ekalda commented on code in PR #14909:
URL: https://github.com/apache/tvm/pull/14909#discussion_r1251781264
##########
tests/python/contrib/test_ethosu/test_codegen.py:
##########
@@ -157,6 +157,76 @@ def conv2d_double(x):
infra.compare_tvm_with_tflite(conv2d_double, [ifm_shape], accel_type)
[email protected]("accel_type", ACCEL_TYPES)
[email protected]("ifm_shape", [(1, 55, 32, 3)])
[email protected](
+ "kernel_shape, activation_function",
+ [((3, 3), "RELU"), ((1, 2), "NONE")],
+)
[email protected]("strides, dilation", [((3, 2), (1, 1))])
[email protected]("op_padding", ["SAME", "VALID"])
[email protected]("sep_padding", [(0, 0, 1, 1), (7, 5, 4, 5)])
[email protected](
+ "op_pairs", [("conv2d", "conv2d"), ("depthwise", "depthwise"), ("conv2d",
"depthwise")]
+)
Review Comment:
This is 128 codegen tests, which would noticeably increase CI time. I think
the variations on `kernel_shape`, `activation_function`, `op_padding` and
`sep_padding` are exercised by other tests as well, so these values could be
kept constant. Also, if we are parametrizing over one value, it doesn't need to
be expressed with `parametrize` and can be included into the test code.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
