如何解决keras高效网络导入和数据增强问题
我正在尝试使用带有数据增强的转移学习来训练模型。 我的图像数据是32 x 32 x 3,我想导入EfficientNet07,但是每次运行时
from tensorflow.keras.applications import EfficientNetB0
model = EfficientNetB0(weights='imagenet')
我收到错误消息:
ImportError: cannot import name 'EfficientNetB7' from 'tensorflow.keras.applications' (C:\Users\…..
我不情愿地回复到Resnet50,效果很好。但是我真的很想使用高效的网络。
第二,我希望在模型运行时使用keras.expermental.preprocessing层添加数据增强,但是我遇到了错误
from tensorflow.keras.layers.experimental import preprocessing
from tensorflow.keras.models import Sequential
from tensorflow.keras import layers
img_augmentation = Sequential(
[
preprocessing.RandomRotation(factor=0.15),preprocessing.RandomTranslation(height_factor=0.1,width_factor=0.1),preprocessing.RandomFlip(),preprocessing.RandomContrast(factor=0.1),],name="img_augmentation",)
AttributeError: module 'tensorflow.keras.layers.experimental.preprocessing' has no attribute 'RandomRotation'
我从https://keras.io/examples/vision/image_classification_efficientnet_fine_tuning/提取了所有这些代码
并且已经从上到下阅读了三次。我继续使用ImageDataGenerator并编写了这段代码
def choosen_args(args):
#this function is to randomly choose the augmentation techniques from the list available in keras
key_list = []
arg_list = list(args.keys())
for i in range(len(arg_list)):
if np.random.randint(2) == 0:
pass
else:
key_list.append(arg_list[i])
arg_dict = dict((k,args[k]) for k in key_list)
return arg_dict
#这是我正在使用的所有扩充的列表-但只有少数几个会被选中进行最终转换
args = dict(
rotation_range = 120,width_shift_range=0.4,height_shift_range=0.4,shear_range=0.2,zoom_range=0.2,fill_mode ='nearest',zca_whitening=True,zca_epsilon=1e-06,brightness_range=(9.0,46.0),channel_shift_range=60.0,horizontal_flip=True,vertical_flip=True,rescale=random.randint(1,11))
data_augmentation_train = ImageDataGenerator( choosen_args(args) )
data_augmentation_validation = ImageDataGenerator( choosen_args(args) )
data_augmentation_train.fit(x_train,augment = True)
data_augmentation_validation.fit(x_test,augment = True)
请帮助:
- 如何获得有效的net07并使用其权重进行转移学习
- 我使用的数据增强代码-如何可视化它的作用-即转换图像
- 有没有更简单的方法来进行数据扩充-如何解决导入和属性错误
- 将数据放入生成器中之后-如何将其与其余的学习学习代码一起使用。
base_model = tf.keras.applications.ResNet50(weights ='imagenet',
include_top = False,input_shape = input_size)
> x_train = tf.keras.applications.resnet50.preprocess_input(x_train)
> x_test = tf.keras.applications.resnet50.preprocess_input(x_test)
> base_model.trainable = False
inputs = keras.Input(shape=(32,32,3)) model = base_model_ResNet50(inputs,training=False) model = keras.layers.GlobalAveragePooling2D()(model ) model= keras.layers.Flatten()(model) model = keras.layers.Dropout(0.2)(model) output = layers.Dense(100,activation="softmax")(model) history = model.fit(data_augmentation_train.flow (x_train,labels_train,batch_size = 64),validation_data =
data_augmentation_validation.flow(x_test,labels_test))
谢谢
解决方法
尝试以方式导入:
from keras_efficientnets import EfficientNetB0
model = EfficientNetB0(weights='imagenet')
,
首先安装高效网络模块:
public class Test {
public static void main(String[] args) {
String[] datas = Test.changeToArray("apple");
for (String data : datas) {
System.out.println(data);
}
Boolean[] bools = Test.changeToArray(true);
for (Boolean bool : bools) {
System.out.println(bool);
}
}
public static <T> T[] changeToArray(T data) {
// i want this..
// but this is compile error
// Cannot create a generic array of T
T[] datas = new T[] {data};
return datas;
}
}
然后将其导入为:
!pip install -U efficientnet
创建模型:
import efficientnet.keras as effnet