Tensorflow CNN 迁移学习的验证精度持续较低

Question

您好，我一直在尝试创建两个张量流模型来实验迁移学习。我使用 kaggle 胸部 X 射线数据集。

这是我的代码

import tensorflow as tf

import numpy as np

from tensorflow import keras

import os

from tensorflow.keras.preprocessing.image import ImageDataGenerator

from tensorflow.keras.preprocessing import image

import matplotlib.pyplot as plt

gen = ImageDataGenerator(rescale=1./255)

train_data = gen.flow_from_directory("/Users/saibalaji/Downloads/chest_xray/train",target_size=(500,500),batch_size=32,class_mode='binary')

test_data = gen.flow_from_directory("/Users/saibalaji/Downloads/chest_xray/test",target_size=(500,500),batch_size=32,class_mode='binary')


model = keras.Sequential()


# Convolutional layer and maxpool layer 1

model.add(keras.layers.Conv2D(32,(3,3),activation='relu',input_shape=(500,500,3)))

model.add(keras.layers.MaxPool2D(2,2))


# Convolutional layer and maxpool layer 2

model.add(keras.layers.Conv2D(64,(3,3),activation='relu'))

model.add(keras.layers.MaxPool2D(2,2))


# Convolutional layer and maxpool layer 3

model.add(keras.layers.Conv2D(128,(3,3),activation='relu'))

model.add(keras.layers.MaxPool2D(2,2))


# Convolutional layer and maxpool layer 4

model.add(keras.layers.Conv2D(128,(3,3),activation='relu'))

model.add(keras.layers.MaxPool2D(2,2))


# This layer flattens the resulting image array to 1D array

model.add(keras.layers.Flatten())


# Hidden layer with 512 neurons and Rectified Linear Unit activation function

model.add(keras.layers.Dense(512,activation='relu'))


# Output layer with single neuron which gives 0 for Cat or 1 for Dog

#Here we use sigmoid activation function which makes our model output to lie between 0 and 1
model.add(keras.layers.Dense(1,activation='sigmoid'))

hist = model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])

model.fit_generator(train_data,
steps_per_epoch = 163,
epochs = 4,
validation_data = test_data
)

，我已将模型保存为 .h5 格式。

然后我创建了一个新的笔记本，从 Kaggle 加载 阿尔茨海默病的数据疾病并加载了我保存的肺炎模型。将其层复制到新模型（除了最后一层），然后将新模型中的所有层冻结为不可训练。然后添加一个具有 4 个神经元、4 个类别的输出密集层。然后只训练最后一层 5 epoch。但问题是 val 准确度始终保持在 35%。我该如何改进它。

这是我的阿尔茨默斯模型代码

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras.preprocessing.image import ImageDataGenerator

from tensorflow.keras.preprocessing import image

import matplotlib.pyplot as plt

import numpy as np

gen = ImageDataGenerator(rescale=1./255)

traindata = datagen.flow_from_directory('/Users/saibalaji/Documents/TensorFlowProjects/ad/train',target_size=(500,500),batch_size=32)

testdata = datagen.flow_from_directory('/Users/saibalaji/Documents/TensorFlowProjects/ad/test',target_size=(500,500),batch_size=32)

model = keras.models.load_model('pn.h5')

nmodel = keras.models.Sequential()

#add all layers except last one

for layer in model.layers[0:-1]:

nmodel.add(layer)

for layer in nmodel.layers:

layer.trainable = False

nmodel.add(keras.layers.Dense(units=4,name='dense_last'))

hist = nmodel.compile(optimizer = tf.keras.optimizers.Adam(learning_rate=0.002),loss = 'categorical_crossentropy', metrics = ['accuracy'])

nmodel.fit(x=traindata,validation_data=testdata,epochs=5,steps_per_epoch=160)

这是我的预测代码。

 class_labels = []
    for class_label,class_mode in traindata.class_indices.items():
        print(class_label)
        class_labels.append(class_label)
    def predictimage(filepath):
        test_image = image.load_img(path=filepath,target_size=(500,500))
        image_array = image.img_to_array(test_image)
        image_array = image_array / 255
        print(image_array.shape)
        image_array_exp = np.expand_dims(image_array,axis=0)
        result = nmodel.predict(image_array_exp)
        print(result)
        plt.imshow(test_image)
        plt.xlabel(class_labels[np.argmax(result)])

我还注意到，即使我将最后一层更改为 4 个神经元，并更改了损失函数，它也仅预测两个类别。

Answer 1

看来您没有在上一层添加激活功能。
使用softmax激活功能也许会有所帮助。

nmodel.add(keras.layers.Dense(units=4, activation= "softmax", name='dense_last'))