Skip to content
This repository has been archived by the owner on Jan 7, 2021. It is now read-only.

not quantized and cannot be deployed to DPU,because it has unquantized input node: #106

Open
rokmc612 opened this issue Sep 25, 2019 · 0 comments

Comments

@rokmc612
Copy link

Hi ,

I used by tensorflow 1.12 and try to ML-suite 1.5.

would you pls check for the below warning msg and the attached Decent_q run log files.

[DEPLOY WARNING] Node Conv2D_eightbit/IteratorGetNext__port__0/min(Type: Min) is Conv2D_eightbit/IteratorGetNext__port__0/reduction_dims. Please deploy it on CPU.
[DEPLOY WARNING] Node Conv2D_eightbit/IteratorGetNext__port__0/max(Type: Max) is not quantized and cannot be deployed to DPU,because it has unquantized input node: Conv2D_eightbit/IteratorGetNext__port__0/reduction_dims. Please deploy it on CPU.
[DEPLOY WARNING] Node Conv2D_eightbit/IteratorGetNext__port__0/quantize(Type: QuantizeV2) is not quantized and cannot be deployed to DPU,because it has unquantized input node: Conv2D_eightbit/IteratorGetNext__port__0/min. Please deploy it on CPU.

Thanks

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant