卷积神经网络————经典vggnet(三)

2021-05-13 13:34:42 阅读：194 来源： 互联网

标签：loss val vggnet 卷积神经网络 train path model data

from tensorflow.keras.layers import Flatten,Dense,Dropout,Input
from tensorflow.keras.applications import VGG16
import matplotlib.pyplot as plt
from tensorflow.keras.models import Model
import csv
import os
import json
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import tensorflow as tf






base_model=VGG16(weights='imagenet',include_top=False,input_tensor=Input(shape=(224,224,3)))
#微调
head_model=base_model.output
head_model=Flatten(name="flatten")(head_model)
head_model = Dense(2048, activation="relu")(head_model)
head_model = Dropout(0.5)(head_model)
head_model=Dense(2048,activation='relu')(head_model)
head_model = Dense(5, activation="softmax")(head_model)
model=Model(base_model.input,head_model)
#冻结前面的5个卷积组，只训练自定义的全连接层
for layer in base_model.layers:
    layer.trainable=False

data_root = r"d:\下载的文件"
#data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
image_path = os.path.join(data_root, "flower_photos")  # flower data set path
train_dir = os.path.join(image_path, "train")
validation_dir = os.path.join(image_path, "val")
assert os.path.exists(train_dir), "cannot find {}".format(train_dir)
assert os.path.exists(validation_dir), "cannot find {}".format(validation_dir)


# create direction for saving weights
if not os.path.exists("save_weights_pre_train"):
    os.makedirs("save_weights_pre_train")

im_height = 224
im_width = 224
batch_size = 32
epochs = 2

_R_MEAN = 123.68
_G_MEAN = 116.78
_B_MEAN = 103.94

def pre_function(img):
    # img = im.open('test.jpg')
    # img = np.array(img).astype(np.float32)
    img = img - [_R_MEAN, _G_MEAN, _B_MEAN]

    return img

# data generator with data augmentation
train_image_generator = ImageDataGenerator(horizontal_flip=True,
                                           preprocessing_function=pre_function)
validation_image_generator = ImageDataGenerator(preprocessing_function=pre_function)

train_data_gen = train_image_generator.flow_from_directory(directory=train_dir,
                                                           batch_size=batch_size,
                                                           shuffle=True,
                                                           target_size=(im_height, im_width),
                                                           class_mode='categorical')
total_train = train_data_gen.n

# get class dict
class_indices = train_data_gen.class_indices

# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
    json_file.write(json_str)

val_data_gen = validation_image_generator.flow_from_directory(directory=validation_dir,
                                                              batch_size=batch_size,
                                                              shuffle=False,
                                                              target_size=(im_height, im_width),
                                                              class_mode='categorical')
total_val = val_data_gen.n
print("using {} images for training, {} images for validation.".format(total_train,
                                                                       total_val))

model.summary()

# using keras high level api for training
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001),
              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=False),
              metrics=["accuracy"])
checkpoint_save_path = "./save_weights_pre_train/myVGG16.ckpt"
callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                save_best_only=True,
                                                save_weights_only=True,
                                                monitor='val_loss')]

# tensorflow2.1 recommend to using fit
history = model.fit(x=train_data_gen,
                    steps_per_epoch=total_train // batch_size,
                    epochs=epochs,
                    validation_data=val_data_gen,
                    validation_steps=total_val // batch_size,
                    callbacks=callbacks)
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

file='./flower_history_pre_train.csv'

with open(file,'a',encoding='utf-8',newline='')as f:
    writer=csv.writer(f)
    writer.writerow(['acc','val_acc','loss','val_loss'])
    for i in range(len(acc)):
        writer.writerow([acc[i], val_acc[i], loss[i], val_loss[i]])





plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()

迁移学习的网络构造有点改变

标签：loss,val,vggnet,卷积,神经网络,train,path,model,data
来源： https://www.cnblogs.com/fengqing111/p/14764129.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9

卷积神经网络————经典vggnet(三)