I noticed that the relay tensor shape type will be converted to `int32_t` after
shape inference, however, if IndexExpr arithmetics is involved, the shape type
will be preserved, which breaks the following example
```
fn (%X: Tensor[(int64(7), int64(16)), float32]) {
%0 = reshape(%X, newshape=[7, -1, 1])
%0
}
```
After shape inference, it becomes
```
fn (%X: Tensor[(int64(7), int64(16)), float32])
-> Tensor[(7, int64(16), 1), float32] {
%0 = reshape(%X, newshape=[7, -1, 1]) # ty=Tensor[(7, int64(16), 1), float32]
%0
}
```
Notice the heterogenous tensor shape type for `%0`, which breaks the downstream
compilation. I looked around the code at
https://github.com/dmlc/tvm/blob/5f89a50e32c82233689623502f377a518aaa35f6/src/relay/op/tensor/transform.cc#L500
but didn't find suspicious things. And I would like to inject some debugging
code to print out the content of `IndexExpr` in C++. Anyone knows how to do
this? Thanks.
---
[Visit
Topic](https://discuss.tvm.ai/t/how-to-debug-and-print-out-content-of-indexexpr/2039/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/ddd56d70711f5e7f9090ed35fcaaf4795b6f94f745d43e567ba95c7877b17ded).
Tianqi Chen, UW, Seattle, WA, 98105, United States
http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=vdR5bitIkcGZc_SvSMixrw2
