Niroop Ammbashankar

@psfoley @kta-intel @manuelhsantana @ifahim Requesting re-review of the readme startup documentation. Reduced steps and added expected output.

looks like there was a major merge to the develop branch. So I rebased, remade this PR to remove conflicts @psfoley @kta-intel @manuelhsantana

Yes, try the "merge_duplicate_nodes" option and give it a try again. But , here are some questions: After transform_graph did you run the fp32 graph? Did it work? After transform_graph...

@felipheggaliza Use the following command: with and without the merge_duplicate_nodes and you should have your optimized FP32 graph. your other FP32 graphs have the following problems: Batchnorms was not folded....

@felipheggaliza Pleasure to be of help. @mdfaijul in in the process of updating and cleaning the quantize graph.py and I am in the process of integrating the regex feature to...

Updated Qunatize_graph.py https://github.com/NervanaSystems/tools/tree/niroop/perchannel_padfusion_fasterrcnnfpn From: Feliphe Gonçalves Galiza [mailto:[email protected]] Sent: Friday, May 24, 2019 11:46 AM To: IntelAI/tools Cc: Ammbashankar, Niroopshankar ; Mention Subject: Re: [IntelAI/tools] RetinaNet Quantization (#1) Hi @nammbash,...