From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id 63FEF45DDB for ; Tue, 11 Apr 2023 15:03:50 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id CA3E568A7E3; Tue, 11 Apr 2023 18:03:47 +0300 (EEST) Received: from out162-62-57-87.mail.qq.com (out162-62-57-87.mail.qq.com [162.62.57.87]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 617526808D8 for ; Tue, 11 Apr 2023 18:03:40 +0300 (EEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=foxmail.com; s=s201512; t=1681225417; bh=l7/oeKwOp07hCoe0XUgMOeZtu7s/wCDL+8gqZs8Wyos=; h=In-Reply-To:References:From:To:Subject:Date; b=tCp69WrQa0fYKxJ2PXV7tWYCC8NWwI20Fb1pzk+H0GjqavREaiAbDHYdZxAvqgVfz 6Y4QJiPqF9QJ7WxWkQ1DV999gnyEK5KsOlSBSGBmNHcB66js1rEjMLK0YmTF5pYapk +rrFXmU4u5RDrZIHGfSDE8MIOCawf1axDmw83wfo= X-QQ-FEAT: oHWrrGTW1dBkUnEbHyTijimPDLI2IvSG X-QQ-SSF: 00000000000000F0000000000000 X-QQ-XMAILINFO: NwI+STeI0wWDNOjfIKkIWu64z4rQ3t6LKcJnL1Ogc6sbC6uVHJ46fx/BCxV3GZ h1IEsR3cUa0Q9L+7pkpFuI9zeX6AhMx7LGfsts7ObnVh5oh+VHcRnL91bUgImP+N4ue7jm8bPdNMK DDbgSkRofB51KfVJjKqtLthZL+TXBM2nGxqbM/BVKkm4oTvUY5efrEEdUWwa9rFY7YIbMYbOKD0k4 1P7V5g7ssCwurMkMDUEUwYxg/fEdswngwAl6Nf1+Q2dzrxNQSTMZl+Kli9RHt/SmdD5mspNnkmXRY XhwXlNzI2H6Fdfec2ST/WDbvloF+60pG74j+bwezvt17w+TC8J5RuJC1bIuhldodDCMWTfaUgmzqw gemGgY7llRyZYHmQlR9QDOhQZz7A+pSE4BxiYuj35g7w4uBcsthglBUD3928+NKqYE9Nx/AonEVtG Fx5Zprj4O1UBt9QsKg0ZN/qz3nEyn9PBI7TvcGAQ16SsgEc98INCaNMgoWwW6pDyb430y6Uy7LLaH AlkRNrHe6IkxRuL0DoDWffcsknmTiXW6lJUbz068Ar1bLY6LZNpcjqzrGsFf9QvrPFYRLCOGOQyR+ 6YOskkQUGtpDM2f6elDez8fP7okSztRVOCUYV+JCglGT5CH2gnZ0dbzCDxZzFQpKP/B0duDxWDgaf Pw40ku6gUpTbG9OCaDgX/hNe61FV5PAMWiya7xGxACqrpIXjCZrFy/GrU668HQZk5d75nrWJC5Alb HAJsKvy6JCtAx8pX50ku2hMJIOWbiQghYLkWwf6IQVzWeNt83jfJGREnINCMiScAJd2V83YEr+hTs WnZw6BtsU14UZgAtQ9vJY4+K3FgH5mg6KdV+BhfIRuhJFVLI/Ye6vWWoBYVMDwqbMpXLd/Wm1cgwP UfQcITpl3F+ulNfLiVYkfkqS1BGtJL8dIH7R2obVlfvQEohCXpD7aR0WkNik1Nt1EKpftbqFhW65r N0JEb2CkhsHjWebNUU X-HAS-ATTACH: no X-QQ-BUSINESS-ORIGIN: 2 X-Originating-IP: 101.86.227.58 In-Reply-To: References: X-QQ-STYLE: X-QQ-mid: webmail416t1681225417t751240 From: "=?ISO-8859-1?B?V2VuemhlV2FuZw==?=" To: "=?ISO-8859-1?B?ZmZtcGVnLWRldmVs?=" Mime-Version: 1.0 Date: Tue, 11 Apr 2023 23:03:37 +0800 X-Priority: 3 Message-ID: X-QQ-MIME: TCMime 1.0 by Tencent X-Mailer: QQMail 2.x X-QQ-Mailer: QQMail 2.x X-Content-Filtered-By: Mailman/MimeDel 2.1.29 Subject: Re: [FFmpeg-devel] [PATCH v1] libavfi/dnn: add Paddle Inference as one of DNN backend X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: Could you please briefly introduce the reason why not adding any dnn backend?  Do you have any plan for the maintenance and development of the dnn backend in the future? From my understanding, the current backend of dnn has tensoflow, openvino and native, but this cannot meet the needs of users. Thus, I believe adding other dnn backends will be great for user experience, user growth, and industrial applications. In particular, various dnn backend can be adapted to different application environments, and there are some emerging inference engines that are faster and stronger, such as Pytorch and Paddle. In addition, from the practical point of view, it is not difficult for a deep learning practitioner to learn and use this framework, but how to choose a framework and apply it in practice, people pay more attention to the effect (recall and precision), and easy deployment, that is, high reasoning performance efficiency. The main reason why Paddle is relatively mainstream and why I want to add paddle backend is that it has a very high efficiency and performance. There are several projects maintained by Paddle, such as paddleDetection, paddleSeg, paddleGAN, paddleOCR and paddleCls have a lot of good pre-training models that migrate well to their own data and has excellent perform ance. Secondly, in terms of reasoning efficiency, Paddle supports many platforms and chips. Models trained using Paddle framework can be directly deployed, and custom device interfaces are open for independent development based on one's own hardware. FFmpeg itself already has very extensive support for codec. If FFmpeg could support the deployment of more reasoning model backend, it would have a wider application. In general, I hope that ffmpeg could support the backend of paddle or more. In any case that my code is not mature or proper, I would be grateful if professionals like you could offer me suggestions and comments. I will be absolutely honored if I could contribute to this project :) Best, Wenzhe Wang WenzheWang wongwwz@foxmail.com   ------------------ Original ------------------ From: "FFmpeg development discussions and patches"