daverim
daverim
Hi @wwwind, do you think you can take a look at this issue?
Hi @SkylerZheng, Please provide more details, including model and reproduction code if possible. If it is x86 CPU, there is an issue with per-channel quantized dynamic range quantization in interpreters...
It is possible to build tensorflow from source but if you are running TFLite, you probably only care about mobile performance, no? In this case, you should test performance of...
Seems reasonable -- we are planning on adding this soon.
Hi do you have any relevant experiment data that you could add to this PR? This seems useful, but hard to see how to set the power value.
Hi could you provide an example? TF1.15 may have had some issues with bias overflow that have been fixed by adjusting the weight scales.
Hi this is true, however, we generally do not support quantize_model for lambda operations. This is because the expectation is that quantization will be applied to supported ops, which is...
No, it is a bug -- there should be a best effort to quantize the output of the lambda layer and at least not cause a crash. I filed a...
Currently, TF does not have the required kernels to run all quantized operations. So we are emulating quantization with float. In order to run this our users are generally converting...
@DLPerf, it would be great if you can send a PR our way. @PraChetit, could you reply as I don't have any insight on this.