我试图按照here的说明进行操作 它使用Reuter dataset。
from keras.datasets import reuters
(X_train, y_train), (X_test, y_test) = reuters.load_data(path="reuters.pkl",
nb_words=None,
skip_top=0,
maxlen=None,
test_split=0.1)
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(64, input_dim=20, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, init='uniform'))
model.add(Activation('tanh'))
model.add(Dropout(0.5))
model.add(Dense(10, init='uniform'))
model.add(Activation('softmax'))
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
#breaks here
model.fit(X_train, y_train,
nb_epoch=20,
batch_size=16)
score = model.evaluate(X_test, y_test, batch_size=16)
但是代码打破了模型拟合。我该如何解决这个问题？
更新：这是我收到的错误。
In [21]: model.fit(X_train, y_train,
....: nb_epoch=20,
....: batch_size=16)
---------------------------------------------------------------------------
Exception Traceback (most recent call last)
<ipython-input-21-4b227e56e5a9> in <module>()
1 model.fit(X_train, y_train,
2 nb_epoch=20,
----> 3 batch_size=16)
//anaconda/lib/python2.7/site-packages/keras/models.pyc in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, **kwargs)
400 shuffle=shuffle,
401 class_weight=class_weight,
--> 402 sample_weight=sample_weight)
403
404 def evaluate(self, x, y, batch_size=32, verbose=1,
//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight)
969 class_weight=class_weight,
970 check_batch_dim=False,
--> 971 batch_size=batch_size)
972 # prepare validation data
973 if validation_data:
//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_dim, batch_size)
909 in zip(y, sample_weights, class_weights, self.sample_weight_modes)]
910 check_array_lengths(x, y, sample_weights)
--> 911 check_loss_and_target_compatibility(y, self.loss_functions, self.internal_output_shapes)
912 if self.stateful and batch_size:
913 if x[0].shape[0] % batch_size != 0:
//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in check_loss_and_target_compatibility(targets, losses, output_shapes)
182 if y.shape[1] == 1:
183 raise Exception('You are passing a target array of shape ' + str(y.shape) +
--> 184 ' while using as loss `categorical_crossentropy`. '
185 '`categorical_crossentropy` expects '
186 'targets to be binary matrices (1s and 0s) '
Exception: You are passing a target array of shape (10105, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via:
```
from keras.utils.np_utils import to_categorical
y_binary = to_categorical(y_int)
```
Alternatively, you can use the loss function `sparse_categorical_crossentropy` instead, which does expect integer targets.
答案 0 :(得分：18)
这是一个非常常见的初学者与Keras的错误。与其他深度学习框架不同，Keras不使用整数标签来进行通常的交叉熵损失，而是期望一个二进制向量（称为“一热”），其中向量仅为0并且在右类的索引上为1。
您可以使用以下代码轻松将标签转换为此格式：
from keras.utils.np_utils import to_categorical
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
在model.fit之前。另一种方法是将损失更改为“sparse_categorical_crossentropy”，它确实需要整数标签。
答案 1 :(得分：0)
答案与目标的格式有关...您有两种可能：
1。可能性：如果您具有一维整数编码目标，则可以使用sparse_categorical_crossentropy作为损失函数
n_class = 3
n_features = 100
n_sample = 1000
X = np.random.randint(0,10, (n_sample,n_features))
y = np.random.randint(0,n_class, n_sample)
inp = Input((n_features,))
x = Dense(128, activation='relu')(inp)
out = Dense(n_class, activation='softmax')(x)
model = Model(inp, out)
model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
history = model.fit(X, y, epochs=3)
2。可能性：如果您已对目标进行一次热编码以使其具有2D形状（n_samples，n_class），则可以使用categorical_crossentropy作为损失
n_class = 3
n_features = 100
n_sample = 1000
X = np.random.randint(0,10, (n_sample,n_features))
y = pd.get_dummies(np.random.randint(0,n_class, n_sample)).values
inp = Input((n_features,))
x = Dense(128, activation='relu')(inp)
out = Dense(n_class, activation='softmax')(x)
model = Model(inp, out)
model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
history = model.fit(X, y, epochs=3)