Pooling output dimension is confusing if we give a non-square matrix as input #43

Closed
czhang99 opened this Issue Jul 27, 2015 · 1 comment

Projects

None yet

2 participants

@czhang99

Hi,

In the given MNIST_CNN example in owl, if we set batch size as 4, the input dimension is something like [28,28,1,4], since the pic is a 28*28 square matrix. However, I found that when input matrix is non-square, the output dimension is confusing. I am wondering if it is a bug or it is implemented that way intentionally.

For example, if input.shape is [4, 2, 1, 4] in owl format, while I set "pooling = conv.Pooler(2, 2, 2, 2, 0, 0, conv.pool_op.max)" and after I did "pooling.ff(input)" I am expected to have [2,1,1,4]. But actually I got [1, 2, 1, 4] as the output dimension in owl. Should I expect to have [1, 2, 1, 4] as the result or there is something going wrong inside the pooling function?

Great appreciation for any comments and suggestions. Thanks!

@hotpxl hotpxl added the bug label Jul 28, 2015
@hotpxl
Member
hotpxl commented Jul 28, 2015

Thanks for reporting. This is indeed a bug on our side.

@hotpxl hotpxl closed this Aug 13, 2015
@lovi9573 lovi9573 pushed a commit to lovi9573/minerva that referenced this issue Oct 9, 2015
@hotpxl hotpxl + lovi9573 [dimension-fix] dimension order (refer #43) 5092da1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment