MO should support LRN k param with caffe model, rather than fixed to 1 (

openvinotoolkit#716) Co-authored-by: yipengqu <[email protected]>
slyalin · Jun 3, 2020 · 2bb7010 · 2bb7010
1 parent 1ffada0
commit 2bb7010
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/model-optimizer/extensions/front/caffe/lrn_ext.py b/model-optimizer/extensions/front/caffe/lrn_ext.py
@@ -29,7 +29,7 @@ def extract(cls, node):
         AttributedLRN.update_node_stat(node, {
             'alpha': param.alpha,
             'beta': param.beta,
-            'bias': 1,
+            'bias': param.k,
             'local_size': param.local_size,
             'region': region,
         })