From dev-return-4285-archive-asf-public=cust-asf.ponee.io@singa.apache.org Thu Feb 20 08:36:25 2020 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [207.244.88.153]) by mx-eu-01.ponee.io (Postfix) with SMTP id 6817818065D for ; Thu, 20 Feb 2020 09:36:25 +0100 (CET) Received: (qmail 26102 invoked by uid 500); 20 Feb 2020 08:36:24 -0000 Mailing-List: contact dev-help@singa.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@singa.apache.org Delivered-To: mailing list dev@singa.apache.org Received: (qmail 26092 invoked by uid 99); 20 Feb 2020 08:36:24 -0000 Received: from ec2-52-202-80-70.compute-1.amazonaws.com (HELO gitbox.apache.org) (52.202.80.70) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 20 Feb 2020 08:36:24 +0000 From: GitBox To: dev@singa.apache.org Subject: [GitHub] [singa] chrishkchris edited a comment on issue #591: Dev branch cpu training problem (with conv and pool) Message-ID: <158218778454.1291.16442192016600217285.gitbox@gitbox.apache.org> References: In-Reply-To: Date: Thu, 20 Feb 2020 08:36:24 -0000 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit chrishkchris edited a comment on issue #591: Dev branch cpu training problem (with conv and pool) URL: https://github.com/apache/singa/issues/591#issuecomment-588757118 @dcslin Thank you so much! It is much much faster than before, I will wait for 10 epoch to make sure that the training loss is also okay ``` root@71b7b910ae0b:~/dcsysh/singa/examples/autograd# python3 mnist_cnn.py Starting Epoch 0: Training loss = 577.733337, training accuracy = 0.796858 Evaluation accuracy = 0.937300, Elapsed Time = 139.402045s Starting Epoch 1: Training loss = 234.865036, training accuracy = 0.920891 Evaluation accuracy = 0.954327, Elapsed Time = 138.340753s Starting Epoch 2: Training loss = 174.085022, training accuracy = 0.941402 Evaluation accuracy = 0.973157, Elapsed Time = 138.636959s Starting Epoch 3: Training loss = 137.803268, training accuracy = 0.953475 Evaluation accuracy = 0.966246, Elapsed Time = 138.846091s Starting Epoch 4: Training loss = 116.644051, training accuracy = 0.961963 Evaluation accuracy = 0.974459, Elapsed Time = 139.520643s ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: users@infra.apache.org With regards, Apache Git Services