我正在尝试使用 Conv2D 网络将图像分类为 27 个类。训练准确度按预期通过 epochs 上升，但 val_accuracy 和 val_loss 值波动剧烈且不够好。
我正在使用单独的数据集进行训练和验证。这些图像的大小为 256 x 256，并且是二进制阈值图像。
训练集中有 22127 张图像（每类约 800 张），验证集中有 11346 张图像（每类约 400 张），所以我相信没有类不平衡。
这是我的架构：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 126, 126, 32) 320
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 63, 63, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 61, 61, 32) 9248
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 30, 30, 32) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 28800) 0
_________________________________________________________________
dense_1 (Dense) (None, 128) 3686528
_________________________________________________________________
dropout_1 (Dropout) (None, 128) 0
_________________________________________________________________
dense_2 (Dense) (None, 96) 12384
_________________________________________________________________
dropout_2 (Dropout) (None, 96) 0
_________________________________________________________________
dense_3 (Dense) (None, 64) 6208
_________________________________________________________________
dense_4 (Dense) (None, 27) 1755
=================================================================
Total params: 3,716,443
Trainable params: 3,716,443
Non-trainable params: 0
Found 22127 images belonging to 27 classes.
Found 11346 images belonging to 27 classes.
这是我用来制作这个模型的代码：
classifier = Sequential()
classifier.add(Convolution2D(32, (3, 3), input_shape=(sz, sz, 1), activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2, 2)))
classifier.add(Convolution2D(32, (3, 3), activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2, 2)))
classifier.add(Flatten())
classifier.add(Dense(units=128,
activation='relu'))
classifier.add(Dropout(0.40))
classifier.add(Dense(units=96,
activation='relu'))
classifier.add(Dropout(0.40))
classifier.add(Dense(units=64,
activation='relu'))
classifier.add(Dense(units=27, activation='softmax'))
使用的优化器是 adam，我使用的损失函数是 categorical_crossentropy。
from keras import optimizers
opt = optimizers.Adam(learning_rate = 0.001)
classifier.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
classifier.summary()
这是将数据从目录流向模型的代码
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
training_set = train_datagen.flow_from_directory('Dataset2/Training Data',
target_size=(sz, sz),
batch_size=10,
color_mode='grayscale',
class_mode='categorical',
shuffle = True)
test_set = test_datagen.flow_from_directory('Dataset2/Test Data',
target_size=(sz , sz),
batch_size=10,
color_mode='grayscale',
class_mode='categorical',
#shuffle = True
)
classifier_obj = classifier.fit_generator(
training_set,
#steps_per_epoch=22127,
epochs=10,
validation_data=test_set,
#validation_steps=11346
verbose = 1)
此代码产生的输出是：
Epoch 1/10
2213/2213 [==============================] - 302s 136ms/step - loss: 0.0130 - accuracy: 0.7108 - val_loss: 0.0604 - val_accuracy: 0.3293
Epoch 2/10
2213/2213 [==============================] - 312s 141ms/step - loss: 0.0035 - accuracy: 0.9371 - val_loss: 0.0279 - val_accuracy: 0.4069
Epoch 3/10
2213/2213 [==============================] - 305s 138ms/step - loss: 0.0024 - accuracy: 0.9558 - val_loss: 0.0260 - val_accuracy: 0.4266
Epoch 4/10
2213/2213 [==============================] - 336s 152ms/step - loss: 0.0018 - accuracy: 0.9680 - val_loss: 0.0452 - val_accuracy: 0.4323
Epoch 5/10
2213/2213 [==============================] - 310s 140ms/step - loss: 0.0015 - accuracy: 0.9731 - val_loss: 0.0339 - val_accuracy: 0.3659
Epoch 6/10
2213/2213 [==============================] - 317s 143ms/step - loss: 0.0014 - accuracy: 0.9746 - val_loss: 0.0415 - val_accuracy: 0.4496
Epoch 7/10
2213/2213 [==============================] - 297s 134ms/step - loss: 0.0012 - accuracy: 0.9777 - val_loss: 0.0379 - val_accuracy: 0.4512
Epoch 8/10
2213/2213 [==============================] - 285s 129ms/step - loss: 0.0012 - accuracy: 0.9782 - val_loss: 0.0157 - val_accuracy: 0.4603
Epoch 9/10
2213/2213 [==============================] - 274s 124ms/step - loss: 0.0012 - accuracy: 0.9795 - val_loss: 0.0289 - val_accuracy: 0.4430
Epoch 10/10
2213/2213 [==============================] - 274s 124ms/step - loss: 9.1970e-04 - accuracy: 0.9837 - val_loss: 0.0459 - val_accuracy: 0.4800
Model Saved
Weights saved
看到有希望的结果，我增加了 epoch 的数量以期获得更高的 val_Accuracy，但结果是 val_accuracy 低于前一个。
我更改了一些参数，并在一夜之间运行了 100 个 epoch 的代码。这是输出：
我在其他答案中发现并尝试但失败的一些事情：
- 使用 SGD 优化器
- 使用正则化器
- 玩弄密集层中的单位数量。
根据其他答案，我认为要么我的模型过度拟合，要么数据不好。请帮助我，因为我完全一无所知。