如何解决tensorflow模型的未实现误差？

Question

    X_data = transformed_df["content"].str.lower()
    y_data = emotions_df

    topLayerModel = tf.keras.models.Sequential()
    topLayerModel.add(Dense(256, input_shape=(512,), activation='relu'))
    topLayerModel.add(Dense(256, input_shape=(256,), activation='relu'))
    topLayerModel.add(Dropout(0.5))
    topLayerModel.add(Dense(128, input_shape=(256,), activation='relu'))
    topLayerModel.add(Dense(4, activation='softmax'))  
    model.compile(optimizer=tf.optimizers.Adam(), metrics = ["accuracy"], loss =                 
    "categorical_crossentropy"),

    model.fit(X_data, y_data, epochs = 5)

我的错误可以在model.fit上找到，但我根本不知道如何解决转换。如何将字符串转换为浮点？我真的希望有人能帮我谢谢你

    Epoch 1/5
    ---------------------------------------------------------------------------
    UnimplementedError                        Traceback (most recent call last)
    <ipython-input-103-47abb3d08a2f> in <module>()
         29 model.compile(optimizer=tf.optimizers.Adam(), metrics = ["accuracy"], loss =         
    "categorical_crossentropy"),
         30 
    ---> 31 model.fit(X_data, y_data, epochs = 5)
         32 
         33 
    
    
    8 frames
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in                 
    quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
         58     ctx.ensure_initialized()
         59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
    ---> 60                                         inputs, attrs, num_outputs)
         61   except core._NotOkStatusException as e:
         62     if name is not None:
    
    UnimplementedError:  Cast string to float is not supported
         [[node sequential_4/dense_16/Cast (defined at <ipython-input-103-47abb3d08a2f>:31) ]]                 
    [Op:__inference_train_function_13983]
    
    Function call stack:
    train_function

请帮忙：（

Answer 1

当我想读取.csv文件时发生了这种情况，我读取了它并将其转换为str，但当我输入时它被解决了，因为它是没有转换

df = pd.read_csv("sqli.csv.csv", engine="python")
#df = df.astype(str)  <<  here the reason of code exception

因此，对于您来说，请尝试从X_数据中删除str

X_data = transformed_df["content"].lower()

如果内容包含符号，并且您需要让它保持原样，请同时删除lower()

X_data = transformed_df["content"]