python - 负维度大小由 1 减去 2 导致的 'conv2d_2/convolution' (op: 'Conv2D') 输入形状：[?,174,1,40], [2,2,40,16]

Question

%store -r x_train 
%store -r x_test 
%store -r y_train 
%store -r y_test 
%store -r yy 
%store -r le
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, Conv2D, MaxPooling2D,  
GlobalAveragePooling2D
from keras.optimizers import Adam
from keras.utils import np_utils
from sklearn import metric
num_rows = 40
num_columns = 174
num_channels = 1
x_train = x_train.reshape(x_train.shape[0],num_rows , num_columns, 
num_channels)
x_test = x_test.reshape(x_test.shape[0], num_rows, 
num_columns,num_channels )

num_labels = yy.shape[1]
filter_size = 2
model = Sequential()

model.add(Conv2D(filters=16, kernel_size=2, 
activation='relu',input_shape=(40,174,1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=32, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=64, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=128, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))
model.add(GlobalAveragePooling2D())

model.add(Dense(num_labels, activation='softmax'))

这是完整的代码。当我尝试创建 CNN 模型时，我遇到了这个错误。

InvalidArgumentError                      Traceback (most recent call 
last)
~/arshin/home/arshin/envs/aiml/lib/python3.6/site- 
 packages/tensorflow/python/framework/ops.py in _create_c_op(graph, 
 node_def, inputs, control_inputs)
 1566   try:
 -> 1567     c_op = c_api.TF_FinishOperation(op_desc)
  1568   except errors.InvalidArgumentError as e:

 InvalidArgumentError: Negative dimension size caused by subtracting 2 
 from 1 for 'conv2d_1/convolution' (op: 'Conv2D') with input shapes: 
 [?,174,1,40], [2,2,40,16].

代码不包含错误。为什么会发生这种情况.......这是因为 tensorflow 版本还是什么.. 我尝试了很多东西，但我无法纠正错误。这段代码有什么问题..

标签： python