗：0.8518-val_精度：0.5000
纪元3/10
3/3[==================================================================2s 609ms/步-损耗：0.6752-精度：0.6250-val_损耗：0.7129-val_精度：0.5000
纪元4/10
3/3[=====================================================================2s 611ms/步-损耗：0.6841-精度：0.6250-val_损耗：0.7010-val_精度：0.5000
纪元5/10
3/3[========================================================================2s 608ms/步-损耗：0.6977-精度：0.5417-val_损耗：0.6551-val_精度：0.5000
纪元6/10
3/3[==================================================================2s 607ms/步-损耗：0.6508-精度：0.7083-val_损耗：0.5752-val_精度：0.5000
纪元7/10
3/3[===============================================================2s 615ms/步-损耗：0.6596-精度：0.6875-val_损耗：0.9326-val_精度：0.5000
纪元8/10
3/3[=====================================================================2s 604ms/步长-损耗：0.7022-精度：0.6458-val_损耗：0.6976-val_精度：0.5000
纪元9/10
3/3[=====================================================================2s 591ms/步长-损耗：0.6331-精度：0.7292-val_损耗：0.9571-val_精度：0.5000
纪元10/10
3/3[========================================================================2s 595ms/步-损耗：0.6085-精度：0.7292-val_损耗：0.6029-val_精度：0.5000
出[24]：

您正在设置每个历元的训练步骤=50//32=1。那么你只有50张训练图像吗？同样地，对于验证，步骤=8//32=0。您是否只有8个验证图像？当您执行程序时，培训和验证生成器会打印出他们找到的多少图像？你需要更多的图像。尝试将批处理大小设置为1

我有8500张培训图像和500张验证图像。步骤的值应该是什么作为起点？我不确定我是从哪里得到这个逻辑的，我一直在玩弄很多东西，试图弄清楚到底发生了什么。试试batch_size=50，steps per epoch=170，这样170 X 50=8500，你就可以每个epoch检查一次你的训练集。将验证批大小设置为50，步骤设置为10，以便每个历元检查一次验证集