Dump value from quantized weight

In “https://github.com/pytorch/glow/blob/master/docs/AOT.md#creating-standalone-executable-bundles

We could create an quantized weightfile “.weight”. I wonder how to dump value from this file? Thx

Hi @Ken,

I don’t think there’s a good way to dump the values from the .weights file out of the box. It’s a binary blob of the weights. You could look at one of the main.cpp drivers mentioned here, e.g. the Resnet50 bundle’s main.cpp, and try to inspect it somehow when loading it in. However it would probably be better/easier to modify BundleSaver.cpp when you’re generating the .weights file to inspect it then.