InceptionResNetV2验证精度保持在20%到30%之间。

Question

我试着训练CNN对9类图像进行分类。每堂课都有1000个图像供训练。我尝试了在VGG16和VGG19上进行训练，两者都能达到90%的验证精度。但当我试图对InceptionResNetV2模型进行培训时，这个模型似乎停留在20%和30%左右。下面是我的InceptionResNetV2和培训代码。我能做些什么来改善训练呢？

base_model = tf.keras.applications.InceptionResNetV2(input_shape=(IMG_HEIGHT, IMG_WIDTH ,3),weights = 'imagenet',include_top=False)
base_model.trainable = False

model = tf.keras.Sequential([
base_model,
Flatten(),
Dense(1024, activation = 'relu', kernel_regularizer=regularizers.l2(0.001)),
LeakyReLU(alpha=0.4),
Dropout(0.5),
BatchNormalization(),
Dense(1024, activation = 'relu', kernel_regularizer=regularizers.l2(0.001)),
LeakyReLU(alpha=0.4),
Dense(9, activation = 'softmax')])

optimizer_model = tf.keras.optimizers.Adam(learning_rate=0.0001, name='Adam', decay=0.00001)
loss_model = tf.keras.losses.CategoricalCrossentropy(from_logits=True)
model.compile(optimizer_model, loss="categorical_crossentropy", metrics=['accuracy'])

Epoch 1/10
899/899 [==============================] - 255s 283ms/step - loss: 4.3396 - acc: 0.3548 - val_loss: 4.2744 - val_acc: 0.3874
Epoch 2/10
899/899 [==============================] - 231s 257ms/step - loss: 3.5856 - acc: 0.4695 - val_loss: 3.9151 - val_acc: 0.3816
Epoch 3/10
899/899 [==============================] - 225s 250ms/step - loss: 3.1451 - acc: 0.4959 - val_loss: 4.8801 - val_acc: 0.2425
Epoch 4/10
899/899 [==============================] - 227s 252ms/step - loss: 2.7771 - acc: 0.5124 - val_loss: 3.7167 - val_acc: 0.3023
Epoch 5/10
899/899 [==============================] - 231s 257ms/step - loss: 2.4993 - acc: 0.5260 - val_loss: 3.7276 - val_acc: 0.3770
Epoch 6/10
899/899 [==============================] - 227s 252ms/step - loss: 2.3148 - acc: 0.5251 - val_loss: 3.7677 - val_acc: 0.3115
Epoch 7/10
899/899 [==============================] - 234s 260ms/step - loss: 2.1381 - acc: 0.5379 - val_loss: 3.4867 - val_acc: 0.2862
Epoch 8/10
899/899 [==============================] - 230s 256ms/step - loss: 2.0091 - acc: 0.5367 - val_loss: 4.1032 - val_acc: 0.3080
Epoch 9/10
899/899 [==============================] - 225s 251ms/step - loss: 1.9155 - acc: 0.5399 - val_loss: 4.1270 - val_acc: 0.2954
Epoch 10/10
899/899 [==============================] - 232s 258ms/step - loss: 1.8349 - acc: 0.5508 - val_loss: 4.3918 - val_acc: 0.2276

Answer 1

VGG-16/19的深度为23/26层，而InceptionResNetV2的深度为572层。现在，医学图像和imagenet数据集之间的领域相似性最小。在VGG中，由于深度较低，所获得的特征并不复杂，而且网络能够根据密集的层特征对其进行分类。然而，在IRV2网络中，由于它太深了，fc层的输出更加复杂(将其可视化为对象，而不是imagenet数据集)，然后，从这些层获得的特性无法连接到密集层特征，因此过于合适。我想你能理解我的观点。

看看我对这个链接上非常相似的问题的答案：Link。这将有助于提高你的准确性。