mbrookhart commented on a change in pull request #6316:
URL: https://github.com/apache/incubator-tvm/pull/6316#discussion_r474786747
##########
File path: python/tvm/relay/op/dyn/_transform.py
##########
@@ -145,3 +146,53 @@ def one_hot_shape_func(attrs, inputs, _):
"""
axis = len(inputs[0].shape) if attrs.axis == -1 else attrs.axis
return [_onehot_shape_func(inputs[0].shape, inputs[3], convert(axis))]
+
+
+@script
+def _strided_slice_shape_func_input_data(data, begin, end, strides,
Review comment:
For the static op, we only require the input shapes, since the tributes
are static, thus the input_shape variant. For the dynamic op, we need the input
data, since the attributes are coming in as values. Thus the input_data
variant. Why the VM is set up to separate those instead of just sending in data
all the time, I'm not sure. Optimization?
----------------------------------------------------------------
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:
[email protected]
