jiangjiajun commented on PR #16651: URL: https://github.com/apache/tvm/pull/16651#issuecomment-1970240420
> @jiangjiajun 针对与PaddleInference模型来说，这个误差应该是可以接受的？我用单一卷积算子进行了测试，在大多数情况下单个卷积算子是满足相对和绝对误差在 10^-5内的要求的，目前判断应该是是多个卷积算子误差的累积导致最后模型的输出结果发生了改变。 How about the different between quantized paddle model and quantized onnx model? -- 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]
