commit | 86c4350ae8f4f9a68e2334b08a6e97c8c457e981 | [log] [tgz] |
---|---|---|
author | Miao Wang <miaowang@google.com> | Tue Sep 19 13:05:06 2017 -0700 |
committer | Miao Wang <miaowang@google.com> | Tue Sep 19 20:08:09 2017 +0000 |
tree | bcc3a998477a634585377dcbf5c0114df79a0b94 | |
parent | dec08deb44c829eca478214972170606323b66cf [diff] |
Fix depthwise_conv tests - For quantized depthwise_conv, the bias needs to be TENSOR_INT32. - The first dimension for the filter needs to be 1. Bug: 63905942 Test: depthwise_conv_quant8 in NeuralNetworkTests pass Change-Id: I180c2f3be59651897839475213fd3c874c55a267