From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mp10.migadu.com ([2001:41d0:403:478a::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by ms9.migadu.com with LMTPS id ENbjOuG7ymRbZQAASxT56A (envelope-from ) for ; Wed, 02 Aug 2023 22:26:10 +0200 Received: from aspmx1.migadu.com ([2001:41d0:403:478a::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by mp10.migadu.com with LMTPS id +CDzOeG7ymSXggEAG6o9tA (envelope-from ) for ; Wed, 02 Aug 2023 22:26:09 +0200 Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by aspmx1.migadu.com (Postfix) with ESMTPS id 6C5FD690FA for ; Wed, 2 Aug 2023 22:26:09 +0200 (CEST) Authentication-Results: aspmx1.migadu.com; dkim=pass header.d=gmail.com header.s=20221208 header.b=JzSNh0Nt; spf=pass (aspmx1.migadu.com: domain of "guix-devel-bounces+larch=yhetil.org@gnu.org" designates 209.51.188.17 as permitted sender) smtp.mailfrom="guix-devel-bounces+larch=yhetil.org@gnu.org"; dmarc=pass (policy=none) header.from=gmail.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=yhetil.org; s=key1; t=1691007969; h=from:from:sender:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:list-id:list-help: list-unsubscribe:list-subscribe:list-post:dkim-signature; bh=TNGFL+cqKBphciJaYWSFGEOlJ3PhyyN1roCa31Sko/Y=; b=T4UKmb6vMM5W/rczl2P5B1IG5HkR+epbbQj0PllY+NwD1i/0sYwgRmjZZ7PFvWhSlBvVDO 1E5quRrzgyibj73Sp0yCMhw8233y0CkyTmh0+0zagoiR8hNLSB+NzJsryfziUg1D1lb7b8 uKto9V4vngfvD9PchzaJFQ8sWKWxncMvXn0oUL8LyjWyYV6Ye7TFkaxrxxE6d7Z8yxBS2N VYeuhSPHTAwNpHmQHbX95TB5bWPUPUtURLrWj/HZzAzefhqoFESfeeE1fxZrJVi3vAI/uS qKTL90duAAl1aPHAjtK7LD87bEhT0MQCnWjaxBfNaByz/Y00AYSt/cPm9BZVbw== ARC-Seal: i=1; s=key1; d=yhetil.org; t=1691007969; a=rsa-sha256; cv=none; b=m804V8C1a0z5KP+hzAtVS67GKHA6tTklsamlX1RkLiqYjI4/vwLJgjSEfD1LWz7FA3KTeQ R4r2eaMjjQw7fE9zQvyupK009TZ9yPxnV28r3A/6h882C3LEvbtIZL7luPfBpQpJXeOH0B kRxd3wk0+p+JSTbtiujFBQuAV9iSuCVo19pL1fSUz7qlC2vrEkMBFty9OLfU806Nwam3ii Es1Y0wnshJSQ0cUR11QGKvP/a0bGXE4LyFZFlIOEk+dayrNNAMpBkgx/OdIR3mJQp7sMZI KN7DTYLw8VbZ5QxJ6nUXGdpQI37lifp10SV+VNDoCcsld/7C9w0MT+4lC6DdWQ== ARC-Authentication-Results: i=1; aspmx1.migadu.com; dkim=pass header.d=gmail.com header.s=20221208 header.b=JzSNh0Nt; spf=pass (aspmx1.migadu.com: domain of "guix-devel-bounces+larch=yhetil.org@gnu.org" designates 209.51.188.17 as permitted sender) smtp.mailfrom="guix-devel-bounces+larch=yhetil.org@gnu.org"; dmarc=pass (policy=none) header.from=gmail.com Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qRIPX-0005qx-1c; Wed, 02 Aug 2023 16:25:35 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qRIPV-0005qo-RK for guix-devel@gnu.org; Wed, 02 Aug 2023 16:25:33 -0400 Received: from mail-oa1-x30.google.com ([2001:4860:4864:20::30]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1qRIPU-00032Z-8o for guix-devel@gnu.org; Wed, 02 Aug 2023 16:25:33 -0400 Received: by mail-oa1-x30.google.com with SMTP id 586e51a60fabf-1bb75afeee3so124414fac.0 for ; Wed, 02 Aug 2023 13:25:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20221208; t=1691007930; x=1691612730; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=TNGFL+cqKBphciJaYWSFGEOlJ3PhyyN1roCa31Sko/Y=; b=JzSNh0NtOuq4LjIZ+wMEKVGwm08/Bcwww4fu5wIYUQcM+QRk2WFL8oxivculTXJfwY 3MakcIy0uEeHcfn2oZ+vTpALX6AyAqf81sscq/C1/Tog0jKGCzHgl/W7O0Dw7QRcyHMR oJVzN+SkclMwBAXV23u8PvMq873UBgaqwMJ4NPNphw0+Ozw4j2yJBg3S6osiUpZLC0Ag p+0rCUwo+NNuTeIsF/XII5iYjGGzoRMAjU7RBQFOiGHVGPgpg/zVEfN7lpAVLrKorCtg tiHbHoIOCa1i8B2vQK9zFg07nUJryT4Ye8fAHIymUeOqcUwGw80HCFpmrm1ZTz2nzi6l 2Few== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1691007930; x=1691612730; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=TNGFL+cqKBphciJaYWSFGEOlJ3PhyyN1roCa31Sko/Y=; b=Zty2NeJONTargEDOzmf9MJcPWl7P2yuLXvIyU0OpPrHQJ3ZQa5dDmWnv5IOFzjyJ5R jD9iwXnWaUMkyhYFcT5vsJue4n2saQPtqMqBAmgOD3Uby9yPw0V9fPD8zyPUB6hzw3lO e4nIDoYs6zeofY22rY9Ac27dOIPYUcVh4RZphifA7kO9D4lk/bfipgC1UlPIAinOJikd 3r7XAWRxfVeP4k/5yVQBWDy2suxmgAtVs6J7DmbKQ8vWZ+T84XB6koZ0YKc1V5eCKuiN XoaXu8CMSzMiUIPWngxqfRjvioKqQiheiZSuiZHucuvARAUB3QklwID7gIc8+/Aw4xcW QHTw== X-Gm-Message-State: ABy/qLZ+iTvcs4SLMGg9zF33LbOax0zl/kdazfGsc/9YVsMJ/SvLAAjV B9BCHWyvlML1Y1TH0seYEL/kSME+TiVkpVNILZg= X-Google-Smtp-Source: APBJJlFh8DvUnAIwW7we5xntXNhbXkLpA9S0LbZBd9IZ3O0In6tVOzFhrkDRJ28XGk6Nt17D6flzviXU1vO2tUD2B7s= X-Received: by 2002:a05:6870:8202:b0:1aa:30e3:6a5e with SMTP id n2-20020a056870820200b001aa30e36a5emr17895467oae.22.1691007930459; Wed, 02 Aug 2023 13:25:30 -0700 (PDT) MIME-Version: 1.0 References: <20230801203700.67ef6l3ibg27wzpk@X-kone> <20230802044643.ibduhkxu3fvpoiok@X-kone> In-Reply-To: <20230802044643.ibduhkxu3fvpoiok@X-kone> From: Nathan Dehnel Date: Wed, 2 Aug 2023 15:25:19 -0500 Message-ID: Subject: Re: Binary descriptors for OpenCV To: Saku Laesvuori Cc: guix-devel@gnu.org Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass client-ip=2001:4860:4864:20::30; envelope-from=ncdehnel@gmail.com; helo=mail-oa1-x30.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: guix-devel@gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: "Development of GNU Guix and the GNU System distribution." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: guix-devel-bounces+larch=yhetil.org@gnu.org Sender: guix-devel-bounces+larch=yhetil.org@gnu.org X-Migadu-Flow: FLOW_IN X-Migadu-Country: US X-Migadu-Spam-Score: -7.30 X-Spam-Score: -7.30 X-Migadu-Queue-Id: 6C5FD690FA X-Migadu-Scanner: mx0.migadu.com X-TUID: 09h6vhmchac9 >You can always check what kind of data the program gives to the neural network as the program is free software. If the data is valid runtime input it is also valid training data. That's not necessarily true. Like an image generating program will be trained on image + caption pairs, but running it involves giving it just the captions. Thus, running the model doesn't inherently show you how to retrain the model. >You can't exactly *know* that any extra training doesn't break the model but the same holds for editing the original training data. You can know with more certainty that it doesn't break the model. On Tue, Aug 1, 2023 at 11:46=E2=80=AFPM Saku Laesvuori = wrote: > > > >If you know how to convert the blob to weights in the neural network > > >(something the program has to do to make any use of the blob) and know > > >the error function, you can continue the training with new data. > > > > Yeah, I get that, but you don't necessarily know what the weights > > mean. Let's charitably assume you know the blob works on image data > > (instead of audio data or whatever). Do you know if it needs to be > > trained on images of a particular size, or color depth, or encoding, > > or color format, etc.? And what about models for more complex data > > than images like genetic data? > > You can always check what kind of data the program gives to the neural > network as the program is free software. If the data is valid runtime > input it is also valid training data. > > > How do you know you're not going to end up with a network that spews > > out invalid garbage if you re-train it with things that are > > incompatible with the original training dataset? And how do you know > > that, beyond trial and error, unless you have the original dataset? > > You can't exactly *know* that any extra training doesn't break the model > but the same holds for editing the original training data. It is only > very likely that training with new data improves the model, but you > can't know it before you try. > > In this specific case we also do have access to the training data. We > just don't want to spend the computing resources on training the model > from scratch.