I'm refactoring tf frontend tensor array and will fix these issues.
---
[Visit Topic](https://discuss.tvm.ai/t/issue-with-static-tensor-array/6333/12)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.
Are you looking at this？
@kevinthesun
---
[Visit Topic](https://discuss.tvm.ai/t/issue-with-static-tensor-array/6333/11)
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/fdd4
Dear All,
I am new to TVM. and I am wondering what facilities does TVM/Relay support to
traverse the network graph?
Assuming I have a DAG, can I traverse from the sink to the source? and vise
versa?
Thanks.
D.
---
[Visit
Topic](https://discuss.tvm.ai/t/traversing-relay-graph-order-so
@tqchen @taknevski I'm having a similar problem here, and I wonder how to
explicitly convert the non-compact subtensor into a compact tensor? I have
tried to add something like:
```python
B = te.compute(
(m, n, k, l),
lambda a, b, c, d: tmpB[a, b, c, d])
```
but I on
yap same problem, we may have to wait for new PR
---
[Visit Topic](https://discuss.tvm.ai/t/issue-with-static-tensor-array/6333/10)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubs
Hi, I found an potential ambiguity in TIRTextPrinter. Because of the
straightforward printing of EvaluateNode, users may not be able to distinguish
these two cases: Array[Expr] vs Array[Evaluate(Expr)].
My question is, is it better to enhance the printing format of EvaluateNode? Or
we don't
I’m facing the same error.
```
unable to unify: 'static_tensor_float32_320_320_3_t' and
''static_tensor_float32_scalar_t';
unable to unify: 'static_tensor_int32_3_t' and ''static_tensor_int32_scalar_t';
```
model: [ssd_mobilenet_v3
(Similar to
http://download.tensorflow.org/models/object_d
