You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/04/03 10:31:20 UTC

[GitHub] [tvm] AD1024 opened a new pull request #7795: [FIX] `skip_conv_layers` will affect quantization of `nn.dense`

AD1024 opened a new pull request #7795:
URL: https://github.com/apache/tvm/pull/7795


   Fixed a bug that will cause quantization not working for `nn.dense`
   Also added the Repr for `skip_dense_layer` field in QConfig


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] AD1024 commented on pull request #7795: [FIX] skip_conv_layers will affect quantization of nn.dense

Posted by GitBox <gi...@apache.org>.
AD1024 commented on pull request #7795:
URL: https://github.com/apache/tvm/pull/7795#issuecomment-817077650


   I will add a test case for this after a paper ddl.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] vinx13 merged pull request #7795: [FIX] skip_conv_layers will affect quantization of nn.dense

Posted by GitBox <gi...@apache.org>.
vinx13 merged pull request #7795:
URL: https://github.com/apache/tvm/pull/7795


   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] AD1024 commented on pull request #7795: [FIX] skip_conv_layers will affect quantization of nn.dense

Posted by GitBox <gi...@apache.org>.
AD1024 commented on pull request #7795:
URL: https://github.com/apache/tvm/pull/7795#issuecomment-824279796


   @vinx13 @ZihengJiang 
   Test case added. Please review. Thank you.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] vinx13 commented on a change in pull request #7795: [FIX] skip_conv_layers will affect quantization of nn.dense

Posted by GitBox <gi...@apache.org>.
vinx13 commented on a change in pull request #7795:
URL: https://github.com/apache/tvm/pull/7795#discussion_r610999188



##########
File path: python/tvm/relay/quantize/quantize.py
##########
@@ -80,7 +80,7 @@ class QConfig(Object):
         "global_scale": 8.0,
         "weight_scale": "power2",
         "skip_dense_layer": True,
-        "skip_conv_layers": [0],
+        "skip_conv_layers": None,

Review comment:
       We don't need to change the default value, as skipping the first conv seems more common




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org

[GitHub] [tvm] tqchen commented on pull request #7795: [FIX] skip_conv_layers will affect quantization of nn.dense

Posted by GitBox <gi...@apache.org>.
tqchen commented on pull request #7795:
URL: https://github.com/apache/tvm/pull/7795#issuecomment-816650544


   cc @ZihengJiang @vinx13 please help to review this PR


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org