Python 检查目标时出错:稀疏\u分类\u交叉熵输出形状
我正在尝试使用迁移学习在一组新颖的图像上训练InceptionV3。我遇到了这个问题——这显然与输入和输出维度的不匹配有关(我认为),但我似乎无法确定这个问题)。之前所有关于SO的相关帖子都与VGG16相关(我已经开始工作了)。 这是我的密码:Python 检查目标时出错:稀疏\u分类\u交叉熵输出形状,python,deep-learning,keras,cross-entropy,Python,Deep Learning,Keras,Cross Entropy,我正在尝试使用迁移学习在一组新颖的图像上训练InceptionV3。我遇到了这个问题——这显然与输入和输出维度的不匹配有关(我认为),但我似乎无法确定这个问题)。之前所有关于SO的相关帖子都与VGG16相关(我已经开始工作了)。 这是我的密码: from keras.applications.inception_v3 import InceptionV3 from keras.models import Model from keras.layers import Dense, Globa
from keras.applications.inception_v3 import InceptionV3
from keras.models import Model
from keras.layers import Dense, GlobalAveragePooling2D
from keras.callbacks import ModelCheckpoint, TensorBoard, CSVLogger, Callback
from keras.optimizers import SGD
from keras.preprocessing.image import ImageDataGenerator
base_model = InceptionV3(weights='imagenet', include_top=False)
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(3, activation='softmax')(x)
model = Model(inputs=base_model.input, output=predictions)
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer=SGD(lr=0.001, momentum=0.9), loss='sparse_categorical_crossentropy')
train_dir = 'hrct_data/ExtractedHRCTs/Train'
validation_dir = 'hrct_data/ExtractedHRCTs/Validation'
nb_train_samples = 21903
nb_validation_samples = 6000
epochs = 30
batch_size = 256
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
validation_datagen = ImageDataGenerator(
rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(512, 512),
batch_size=batch_size,
class_mode="categorical")
validation_generator = validation_datagen.flow_from_directory(
validation_dir,
target_size=(512, 512),
batch_size=batch_size,
class_mode="categorical")
model.fit_generator(
train_generator,
steps_per_epoch=21903 // batch_size,
epochs=30,
validation_data=validation_generator,
validation_steps=6000 // batch_size)
model.save_weights('hrct_inception.h5')
下面是错误:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-89-f79a107413cd> in <module>()
4 epochs=30,
5 validation_data=validation_generator,
6 validation_steps=6000 // batch_size)
7 model.save_weights('hrct_inception.h5')
/Users/simonalice/anaconda/lib/python3.5/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
86 warnings.warn('Update your `' + object_name +
87 '` call to the Keras 2 API: ' + signature, stacklevel=2)
88 return func(*args, **kwargs)
89 wrapper._legacy_support_signature = inspect.getargspec(func)
90 return wrapper
/Users/simonalice/anaconda/lib/python3.5/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_q_size, workers, pickle_safe, initial_epoch)
1888 outs = self.train_on_batch(x, y,
1889
sample_weight=sample_weight,
1890 class_weight=class_weight)
1891
1892 if not isinstance(outs, list):
/Users/simonalice/anaconda/lib/python3.5/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1625 sample_weight=sample_weight,
1626 class_weight=class_weight,
1627 check_batch_axis=True)
1628 if self.uses_learning_phase and not
isinstance(K.learning_phase(), int):
1629 ins = x + y + sample_weights + [1.]
/Users/simonalice/anaconda/lib/python3.5/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
1307 output_shapes,
1308 check_batch_axis=False,
1309 exception_prefix='target')
1310 sample_weights = _standardize_sample_weights(sample_weight,
1311 self._feed_output_names)
/Users/simonalice/anaconda/lib/python3.5/site-packages/keras/engine/training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
137 ' to have shape ' + str(shapes[i]) +
138 ' but got array with shape ' +
139 str(array.shape))
140 return arrays
141
ValueError: Error when checking target: expected dense_12 to have shape (None, 1) but got array with shape (256, 3)
---------------------------------------------------------------------------
ValueError回溯(最近一次调用上次)
在()
4个时代=30,
5验证数据=验证生成器,
6个验证步骤=6000//批量大小)
7型号。保存重量('hrct_inception.h5')
/包装器中的Users/simonance/anaconda/lib/python3.5/site-packages/keras/legacy/interfaces.py(*args,**kwargs)
86警告。警告('更新您的`+对象\u名称+
87'`对Keras 2 API的调用:'+签名,stacklevel=2)
88返回函数(*args,**kwargs)
89包装器。_legacy_support_signature=inspect.getargspec(func)
90返回包装器
/用户/Simonance/anaconda/lib/python3.5/site-packages/keras/engine/training.py-in-fit\u生成器(self、生成器、每个历元的步骤、历元、冗余、回调、验证数据、验证步骤、类权重、最大大小、工人、pickle\u-safe、初始历元)
1888 outs=批量(x,y,
1889
样品重量=样品重量,
1890级重量=级重量)
1891
1892如果不存在(输出,列表):
/用户/Simonance/anaconda/lib/python3.5/site-packages/keras/engine/training.py批量生产(自身、x、y、样品重量、等级重量)
1625样品重量=样品重量,
1626等级重量=等级重量,
1627检查(批次轴=真)
1628如果self.used\u learning\u阶段
isinstance(K.learning_phase(),int):
1629英寸=x+y+样本重量+1。]
/用户/Simonance/anaconda/lib/python3.5/site-packages/keras/engine/training.py标准化用户数据(自身、x、y、样本重量、类别重量、检查批次轴、批次大小)
1307个输出_形,
1308检查批次轴=错误,
1309异常(前缀=”目标“)
1310样本权重=\u标准化样本权重(样本权重,
1311自身(输入输出名称)
/用户/Simonance/anaconda/lib/python3.5/site-packages/keras/engine/training.py输入数据(数据、名称、形状、检查批处理轴、异常前缀)
137'具有形状'+str(形状[i])+
138'但有形状的数组'+
139 str(数组形状))
140返回阵列
141
ValueError:检查目标时出错:预期密集_12具有形状(无,1),但获得具有形状(256,3)的数组
任何帮助——即使是让我走上正确的方向,都会有所帮助 我相信这个错误是因为您使用了
sparse\u category\u crossentropy
这种丢失是将您在训练期间馈送的目标(“y”)自动编码为一个热编码目标。因此,它期望的目标是shape(256,1)
,其中您只提供索引
数据生成器提供的内容已经编码为类。所以你把(256,3)
作为目标。。。因此出现了错误:
若要修复此问题,请尝试使用“categorical\u crossentropy
”作为损失函数。这一个期望的是生成器给出的热编码向量
我希望这有帮助:-)请内联发布代码和错误,而不是作为截图发布。这使得帮助您变得非常麻烦。这里是……这里是解决方案:
ValueError: Error when checking target: expected dense_12 to have shape (None, 1) but got array with shape (256, 3)