[GitHub] [tvm] wayne-jd-chen removed a comment on issue #4118: [RFC] Dynamic Shape Support - Graph Dispatching

[GitBox <gi...@apache.org>]

wayne-jd-chen removed a comment on issue #4118:
URL: https://github.com/apache/tvm/issues/4118#issuecomment-789559705


   i am wondering if there is any chance to introduce a quick way to compatible with dynamic shapes? 
   as @cloudhan mentioned, TensorRT can let user set necessary input dimensions at runtime, and auto compute other tensors' shape:
   [Working With Dynamic Shapes](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#work_dynamic_shapes)
   
   and i noticed, relay can parse models with dynamic shapes, but will failed at relay.build() or vm.compile()
   so, can we have some feature like:
   ```python
   mod, params = relay.frontend.from_tensorflow(...)
   mod.get_tensor_by_name('input:0').set_shapes((...))
   mod.auto_compute_shapes()
   ...
   relay.build(mod, target)
   ```
   
   to achieve the full support and optimization of dynamic shapes seems to be a huge project, and i found a lot users show their interesting and concern about this topic. i think maybe a little further step could be quickly done can be helpful.
   
   @kevinthesun , i'm a newbie to tvm, maybe what i thought is too simple as a matter of course. just want to help, appreciate~


----------------------------------------------------------------
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:
users@infra.apache.org