conv1D中的形状尺寸

Question

我试图用一层构建一个CNN,但我有一些问题.确实,编译器说我

ValueError:检查模型输入时出错:预期conv1d_1_input具有3个维度,但是具有形状的数组(569,30)

这是代码

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))

Answer 1

TD; LR你需要重塑你的数据有一个空间的尺寸Conv1d是有道理的:

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))

基本上重塑一个如下所示的数据集:

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

至:

[[.8
.1
.3],

[.2,
 .4,
 .6
 ],

[.3,
 .6
 .1]]

说明和例子

通常,卷积在空间维度上起作用.内核在产生张量的维度上"卷积".在Conv1D的情况下,内核通过每个示例的"步骤"维度传递.

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.

这是一个例句:

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

在这种情况下我们将输入设置为conv的方式:

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

在您的情况下,您将把要素视为空间维度,每个要素的长度为1(见下文)

以下是您的数据集中的示例

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))

如您所见,您的数据集必须重新整形为(569,30,1),请使用:

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))

这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)

Answer 2

我在其他帖子中也提到过：

要将形状的常用特征表数据输入(nrows, ncols)到 Keras 的 Conv1d 中，需要执行以下 2 个步骤：

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

例如，取 iris 数据集的前 4 个特征：

要查看通常的格式及其形状：

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

输出显示通常的格式及其形状：

[[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)

上述代码数据格式及其形状的输出：

[[[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)

这适用于 Keras 的 Conv1d。因为input_shape (4,1)需要。