深度学习模型: ValueError:带基10：'php‘的int()无效文本

Question

我正在努力深入学习预测标签(c，php，.)堆叠溢出柱。然而，当我试图适应我的模型，我有很多错误的形状，我的训练集。在纠正这些错误后，我收到了一个新的错误，我不知道如何纠正它。如果你能帮我纠正它，因为我是新的深入学习模式，这将是真的很好的你！

我的代码：

model = Sequential()

model.add(Dense(16,activation='relu',input_shape = (384,))) #hidden
model.add(Dense(len(data.tag_name.unique()),activation='sigmoid')) #output

model.compile(optimizer='SGD',loss='binary_crossentropy',metrics=['accuracy'])
model.fit(np.array(list_embedding),tf.one_hot(np.array(data.tag_name).reshape([2686,1]),depth=len(data.tag_name.unique())),validation_data=0.3,epochs=20)

X_train：火车 y_train：火车

错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-20-3fddbbfa9112> in <module>
     10 
     11 model.compile(optimizer='SGD',loss='binary_crossentropy',metrics=['accuracy'])
---> 12 model.fit(np.array(list_embedding),tf.one_hot(np.array(data.tag_name).reshape([2686,1]),depth=len(data.tag_name.unique())),validation_data=0.3,epochs=20) #reshape y one hot encoding dummies

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
    204     """Call target, and fall back on dispatchers if there is a TypeError."""
    205     try:
--> 206       return target(*args, **kwargs)
    207     except (TypeError, ValueError):
    208       # Note: convert_to_eager_tensor currently raises a ValueError, not a

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py in one_hot(indices, depth, on_value, off_value, axis, dtype, name)
   4347                       "dtype {1} of off_value".format(on_dtype, off_dtype))
   4348 
-> 4349     return gen_array_ops.one_hot(indices, depth, on_value, off_value, axis,
   4350                                  name)
   4351 

/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/ops/gen_array_ops.py in one_hot(indices, depth, on_value, off_value, axis, name)
   6232   if tld.is_eager:
   6233     try:
-> 6234       _result = pywrap_tfe.TFE_Py_FastPathExecute(
   6235         _ctx, "OneHot", name, indices, depth, on_value, off_value, "axis",
   6236         axis)

ValueError: invalid literal for int() with base 10: 'php'

Answer 1

使用LabelEncoder对标签进行编码

from sklearn import preprocessing
labelencode = preprocessing.LabelEncoder()

labelencode.fit(["php", "c#", "c++", "python"])

y_train = labelencode.transform(["python", "php", "python"])

输出

array([3, 2, 3])

还请看一下类似的问题https://stackoverflow.com/a/62760616/14290244