wooseok-cadence opened a new pull request, #15173: URL: https://github.com/apache/tvm/pull/15173
Loading int16 conv transpose op in tflite model currently fails because output type is not int64. This patch adjusts output type to int64 for int16 quantized transpose convolution operation. In addition, one typo in QnnConv2DTransposeRel is fixed. Test script is also included to evaluate the loading of int16 quantized transpose convolution op. -- 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]
