Question

我正在构建一个简单的神经网络。数据是一个231长向量，是一个热编码的。每个231个长向量被分配一个8个长的热编码标签。

到目前为止，我的代码是：

ID           DATE         EVENT
300-1-003    2019-07-14   4
300-1-004    2019-10-27   1
300-1-004    2019-10-29   4
300-1-008    2019-10-11   4

问题是输出层是8个单位，但是我的标签不是单个单位，它们是8位长的矢量，是一个热编码的。如何将其表示为输出？

错误消息是：

ssdf = pd.read_csv("/some/path/to/1AMX_one_hot.csv", sep=',') ss = ssdf.iloc[:,3:11] # slice the df for the ss labels = ss.values # vector of all ss's labels = labels.astype('int32') # data onehot = ssdf.iloc[:,11:260] data = onehot.values data = data.astype('int32') model = tf.keras.Sequential() # Adds a densely-connected layer with 64 units to the model: model.add(layers.Dense(64, activation='relu')) # Add another: model.add(layers.Dense(64, activation='relu')) # Add a softmax layer with 8 output units: model.add(layers.Dense(8, activation='softmax')) model.compile(Adam(lr=.0001), loss='sparse_categorical_crossentropy', metrics=['accuracy'] ) ## fit the model model.fit(data, labels, epochs=10, batch_size=32)

完整追溯：

TypeError: Unable to build 'Dense' layer with non-floating point dtype <dtype: 'int32'>

Answer 1

示例代码中有几个问题：

您需要网络的输入层或输入形状。
将数据和标签为：astype(np.float32)

如果标签的形状为（150，8），则使最后一层带有8个神经元。

model.add(layers.Dense(8, activation='softmax'))
model.compile(Adam(lr=0.0001),
              loss='categorical_crossentropy',
              metrics=['accuracy'])

更新：

ssdf = pd.read_csv("/some/path/to/1AMX_one_hot.csv", sep=',')

ss = ssdf.iloc[:,3:11] # slice the df for the ss
labels = ss.values # vector of all ss's
labels = labels.astype('float32')                     # changed this
# data
onehot = ssdf.iloc[:,11:260]
data = onehot.values
data = data.astype('float32')                         # changed this

model = tf.keras.Sequential()
# Adds a densely-connected layer with 64 units to the model:
model.add(layers.Dense(64, activation='relu'))

# Add another:
model.add(layers.Dense(64, activation='relu'))

# Add a softmax layer with 8 output units:
model.add(layers.Dense(8, activation='softmax'))


model.compile(Adam(lr=.0001), 
          loss='categorical_crossentropy',            # changed this
          metrics=['accuracy']
)

## fit the model
model.fit(data, labels, epochs=10, batch_size=32)

Keras / Tensorflow中简单神经网络的错误

1 个答案: