[GitHub] apeforest commented on a change in pull request #12558: [MXNET-952] added a line to check for kernel size and unittest for the same

[GitBox <gi...@apache.org>]

apeforest commented on a change in pull request #12558: [MXNET-952] added a line to check for kernel size and unittest for the same
URL: https://github.com/apache/incubator-mxnet/pull/12558#discussion_r217773810
 
 

 ##########
 File path: tests/python/unittest/test_operator.py
 ##########
 @@ -6913,6 +6913,28 @@ def test_invalid_depth_dim():
     test_invalid_block_size()
     test_invalid_depth_dim()
 
+@with_seed()
+def test_correlation_kernel_size():
+    import numpy as np
+    import mxnet as mx
+
+    # Network
+    data1 = mx.symbol.Variable('data1')
+    cor = mx.sym.Correlation(data1=data1, data2=data1, kernel_size=28, stride1=1, stride2=1, pad_size=0, max_displacement=0)
+    loss = mx.sym.MakeLoss(cor, normalization='batch')
+    group = mx.symbol.Group([mx.sym.BlockGrad(cor), loss])
+
+    # Data
+    datashape = (1, 1, 28, 28)  # like mnist
+    data = np.random.rand(1, 1, 28, 28)
+
+    #Bind, execute, get computed correlation
+    executor = group.simple_bind(ctx=mx.cpu(), data1=datashape)
+    outs = executor.forward(is_train=True, data1=data)
+    cor = executor.outputs[0]
+    grad1 = executor.outputs[1]
+    print(cor)
 
 Review comment:
   Agree with @Vikas89. I think your PR is mainly to test the error message when kernel size is even. Therefore, you do not need to test the regular case. Instead, you may want to test the case where the exception will be raised. 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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


With regards,
Apache Git Services