【发布时间】:2016-03-17 10:40:14
【问题描述】:
我正在使用 Tensorflow 处理一维信号(形状为 (?, 5000, 1, 12))并希望执行跨步操作。但是,当我尝试 tf.nn.conv2d(input_variable, W, strides=[1, stride, 1, 1], padding='SAME') 时,我得到一个 ValueError:
/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.pyc in conv2d_shape(op)
207 if stride_r != stride_c:
208 # TODO(shlens): Add support for this.
--> 209 raise ValueError("Current implementation only supports equal length "
210 "strides in the row and column dimensions.")
211
ValueError: Current implementation only supports equal length strides in the row and column dimensions.
对于当前实现的限制,是否有已知的解决方法,它只允许我进行水平跨步?
【问题讨论】:
标签: python tensorflow