我正在根据this example
构建符合我自己数据的CNN基本上,我的数据有3640个功能;我有一个卷积层,后跟一个池化层,它汇集了所有其他特征,所以我最终得到了维度(?,1,11819,1),因为在转换层/ 2 = = 1819之后有3638个特征。
当我尝试在汇总后重新整形我的数据以便在表格中获取它[n_samples,n_fetures]
print("pool_shape", pool_shape) #pool (?, 1, 1819, 10)
print("y_shape", y_shape) #y (?,)
pool.set_shape([pool_shape[0], pool_shape[2]*pool_shape[3]])
y.set_shape([y_shape[0], 1])
我收到错误:
ValueError: Shapes (?, 1, 1819, 10) and (?, 18190) are not compatible
我的代码:
N_FEATURES = 140*26
N_FILTERS = 1
WINDOW_SIZE = 3
def my_conv_model(x, y):
x = tf.cast(x, tf.float32)
y = tf.cast(y, tf.float32)
print("x ", x.get_shape())
print("y ", y.get_shape())
# to form a 4d tensor of shape batch_size x 1 x N_FEATURES x 1
x = tf.reshape(x, [-1, 1, N_FEATURES, 1])
# this will give you sliding window of 1 x WINDOW_SIZE convolution.
features = tf.contrib.layers.convolution2d(inputs=x,
num_outputs=N_FILTERS,
kernel_size=[1, WINDOW_SIZE],
padding='VALID')
print("features ", features.get_shape()) #features (?, 1, 3638, 10)
# Max pooling across output of Convolution+Relu.
pool = tf.nn.max_pool(features, ksize=[1, 1, 2, 1],
strides=[1, 1, 2, 1], padding='SAME')
pool_shape = pool.get_shape()
y_shape = y.get_shape()
print("pool_shape", pool_shape) #pool (?, 1, 1819, 10)
print("y_shape", y_shape) #y (?,)
### here comes the error ###
pool.set_shape([pool_shape[0], pool_shape[2]*pool_shape[3]])
y.set_shape([y_shape[0], 1])
pool_shape = pool.get_shape()
y_shape = y.get_shape()
print("pool_shape", pool_shape) #pool (?, 1, 1819, 10)
print("y_shape", y_shape) #y (?,)
prediction, loss = learn.models.logistic_regression(pool, y)
return prediction, loss
如何重塑数据以获得有意义的数据表示并稍后将其传递给逻辑回归层?
答案 0 :(得分:1)
这看起来像Tensor.set_shape()
方法和tf.reshape()
运算符之间的混淆。在这种情况下,您应该使用tf.reshape()
,因为您要更改pool
和y
张量的形状:
tf.reshape(tensor, shape)
运算符采用任意形状的tensor
,并返回具有给定shape
的张量,只要它们具有相同数量的元素即可。此运算符应用于更改输入张量的形状。
tensor.set_shape(shape)
方法采用可能具有部分已知或未知形状的tensor
,并向TensorFlow断言它实际上具有给定的shape
。此方法应用于提供有关特定张量形状的更多信息。
例如,当您获取具有数据相关输出形状(例如tf.image.decode_jpeg()
)的运算符的输出并断言它具有静态形状时(例如,基于关于数据集中图像的大小)。
在您的计划中,您应该使用以下内容替换对set_shape()
的调用:
pool_shape = tf.shape(pool)
pool = tf.reshape(pool, [pool_shape[0], pool_shape[2] * pool_shape[3]])
y_shape = tf.shape(y)
y = tf.reshape(y, [y_shape[0], 1])
# Or, more straightforwardly:
y = tf.expand_dims(y, 1)