Uh oh!
There was an error while loading. Please reload this page.
Qnn fully connected - #3910
Conversation
@anijain2305@zhiics@vinx13 can you take a look at this PR. |
anijain2305
left a comment
There was a problem hiding this comment.
Overall LGTM. Some minor comments.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
shoubhik
commented
Sep 9, 2019
anijain2305
commented
Sep 12, 2019
shoubhik
commented
Sep 12, 2019
Fixed the test related issue. |
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
shoubhik
commented
Sep 20, 2019
@jackwish Could you take a look |
zhenhuaw-me
left a comment
There was a problem hiding this comment.
LGTM. Sorry that I have missed this :)
shoubhik
commented
Sep 21, 2019
@zhiics can you merge this. |
zhiics
commented
Sep 22, 2019
Thanks everyone. This is now merged. |
* Qnn Dense layer. * Reformatting code. * Reformatting code and making the test case more readable. * Fixing lint issues. * Fixing test method names to pass the nose related configurations. * Aligning the code for code style.
* Qnn Dense layer. * Reformatting code. * Reformatting code and making the test case more readable. * Fixing lint issues. * Fixing test method names to pass the nose related configurations. * Aligning the code for code style.
* Qnn Dense layer. * Reformatting code. * Reformatting code and making the test case more readable. * Fixing lint issues. * Fixing test method names to pass the nose related configurations. * Aligning the code for code style.
This is continuation of the Qnn dialect. After the convolution #3580 this the implementaion of Dense layer with quantized inputs. In future revisions we will add schdules for more optimal performance.