MarisaKirisame commented on a change in pull request #4644: [WIP] Relay op
strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r374619441
##########
File path: python/tvm/relay/backend/compile_engine.py
##########
@@ -63,6 +83,316 @@ def _get_cache_key(source_func, target):
return source_func
+def get_shape(shape):
+ """Convert the shape to correct dtype and vars."""
+ ret = []
+ for dim in shape:
+ if isinstance(dim, tvm.expr.IntImm):
+ val = int(dim)
+ assert val <= np.iinfo(np.int32).max
+ ret.append(tvm.expr.IntImm("int32", val))
+ elif isinstance(dim, tvm.expr.Any):
+ ret.append(tvm.var("any_dim", "int32"))
Review comment:
why is this ok? suppose there is two Any in the code, do they get mapped to
the same symbolic shape?
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
