Tensorflow 如何克服错误的维度问题
我在做“Iris数据集上的模型验证”的作业 我得到了这个错误：“检查输入时出错：预期密集_输入具有形状（135），但得到了具有形状（4，）的数组”。我如何克服这个问题 我的代码是Tensorflow 如何克服错误的维度问题,tensorflow,tensorflow2.0,tensorflow-datasets,Tensorflow,Tensorflow2.0,Tensorflow Datasets,我在做“Iris数据集上的模型验证”的作业 我得到了这个错误：“检查输入时出错：预期密集_输入具有形状（135），但得到了具有形状（4，）的数组”。我如何克服这个问题 我的代码是 from numpy.random import seed seed(8) import tensorflow as tf import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, model_selection
from numpy.random import seed
seed(8)
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets, model_selection
from sklearn.model_selection import train_test_split
%matplotlib inline
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D
def read_in_and_split_data(iris_data):
data=iris_data["data"]
targets=iris_data["target"]
train_data, test_data, train_targets, test_targets= train_test_split(data,targets,test_size=0.1)
return(train_data, test_data, train_targets, test_targets)
iris_data = datasets.load_iris()
train_data, test_data, train_targets, test_targets = read_in_and_split_data(iris_data)
train_targets = tf.keras.utils.to_categorical(np.array(train_targets))
test_targets = tf.keras.utils.to_categorical(np.array(test_targets))
def get_model(input_shape):
model= Sequential ([
Dense(64, kernel_initializer='he_uniform',bias_initializer='ones', input_shape=(train_data.shape[0],)),
Dense(128, activation= "relu"),
Dense(128, activation= "relu"),
Dense(128, activation= "relu"),
Dense(128, activation= "relu"),
Dense(64, activation= "relu"),
Dense(64, activation= "relu"),
Dense(64, activation= "relu"),
Dense(64, activation= "relu"),
Dense(3, activation= 'softmax')
])
return model
model = get_model(train_data[0].shape)
def compile_model(model):
opt= tf.keras.optimizers.Adam(learning_rate=0.0001)
acc= tf.keras.metrics.SparseCategoricalAccuracy()
mae= tf.keras.metrics.MeanAbsoluteError()
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
compile_model(model)
def train_model(model, train_data, train_targets, epochs):
return model.fit(train_data, train_targets, epochs=epochs, validation_split= 0.15, batch_size=40)
history = train_model(model, train_data, train_targets, epochs=800)
ValueError Traceback (most recent call last)
<ipython-input-20-96db4320a1b9> in <module>
1 # Run your function to train the model
2
----> 3 history = train_model(model, train_data, train_targets, epochs=800)
<ipython-input-19-ce18af880dd7> in train_model(model, train_data, train_targets, epochs)
11 """
12
---> 13 return model.fit(train_data, train_targets, epochs=epochs, validation_split= 0.15,
batch_size=40)
14
15
/opt/conda/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, validation_freq,
max_queue_size, workers, use_multiprocessing, **kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in
fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data,
shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps,
validation_freq, **kwargs)
222 validation_data=validation_data,
223 validation_steps=validation_steps,
--> 224 distribution_strategy=strategy)
225
226 total_samples = _get_total_number_of_samples(training_data_adapter)
/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in _
process_training_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights,
steps_per_epoch, validation_split, validation_data, validation_steps, shuffle,
distribution_strategy, max_queue_size, workers, use_multiprocessing)
514 batch_size=batch_size,
515 check_steps=False,
--> 516 steps=steps_per_epoch)
517 (x, y, sample_weights,
518 val_x, val_y,
/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py in _
standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name,
steps, validation_split, shuffle, extract_tensors_from_dataset)
2470 feed_input_shapes,
2471 check_batch_axis=False, # Don't enforce the batch size.
-> 2472 exception_prefix='input')
2473
2474 # Get typespecs for the input data and sanitize it if necessary.
/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py in
standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
572 ': expected ' + names[i] + ' to have shape ' +
573 str(shape) + ' but got array with shape ' +
--> 574 str(data_shape))
575 return data
576
ValueError: Error when checking input: expected dense_input to have shape (135,) but got array with
shape (4,)
ValueError回溯（最近一次调用）
在里面
1#运行您的函数来训练模型
2.
---->3历史=列车模型（模型、列车数据、列车目标、历次=800）
列车内模型（模型、列车数据、列车目标、年代）
11 """
12
--->13返回模型拟合（序列数据，序列目标，历元=历元，验证分割=0.15，
批次（单位尺寸=40）
14
15
/opt/conda/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py in fit（self，
x、 y、批量大小、年代、详细信息、回调、验证拆分、验证数据、洗牌、，
类别权重、样本权重、初始历元、每历元步长、验证步长、验证频率、，
最大队列大小，工人，使用多处理，**kwargs）
726最大队列大小=最大队列大小，
727名工人=工人，
-->728使用多处理=使用多处理）
729
730 def评估（自我，
/opt/conda/lib/python3.7/site-packages/tensorflow\u core/python/keras/engine/training\u v2.py in
拟合（自我、模型、x、y、批量大小、年代、详细、回调、验证拆分、验证数据、，
洗牌、等级权重、样本权重、初始历元、每历元步骤、验证步骤、，
验证频率，**kwargs）
222验证数据=验证数据，
223验证步骤=验证步骤，
-->224分销（策略=策略）
225
226总样本数=\u获取\u总样本数\u（训练\u数据\u适配器）
/opt/conda/lib/python3.7/site-packages/tensorflow\u core/python/keras/engine/training\u v2.py in\u
过程训练输入（模型、x、y、批量、年代、样本权重、类别权重、，
每个历元的步骤、验证分割、验证数据、验证步骤、洗牌、，
分布策略、最大队列大小、工人、使用（多处理）
514批次大小=批次大小，
515检查步骤=错误，
-->516步=每一个历元的步数）
517（x，y，样本重量，
518瓦卢x，瓦卢y，
/opt/conda/lib/python3.7/site-packages/tensorflow\u core/python/keras/engine/training.py in\u
标准化用户数据（自身、x、y、样本重量、类别重量、批次大小、检查步骤、步骤名称、，
步骤、验证（拆分、洗牌、从数据集中提取张量）
2470个进纸输入形状，
2471检查_batch_axis=False，#不强制执行批大小。
->2472异常（前缀为“输入”）
2473
2474#获取输入数据的类型规范，必要时对其进行清理。
/opt/conda/lib/python3.7/site-packages/tensorflow\u core/python/keras/engine/training\u utils.py in
标准化输入数据（数据、名称、形状、检查批处理轴、异常前缀）
572'：预期“+名称[i]+”具有形状”+
573 str（shape）+“但是得到了具有shape的数组”+
-->574 str（数据形状））
575返回数据
576
ValueError：检查输入时出错：预期密集_输入具有形状（135，），但获得具有
形状（4，）
请原谅我询问此消息。我还是一个新手，tensorflow 2.0对我来说是全新的。我在这里和那里都会犯错误。但我在此祝大家圣诞快乐。错误表明您的输入数据形状与模型的输入形状不兼容。您需要检查您的train\u数据形状：
print(train_data.shape)