Experiment with Onnx

[kwalcock]

No description provided.

[kwalcock]

@ZhengTang1120, this shows how processors' glove embeddings can be accessed. On my computer it takes 3-4 seconds to load them while parsing the text file takes about 1:05 minutes. The faster version is pre-normalized. The text file needs still to be normalized as it is read in. I hope that I didn't misinform you about that earlier. It looks like the unknown vector is already normalized in both cases, despite the TODO in the code. Perhaps the normalization will help the performance.

[MihaiSurdeanu]

Thanks Keith!

…

On Thu, Jan 20, 2022 at 17:18 Keith Alcock ***@***.***> wrote: @ZhengTang1120 <https://github.com/ZhengTang1120>, this shows how processors' glove embeddings can be accessed. On my computer it takes 3-4 seconds to load them while parsing the text file takes about 1:05 minutes. The faster version is pre-normalized. The text file needs still to be normalized as it is read in. I hope that I didn't misinform you about that earlier. It looks like the unknown vector is already normalized in both cases, despite the TODO in the code. Perhaps the normalization will help the performance. — Reply to this email directly, view it on GitHub <#591 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAI75TQXAD74YSUKV7GA5RLUXCQ6TANCNFSM5MOEPXRA> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>