ValueError: invalid literal for float() Keras

Question

我正在使用 keras 构建一个简单的神经网络。

训练数据的每个元素都有 100 个维度，我正在从文本文件中读取元素的标签。

f = open('maleE', "rt")
labelsTrain = [line.rstrip() for line in f.readlines()]
f.close()

标签是具有以下结构的字符串：number_text

要在训练数据上拟合模型：

model.fit(train, labelsTrain, epochs= 20000, batch_size= 1350)

我收到以下错误：

File "DNN.py", line 112, in <module>
    model.fit(train, labelsTrain, epochs=20000, batch_size=1350)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/keras/models.py", line 867, in fit
    initial_epoch=initial_epoch)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/keras/engine/training.py", line 1598, in fit
    validation_steps=validation_steps)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/keras/engine/training.py", line 1183, in _fit_loop
    outs = f(ins_batch)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2273, in __call__
    **self.session_kwargs)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
    run_metadata_ptr)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1087, in _run
    np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
  File "/Users/renzo/PyEnvironments/tensorKeras/lib/python2.7/site-packages/numpy/core/numeric.py", line 531, in asarray
    return array(a, dtype, copy=False, order=order)
ValueError: invalid literal for float(): 225_sokode

标签是 378 个标签列表中的元素 279。

Answer 1

首先，为每个 classes 选择一个唯一的名称。我这样说是因为我不明白你的 class 标签中的 number 是什么（如果每个 class 都不相同，请使用 str.split() to just keep the text). Then you should encode your string labels. For example, see this post 进行单热编码标签数量。

ValueError: invalid literal for float() Keras

ValueError: invalid literal for float() Keras

python

neural-network

model-fitting

keras

tensorflow