[SYSTEMDS-1686] Transpose Conv2d has incorrect filter shape and incorrect input size argument

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: SystemML 1.0.0
• Fix Version/s: SystemML 0.15
• Assignee: Matthias Boehm
• Reporter: Mike Dusenberry
• Created: 13/Jun/17 01:21
• Updated: 09/Sep/17 01:41
• Resolved: 16/Jun/17 18:42

Description

Currently, the transpose conv2d layer (nn/layers/conv2d_tranpose.dml has a bug in which the filters tensor W has an incorrect shape, and the conv2d_backward_data op has an incorrect input shape argument. This results in an exception when the number of input channels C is not equal to the number of filters F (i.e. number of output channels). Since the transpose conv2d op is the gradient of the conv2d op, the filter tensor needs to have the shape C, F, Hf, Wf for F filters, rather than F, C, Hf, Wf, in order to map from an input with C channels to an output with F channels during the input data gradient function (conv2d_backward_data) that is used in the forward pass. Additionally, the input_shape argument for conv2d_backward_data needs to be N, F, Hout, Wout, rather than N, C, Hout, Wout in order to map from an input with C channels to an output with F channels. Our current test cases did not catch this issue because the tests used C = F = 1.

Issue Links

• relates to: SYSTEMDS-540 Deep Learning
• relates to: SYSTEMDS-618 Deep Learning DML Library