Skip to content

Conversation

@lhutton1
Copy link
Contributor

@lhutton1 lhutton1 commented Sep 8, 2020

Fixes an issue described in #6410. In order to retrieve the shape of a tensor tinfos should be used.

cc @leandron @anijain2305

@lhutton1 lhutton1 force-pushed the fix-convert-layout branch 2 times, most recently from fe2213d to e68ec69 Compare September 8, 2020 16:35
@comaniac
Copy link
Contributor

comaniac commented Sep 8, 2020

cc @JoeyTPChou to take a look as well as he encountered the same issue weeks ago.

Copy link
Contributor

@anijain2305 anijain2305 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@JoeyTPChou
Copy link

Thanks for the work!

Fixes an issue described in apache#6410. In order to retrieve the shape a tensor `checked_type` should be used.

Change-Id: I991d194d9cc15ee20464ff2e239fd05c035000c8
@lhutton1
Copy link
Contributor Author

lhutton1 commented Sep 8, 2020

Apologies, just realized I forgot to add a call from main in the tests.

@zhiics zhiics merged commit 82c1c73 into apache:master Sep 9, 2020
@zhiics
Copy link
Member

zhiics commented Sep 9, 2020

lhutton1 added a commit to lhutton1/tvm that referenced this pull request Sep 10, 2020
… to unpack

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
lhutton1 added a commit to lhutton1/tvm that referenced this pull request Sep 10, 2020
… to unpack

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
lhutton1 added a commit to lhutton1/tvm that referenced this pull request Sep 14, 2020
… to unpack

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
masahi pushed a commit that referenced this pull request Sep 16, 2020
… to unpack (#6442)

This patch follows a previous bugfix in #6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
kevinthesun pushed a commit to kevinthesun/tvm that referenced this pull request Sep 17, 2020
…WC (apache#6419)

Fixes an issue described in apache#6410. In order to retrieve the shape a tensor `checked_type` should be used.

Change-Id: I991d194d9cc15ee20464ff2e239fd05c035000c8
kevinthesun pushed a commit to kevinthesun/tvm that referenced this pull request Sep 17, 2020
… to unpack (apache#6442)

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
kevinthesun pushed a commit to kevinthesun/tvm that referenced this pull request Sep 18, 2020
…WC (apache#6419)

Fixes an issue described in apache#6410. In order to retrieve the shape a tensor `checked_type` should be used.

Change-Id: I991d194d9cc15ee20464ff2e239fd05c035000c8
kevinthesun pushed a commit to kevinthesun/tvm that referenced this pull request Sep 18, 2020
… to unpack (apache#6442)

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
trevor-m pushed a commit to neo-ai/tvm that referenced this pull request Sep 18, 2020
…WC (apache#6419)

Fixes an issue described in apache#6410. In order to retrieve the shape a tensor `checked_type` should be used.

Change-Id: I991d194d9cc15ee20464ff2e239fd05c035000c8
trevor-m pushed a commit to neo-ai/tvm that referenced this pull request Sep 18, 2020
… to unpack (apache#6442)

This patch follows a previous bugfix in apache#6419. I made a very simple oversight for qnn.conv2d in that tinfos also contains qnn parameters. Therefore, we need to extract data_info and weight_info differently.

Change-Id: Ib0ad01f427543371380d0bb604a77b5e0ec1103d
@lhutton1 lhutton1 deleted the fix-convert-layout branch September 23, 2020 10:27
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

7 participants