search

pytorch / glow

Compiler for Neural Network hardware accelerators
Apache License 2.0
3.23k stars 692 forks source link

Get value from quantized weight #2536

Open a462428 opened 5 years ago

a462428 commented 5 years ago

After

"image-classifier tests/images/imagenet/cat_285.png -image-mode=0to1 -m=resnet50 -model-input-name=gpu_0/data -load-profile=profile.yml -cpu -emit-bundle build"

We could get quantized ".weight" file. Is it able to get the value from this file?

opti-mix commented 5 years ago

@a462428 Could you clarify your use-case? Do you need the quantized weights during the compilation of a network or when an AOT compiled network (i.e. produced by means of -emit-bundle and linked with your executable) is being executed?

a462428 commented 5 years ago

@opti-mix Hi, I wanna check the quantized weights during the compilation of a network.