构建神经网络 [TensorFlow 2.0] 模型子类化 - ValueError/TypeError

Question

我正在使用 TensorFlow 2.0 和 Python 3.7.5 来使用模型子分类方法构建用于虹膜分类的神经网络。

我的代码如下：

import tensorflow as tf
from tensorflow.keras import Sequential, Model
from tensorflow.keras.layers import Dense, Input
import pandas as pd
import numpy as np


# Read in data-
data = pd.read_csv("iris.csv")

# Get data types for different attributes-
data.dtypes
'''
sepallength    float64
sepalwidth     float64
petallength    float64
petalwidth     float64
class           object
dtype: object
'''


# Get shape of data-
data.shape
# (150, 5)


# Check for missing values-
data.isnull().values.any()
# False

# Perform label encoding for target variable-

# Initialize a label encoder-
le = LabelEncoder()

# Label encode target attribute-
data['class'] = le.fit_transform(data['class'])

# Get different classes which are label encoded-
le.classes_
# array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)

# Split data into features (X) and target (y)-
X = data.drop('class', axis = 1)
y = data['class']


# Get training & testing sets using features and labels-
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

# Convert from Pandas to numpy arrays-
X_train = X_train.to_numpy()
X_test = X_test.to_numpy()

y_train = y_train.to_numpy()
y_test = y_test.to_numpy()

print("\nTraining and Testing set dimensions:")
print("X_train.shape = {0}, y_train.shape = {1}".format(X_train.shape, y_train.shape))
print("X_test.shape = {0}, y_test.shape = {1}\n".format(X_test.shape, y_test.shape))
# Training and Testing set dimensions:
# X_train.shape = (105, 4), y_train.shape = (105,)
# X_test.shape = (45, 4), y_test.shape = (45,)



class IrisClassifier(Model):

    def __init__(self):
        super(IrisClassifier, self).__init__()

        '''
        self.layer1 = Dense(
            units = 4, activation = 'relu',
            kernel_initializer = tf.keras.initializers.GlorotNormal()
            )
        '''

        self.input_layer = Input(
            shape = (4,)
            )

        self.layer1 = Dense(
            units = 10, activation = 'relu',
            input_dim = 4,
            kernel_initializer = tf.keras.initializers.GlorotNormal()
            )

        self.layer2 = Dense(
            units = 10, activation = 'relu',
            kernel_initializer = tf.keras.initializers.GlorotNormal()
            )

        self.outputlayer = Dense(
            units = 3, activation = 'softmax'
            )


    def call(self, x):
        x = self.input_layer(x)
        x = self.layer1(x)
        x = self.layer2(x)
        # x = self.layer3(x)

        return self.outputlayer(x)


# Instantiate a model of defined neural network class-
model = IrisClassifier()

# Define EarlyStopping callback-
callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=3)

# Compile defined model-
model.compile(
    optimizer=tf.keras.optimizers.Adam(lr = 0.001),
    loss = 'sparse_categorical_crossentropy',
    metrics = ['accuracy']
     )


# Train model-
history2 = model.fit(
    x = X_train, y = y_train,
    validation_data = [X_test, y_test],
    epochs = 50, batch_size = 16,
    callbacks = [callback]
    )

当我执行“history2”代码时，出现以下错误：

----------------------------------- ---------------------------- ValueError Traceback（最近一次调用 最后）在 3 验证数据 = [X_test, y_test], 4 epochs = 50，batch_size = 16， ----> 5 个回调 = [回调] 6)

~/.local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split，validation_data，shuffle，class_weight， sample_weight，initial_epoch，steps_per_epoch，validation_steps， 验证频率，最大队列大小，工人，使用多处理， **kwargs） 第726章 727工人=工人， --> 728 使用_多处理=使用_多处理) 729 730 def 评估（自我，

~/.local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py 适合（自我，模型，x，y，batch_size，epochs，详细，回调， validation_split，validation_data，shuffle，class_weight， sample_weight，initial_epoch，steps_per_epoch，validation_steps， 验证频率，**kwargs） 640 步=steps_per_epoch, 第641章 --> 642 洗牌=洗牌） 643 第644章

~/.local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py 在 _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size、check_steps、steps_name、steps、validation_split、shuffle、 extract_tensors_from_dataset) 2417 # 首先，我们建立模型 如有必要，可即时进行。 2418 如果不是 self.inputs： -> 2419 all_inputs，y_input，dict_inputs = self._build_model_with_inputs（x，y）2420 is_build_call = 真 2421 其他：

~/.local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py 在 _build_model_with_inputs(self, inputs, targets) 2580 # 或 数组列表，并从传递的
中提取输入的平面列表 2581#结构。 -> 2582 training_utils.validate_input_types(inputs, orig_inputs) 2583 2584 if isinstance(inputs, (list, tuple)):

~/.local/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py 在 validate_input_types（inp，orig_inp，allow_dict，field_name）1149 raise ValueError( 1150 '请提供模型输入 单个数组或 ' 列表 -> 1151 '数组。你通过了：{}={}'.format(field_name, orig_inp)) 1152 1153

ValueError: 请提供单个数组或一个数组作为模型输入 数组列表。你通过了：输入= sepallength sepalwidth 花瓣长 花瓣宽 117 7.7 3.8 6.7
2.2 7 5.0 3.4 1.5 0.2 73 6.1 2.8 4.7 1.2 92 5.8 2.6 4.0 1.2 87 6.3 2.3 4.4 1.3 ... ... ... ... ... 93 5.0 2.3 3.3 1.0 30 4.8 3.1 1.6 0.2 25 5.0 3.0 1.6 0.2 31 5.4 3.4 1.5 0.4 97 6.2 2.9 4.3 1.3

[105 行 x 4 列]

将 X_train、y_train、X_test 和 y_test 转换为 numpy 数组后，当我执行 history2 来训练模型时，出现以下错误：

TypeError：在转换后的代码中：

<ipython-input-14-ae6111e00410>:34 call  *
    x = self.input_layer(x)
/home/arjun/.local/lib/python3.7/site-packages/tensorflow_core/python/autograph/impl/api.py:427

converted_call f in m.dict.values() for m in (collections, pdb, copy, inspect, re))： /home/arjun/.local/lib/python3.7/site-packages/tensorflow_core/python/autograph/impl/api.py:427 f in m.dict.values() for m in (collections, pdb, copy, inspect, re))： /home/arjun/.local/lib/python3.7/site-packages/tensorflow_core/python/ops/math_ops.py:1336 张量等于 return gen_math_ops.equal(self, other) /home/arjun/.local/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_math_ops.py:3627 平等的 名称=名称） /home/arjun/.local/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py:536 _apply_op_helper repr(values), type(values).name, err))

TypeError: Expected float32 passed to parameter 'y' of op 'Equal', got 'collections' of type 'str' instead. Error: Expected float32, got

改为“str”类型的“集合”。

怎么了？

谢谢！

Answer 1

我解决了这个问题。根据 Francois Chollet 的说法：

子类模型是一段 Python 代码（调用方法）。有 这里没有图层图。我们不知道层是如何连接的 彼此（因为这是在调用主体中定义的，而不是作为 显式数据结构），因此我们无法推断输入/输出形状

因此，以下代码运行良好（您未指定输入训练数据形状）：

# Define EarlyStopping callback-
callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=3)

class IrisClassifier(Model):

    def __init__(self):
        super(IrisClassifier, self).__init__()

        self.layer1 = Dense(
            units = 10, activation = 'relu',
            # input_dim = 4,
            kernel_initializer = tf.keras.initializers.GlorotNormal()
            )

        self.layer2 = Dense(
            units = 10, activation = 'relu',
            kernel_initializer = tf.keras.initializers.GlorotNormal()
            )

        self.outputlayer = Dense(
            units = 3, activation = 'softmax'
            )


    def call(self, x):
        # x = self.input_layer(x)
        x = self.layer1(x)
        x = self.layer2(x)
        # x = self.layer3(x)
        return self.outputlayer(x)


# Instantiate a model of defined neural network class-
model2 = IrisClassifier()


# Compile defined model-
model2.compile(
    optimizer=tf.keras.optimizers.Adam(lr = 0.001),
    loss = 'sparse_categorical_crossentropy',
    metrics = ['accuracy']
     )


# Train model-
history2 = model2.fit(
    x = X_train, y = y_train,
    validation_data = [X_test, y_test],
    epochs = 50, batch_size = 16,
    callbacks = [callback]
    )

谢谢！

Answer 2

您的问题源于您在将数据拟合到模型之前对数据进行预处理的方式。

很有可能您从 iris 传递了整个 csv 数据集，包括您的列标题，因此是您的问题。您可以从

验证这一点

"你通过了：inputs= sepallength sepalwidth petallength petalwidth 117 7.7 3.8 6.7"。

确保您的 Xs 和 ys 不包含列名，而只包含值。使用X_train = X_train.to_numpy() 确保转换正常。在旧版本中，您也可以使用X_train.values，但后者已被弃用。