gussmith23 opened a new issue #6470:
URL: https://github.com/apache/incubator-tvm/issues/6470
Parsing a Relay program which uses `nn.dense` seems to be finicky! I might
be doing something wrong here, let me know!
A minimum working example:
```python3
import tvm
from tvm import relay
from tvm.relay.testing.mobilenet import get_workload
x = relay.var('x', shape = (3,))
y = relay.var('y', shape = (3,3))
prog = relay.nn.dense(x, y)
function = relay.Function([x, y], prog)
module = tvm.IRModule.from_expr(function)
print(module.astext())
tvm.parser.fromtext(module.astext())
# if we remove the "None" that is causing the error, we get a different
error:
tvm.parser.fromtext(
'''
#[version = "0.0.5"]
def @main(%x: Tensor[(3), float32], %y: Tensor[(3, 3), float32]) ->
Tensor[(3), float32] {
nn.dense(%x, %y) /* ty=Tensor[(3), float32] */
}
'''
)
```
----------------------------------------------------------------
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]
