I want to know what is the difference between a these two. For me, they are the same function, so I do not see the reason of existance two same functions.
In TensorFlow 2, they accept different arguments:
tf.nn.convolution(input,...)
Computes sums of N-D convolutions (actually cross-correlation).
input
: An (N+2)-D Tensor of type T, of shape [batch_size] + input_spatial_shape + [in_channels]
While the second one is more specific:
tf.nn.conv1d(input,...)
Computes a 1-D convolution given 3-D input and filter tensors.
input
: A 3D Tensor.input: A 3D Tensor.
-
$\begingroup$ Thank you for your answer. So, basically, both in some case, e.g. 3D tensor input, are computing the same thing? $\endgroup$ – Cepeline Jan 29 '20 at 15:15
-
$\begingroup$ I don't know for sure. I believe you can check it by feeding a 3D tensor to both. $\endgroup$ – homocomputeris Jan 30 '20 at 11:38