austinmw opened a new issue #5998: URL: https://github.com/apache/incubator-tvm/issues/5998
I've pulled the docker image `tvmai/demo-gpu` and am trying the tutorial [Compile ONNX Models](https://tvm.apache.org/docs/tutorials/frontend/from_onnx.html?highlight=onnx) using the python3 install inside the container. The first issue I run into is that the line `from tvm import te` fails to import. The version of tvm inside this container is `'0.6.dev'`, so maybe the tutorial is a bit out of date? The second issue I run into is in the section "Compile the model with relay": ```python with tvm.transform.PassContext(opt_level=1): intrp = relay.build_module.create_executor('graph', mod, tvm.cpu(0), target) ``` > Traceback (most recent call last): > > File "<stdin>", line 1, in <module> > > AttributeError: module 'tvm' has no attribute 'transform' Any recommendations for how I should move past this would be greatly appreciated. ---------------------------------------------------------------- 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]
