From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mp11.migadu.com ([2001:41d0:306:2d92::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by ms9.migadu.com with LMTPS id yIuZJtnfyWTuogAASxT56A (envelope-from ) for ; Wed, 02 Aug 2023 06:47:21 +0200 Received: from aspmx1.migadu.com ([2001:41d0:306:2d92::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by mp11.migadu.com with LMTPS id mGSMJtnfyWSNSAEA9RJhRA (envelope-from ) for ; Wed, 02 Aug 2023 06:47:21 +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 81F1F4D8AD for ; Wed, 2 Aug 2023 06:47:21 +0200 (CEST) Authentication-Results: aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b=g6Ti5uqa; 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=reject) header.from=laesvuori.fi ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=yhetil.org; s=key1; t=1690951641; 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:in-reply-to:in-reply-to: references:references:list-id:list-help:list-unsubscribe: list-subscribe:list-post:dkim-signature; bh=HxQulh6htpoYKiNVLOvQ6JLTCwDqUI7zJcUOWOIYVQE=; b=VlbrH15XLP++SxaJYiNXaIIZmBmPYc0t92OaR/Xt28lahX0bPcJ5fTpZUvnzeDlh3pMu1X MuZQrYWq92pVxJvGRr32ObDDxBKzfE4x4BN9BViO5wbRiFMeg8g+DKWhqJciP+GY7oDFKF DeS52EqgPQJxjgrs77yAUz0Cb4l7mqTnnncQys8CaAjFDT37GEcxKTeqLBIxzNORHqjbBI DPa/3qxOmd6NJHiDhL05tZ8m3Ufcua6IdSsYQWLb4hnSz9dAIqRm2HeY0XNtQ0Ut0sGUz9 wgXGzioLGNtYQr8bn7fBq9ZlZTtdSky70STQSPmYzloXyT9/1K/M/GrsqVxkog== ARC-Authentication-Results: i=1; aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b=g6Ti5uqa; 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=reject) header.from=laesvuori.fi ARC-Seal: i=1; s=key1; d=yhetil.org; t=1690951641; a=rsa-sha256; cv=none; b=DEG6t2S8Lugaa2xR5yDWy3lRi06IqvAO+vTB+gYLr3McJnr1ZTaGvvE+jab56+enK1ObS9 v3ot2s75sv8M46P39yi6t6QZnilRT2Xbhhygz+BH9WIcgW0S0wyJPI44EtU2zgLZIq4qQH ENfcE3UiT5BxUAm2u8EjzIkvb72J0MEMP504NraTcTLxIgkaZ9IqRIRHbbeodn9M6k3rLA OWuy5VibPk7T8NsFSnG4SXQ85FaIlB37chNYl/B8U9UlZntWswGNLIe1PBUxzxeCRcIpls lgOT/k7VydKSz9u94Z0k4MuiTodA59olCqKB5YmiqiyEGEgDg30JdnTjxQ58+Q== Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qR3l8-0005cW-NV; Wed, 02 Aug 2023 00:46:56 -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 1qR3l7-0005c7-3K for guix-devel@gnu.org; Wed, 02 Aug 2023 00:46:53 -0400 Received: from vmi571514.contaboserver.net ([75.119.130.101] helo=mail.laesvuori.fi) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qR3l4-0004mN-5V for guix-devel@gnu.org; Wed, 02 Aug 2023 00:46:52 -0400 Received: from X-kone (unknown [192.130.254.9]) by mail.laesvuori.fi (Postfix) with ESMTPSA id 58E8A340134; Wed, 2 Aug 2023 06:46:52 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=laesvuori.fi; s=mail; t=1690951612; bh=HxQulh6htpoYKiNVLOvQ6JLTCwDqUI7zJcUOWOIYVQE=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=g6Ti5uqaxVb9vff2efVyXDDm5KAsGW2h2y39CE7wyNqYp6fEc8VPuSni5aU/RCfHo ZxoA4nDDq44UljZnrSfxFJRuBsLha7QlJ0D7T7J6wxRoZr4nSs2D9NRYnyCbj5Wpck nYnhaoyaUQdqHWGjTh8w13uEE98eMDt4/Rr3kbhs= Date: Wed, 2 Aug 2023 07:46:43 +0300 From: Saku Laesvuori To: Nathan Dehnel Cc: guix-devel@gnu.org Subject: Re: Binary descriptors for OpenCV Message-ID: <20230802044643.ibduhkxu3fvpoiok@X-kone> References: <20230801203700.67ef6l3ibg27wzpk@X-kone> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="shzbktep6dkqitd3" Content-Disposition: inline In-Reply-To: Received-SPF: pass client-ip=75.119.130.101; envelope-from=saku@laesvuori.fi; helo=mail.laesvuori.fi 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, SPF_HELO_PASS=-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-Scanner: mx2.migadu.com X-Migadu-Spam-Score: -7.10 X-Spam-Score: -7.10 X-Migadu-Queue-Id: 81F1F4D8AD X-TUID: SoQNDIZoSxt3 --shzbktep6dkqitd3 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable > >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. >=20 > 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.=20 > 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 =66rom scratch. --shzbktep6dkqitd3 Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEoMkZR3NPB29fCOn/JX0oSiodOjIFAmTJ37MACgkQJX0oSiod OjLSkQ/8CmC0fxYaEg/4bcXrknqBVz7Sb7ephirAUhhIAyjwosLaIDxJ87fEEVpA hbSZglkNWOkXegaVoCMWBdXPqEPi4FXOGaU9Cg3p7zyQ13js4arSQcW/Ll6MdSJl WQrWQovpNDpslgeRvzNd6TOWXNAk4lxcggDlAe3KvYpYa9wKBeSUhKTmsLvAIbMv tY+pTRATHGGuQXee6iVYB6roKtsuPGp5+rR59YbxRvlAz19Mj8QSBolfzBj0HquZ IpyD1q+a4TOkFLZIJQEtGAt2F9uN/WL1CIrcJNPbq+FKXU5qCv6dhcayy9ONI1r4 IDNd85U+kETXQfScO83SlQmfm23sDG9BsIslqDfkohLsVzkNTpKlHh8XRBYvm3SH rP9OMjYlOIVNeOQWK/j5Af0XuZXq7BTV/9uta7NgWt6RVmSS5NCNl9yDnv6WwEAi N0+tUQb701/qewfyEdIUR3aJkcOM42+E2w2Lm15MWc44UKAB0gIOb8WjbCDbYsVy bDkFIYXz6ja9ch2ZWzWN7xKyLjIqYkrzxL2XGIoa1DqTppmjM2sSfunprgjaV1Ec 91lIUgNCobLr95IP/a4D6oVI4MNhDoq0RZg1KnhBXNochaf++EUzUVprhchIvdo4 F4ERtUO0e28SOzOdPBDEL+zdwOeLgQAPAQJprDWjVkF97N1EMGA= =1T/J -----END PGP SIGNATURE----- --shzbktep6dkqitd3--