这是我做的。我得到了狗/猫图像分类的代码,我编译并运行了80%的准确性。我添加了一个班级(飞机)文件夹到火车和验证文件夹。在下面的代码如何在keras中进行多级图像分类?
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical')
所做的变更binary class_mode
到categorical
也损失categorical_crossentropy
。还将输出布局sigmoid
更改为softmax
。 收到以下错误。
ValueError: Error when checking target: expected activation_10 to have shape (None, 1) but got array with shape (16, 3)
我是否需要明确地将训练标签更改为如下所述的分类?
train_labels = to_categorical(train_labels, num_classes=num_classes)
(我从网站multilabel classification using keras阅读),我不知道这里发生了什么。请帮忙。我对深度学习比较陌生。
模型
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
请分享您的模型,以及您的标签数据结构('y_test') - 它是一个整数(0/1/2)还是一个热点编码矢量('[0.0,0.0,1.0] ')? – desertnaut
#我们图像的维度。 img_width,IMG_HEIGHT = 150,150 train_data_dir = '/家/埃德/ DC /火车' validation_data_dir = '/家/埃德/ DC /验证' nb_train_samples = 2011 nb_validation_samples = 813个 历元= 3 的batch_size = 16 如果K.image_data_format()== 'channels_first': input_shape =(3,img_width,IMG_HEIGHT) 其他: input_shape =(img_width,IMG_HEIGHT,3) 模式=连续() –
根本不是我问 - 请再次检查我的问题;以及我们应该如何处理系统本地的目录路径?此外,评论并非适合这类信息的地方 - 如果需要,您应该编辑并更新您的帖子 – desertnaut