jikechao opened a new pull request, #15082: URL: https://github.com/apache/tvm/pull/15082
This PR removed the wrong assertion about UpSampling2D. In the Keras frontend of TVM, The UpSampling2D has a wired constraint: "Height must equal width for operator Upsample." However, from the [documentation about UpSampling2D](https://keras.io/api/layers/reshaping_layers/up_sampling2d/), The constraint about `size` is, " Int, or tuple of 2 integers". Meanwhile, An official example from the Keras documentation uses the size(1, 2) . Thus, the assertion in TVM is wrong, and I deleted the related statements. -- 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]
