conv1D中的形状尺寸

2024-09-25 00:22:41 发布

您现在位置:Python中文网/ 问答频道 /正文

我试着建立一个只有一层的CNN,但我有一些问题。 事实上,编者告诉我

ValueError: Error when checking model input: expected conv1d_1_input to have 3 dimensions, but got array with shape (569, 30)

这是密码

import numpy
from keras.models import Sequential
from keras.layers.convolutional import Conv1D
numpy.random.seed(7)
datasetTraining = numpy.loadtxt("CancerAdapter.csv",delimiter=",")
X = datasetTraining[:,1:31]
Y = datasetTraining[:,0]
datasetTesting = numpy.loadtxt("CancereEvaluation.csv",delimiter=",")
X_test = datasetTraining[:,1:31]
Y_test = datasetTraining[:,0]
model = Sequential()
model.add(Conv1D(2,2,activation='relu',input_shape=X.shape))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X, Y, epochs=150, batch_size=5)
scores = model.evaluate(X_test, Y_test)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

Tags: csvfromtestimportnumpyinputmodelkeras
3条回答

如果无法看到更多细节,则预处理后的数据形状不正确。
将X重塑为具有3个维度:

np.reshape(X, (1, X.shape[0], X.shape[1]))

我在其他帖子中也提到过:

要将形状(nrows, ncols)的常用特征表数据输入到路缘石的Conv1d,需要执行以下两个步骤:

xtrain.reshape(nrows, ncols, 1)
# For conv1d statement: 
input_shape = (ncols, 1)

例如,以iris数据集的前4个特征为例:

要查看常用格式及其形状:

iris_array = np.array(irisdf.iloc[:,:4].values)
print(iris_array[:5])
print(iris_array.shape)

输出显示常用格式及其形状:

[[5.1 3.5 1.4 0.2]
 [4.9 3.  1.4 0.2]
 [4.7 3.2 1.3 0.2]
 [4.6 3.1 1.5 0.2]
 [5.  3.6 1.4 0.2]]

(150, 4)

以下代码更改格式:

nrows, ncols = iris_array.shape
iris_array = iris_array.reshape(nrows, ncols, 1)
print(iris_array[:5])
print(iris_array.shape)

上述代码数据格式的输出及其形状:

[[[5.1]
  [3.5]
  [1.4]
  [0.2]]

 [[4.9]
  [3. ]
  [1.4]
  [0.2]]

 [[4.7]
  [3.2]
  [1.3]
  [0.2]]

 [[4.6]
  [3.1]
  [1.5]
  [0.2]]

 [[5. ]
  [3.6]
  [1.4]
  [0.2]]]

(150, 4, 1)

这对凯拉斯的Conv1d很有效。对于input_shape (4,1)是必需的。

td;lr您需要重塑数据的形状,使其具有空间维度,以便Conv1d有意义:

X = np.expand_dims(X, axis=2) # reshape (569, 30) to (569, 30, 1) 
# now input can be set as 
model.add(Conv1D(2,2,activation='relu',input_shape=(30, 1))

从本质上重塑数据集,如下所示:

features    
.8, .1, .3  
.2, .4, .6  
.7, .2, .1  

致:

[[.8
.1
.3],

[.2,
 .4,
 .6
 ],

[.3,
 .6
 .1]]

说明和示例

通常卷积作用于空间维度。内核在维度上“卷积”产生一个张量。在Conv1D的情况下,内核被传递到每个示例的“steps”维度上。

您将看到在NLP中使用的Conv1D,其中steps是句子中的单词数(填充到某个固定的最大长度)。这些单词可能被编码为长度为4的向量。

下面是一个例子:

jack   .1   .3   -.52   |
is     .05  .8,  -.7    |<--- kernel is `convolving` along this dimension.
a      .5   .31  -.2    |
boy    .5   .8   -.4   \|/

在这种情况下,我们设置conv输入的方式是:

maxlen = 4
input_dim = 3
model.add(Conv1D(2,2,activation='relu',input_shape=(maxlen, input_dim))

在您的例子中,您将把特征视为空间维度,每个特征的长度为1。(见下文)

下面是您的数据集中的一个示例

att1   .04    |
att2   .05    |  < -- kernel convolving along this dimension
att3   .1     |       notice the features have length 1. each
att4   .5    \|/      example have these 4 featues.

我们将Conv1D示例设置为:

maxlen = num_features = 4 # this would be 30 in your case
input_dim = 1 # since this is the length of _each_ feature (as shown above)

model.add(Conv1D(2,2,activation='relu',input_shape=(maxlen, input_dim))

正如您所看到的,您的数据集必须在(569,30,1)中重新调整 使用:

X = np.expand_dims(X, axis=2) # reshape (569, 30, 1) 
# now input can be set as 
model.add(Conv1D(2,2,activation='relu',input_shape=(30, 1))

下面是一个可以运行的完整示例(我将使用Functional API

from keras.models import Model
from keras.layers import Conv1D, Dense, MaxPool1D, Flatten, Input
import numpy as np

inp =  Input(shape=(5, 1))
conv = Conv1D(filters=2, kernel_size=2)(inp)
pool = MaxPool1D(pool_size=2)(conv)
flat = Flatten()(pool)
dense = Dense(1)(flat)
model = Model(inp, dense)
model.compile(loss='mse', optimizer='adam')

print(model.summary())

# get some data
X = np.expand_dims(np.random.randn(10, 5), axis=2)
y = np.random.randn(10, 1)

# fit model
model.fit(X, y)

相关问题 更多 >