jiangjiajun opened a new pull request #9459: URL: https://github.com/apache/tvm/pull/9459
This pull request add 4 operators, the first 3 operators support 4D tensor's interpolation, and `flatten_contiguous_range` is a operator just like `torch.flatten`. - 'nearest_interp_v2` - `bicubic_interp_v2` - `bilinear_interp_v2` - 'flatten_contiguous_range` Also this pull request use `infer_value` to replace `try_infer_value`, for the reason that `infer_value` will take model's parameters to infer value while `try_infer_value` not, this will solve some dynamic shape problem(e.g if the parameter `shape` of `reshape` operator is a parameter, `try_infer_value` will fail to infer its value) Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them in the pull request thread. -- 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]
