Civitasv commented on issue #15306:
URL: https://github.com/apache/tvm/issues/15306#issuecomment-1633452250
Okay, here's the IRModule:
```py
# from tvm.script import ir as I
# from tvm.script import relax as R
@I.ir_module
class Module:
@R.function
def main(latent_sample: R.Tensor((1, 4, 64, 64), dtype="float32")) ->
R.Tensor((1, 3, 512, 512), dtype="float32"):
R.func_attr({"num_input": 1})
with R.dataflow():
...
lv254 = R.call_tir(resize2d, (lv253,), out_sinfo=R.Tensor((1,
512, 128, 128), dtype="float32"))
...
lv378 = R.call_tir(resize2d1, (lv377,), out_sinfo=R.Tensor((1,
512, 256, 256), dtype="float32"))
...
lv505 = R.call_tir(resize2d2, (lv504,), out_sinfo=R.Tensor((1,
256, 512, 512), dtype="float32"))
...
gv: R.Tensor((1, 3, 512, 512), dtype="float32") = R.add(lv648,
lv649)
R.output(gv)
return gv
# Metadata omitted. Use show_meta=True in script() method to show it.
```
--
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]
