{"id":2689,"date":"2019-10-17T04:41:03","date_gmt":"2019-10-17T04:41:03","guid":{"rendered":"https:\/\/www.thegioimaychu.vn\/blog\/?p=2689"},"modified":"2019-10-23T04:03:22","modified_gmt":"2019-10-23T04:03:22","slug":"diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow","status":"publish","type":"post","link":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/","title":{"rendered":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow"},"content":{"rendered":"<style>.iblink{color:#975!important;}.iblink:hover{color:orange!important;}<\/style><p>Trong blog n\u00e0y, ch\u00fang t\u00f4i \u0111\u00e3 ki\u1ec3m tra \u0111i\u1ec3m chu\u1ea9n GPU NVIDIA GeForce RTX 2080 Ti tr\u00ean khung h\u1ecdc s\u00e2u c\u1ee7a TensorFlow . K\u1ebft qu\u1ea3 c\u1ee7a ch\u00fang t\u00f4i cho th\u1ea5y RTX 2080 Ti cung c\u1ea5p gi\u00e1 tr\u1ecb \u0111\u00e1ng kinh ng\u1ea1c cho gi\u00e1 c\u1ea3. Ch\u00fang t\u00f4i \u0111\u00e3 ch\u1ea1y th\u1eed nghi\u1ec7m tr\u00ean m\u1ed9t trong nh\u1eefng m\u00e1y tr\u1ea1m h\u1ecdc s\u00e2u c\u1ee7a ch\u00fang t\u00f4i (xem th\u00f4ng s\u1ed1 k\u1ef9 thu\u1eadt h\u1ec7 th\u1ed1ng b\u00ean d\u01b0\u1edbi), v\u1edbi nhi\u1ec1u c\u1ea5u h\u00ecnh GPU (1,2,4). V\u1edbi m\u1ee9c gi\u00e1 kh\u1edfi \u0111i\u1ec3m, k\u1ebft qu\u1ea3 c\u1ee7a Turing RTX 2080 Ti th\u1ef1c s\u1ef1 \u0111\u00e1ng ch\u00fa \u00fd cho vi\u1ec7c \u0111\u00e0o t\u1ea1o h\u1ecdc t\u1eadp s\u00e2u. \u0110i\u1ec1u n\u00e0y \u0111\u01b0\u1ee3c th\u1ec3 hi\u1ec7n r\u00f5 h\u01a1n khi so s\u00e1nh hi\u1ec7u su\u1ea5t v\u1edbi Volta Powered TITAN V ( xem blog c\u1ee7a ch\u00fang t\u00f4i \u1edf \u0111\u00e2y ), trong \u0111\u00f3 hi\u1ec7u su\u1ea5t g\u1ea7n nh\u01b0 ngang b\u1eb1ng.<\/p>\n<h2>Benchmark Snapshot: Nasnet, VGG16, Inception V3, ResNET-50<\/h2>\n<p><img decoding=\"async\" src=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/tgmc-blog-5da7f0e55f3c2.jpg\" alt=\"\" \/><\/p>\n<h2>Ph\u01b0\u01a1ng ph\u00e1p \u0111o<\/h2>\n<p>C\u1ea5u h\u00ecnh \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng cho TensorFlow kh\u00f4ng thay \u0111\u1ed5i t\u1eeb \u0111\u1ea7u \u0111\u1ebfn cu\u1ed1i ngo\u1ea1i tr\u1eeb s\u1ed1 l\u01b0\u1ee3ng GPU \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng trong m\u1ed9t l\u1ea7n ch\u1ea1y chu\u1ea9n c\u1ee5 th\u1ec3.<\/p>\n<p><em>Ghi ch\u00fa:<\/em> Ch\u1ee9c n\u0103ng gi\u1eef l\u1ea1i h\u00ecnh \u1ea3nh trong TensorFlow \u0111\u00e3 \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng \u0111\u1ec3 nh\u1eadp d\u1eef li\u1ec7u th\u1ef1c (h\u00ecnh \u1ea3nh) v\u00e0o m\u00f4 h\u00ecnh Nasnet, ch\u1ee9a d\u1eef li\u1ec7u th\u1ef1c bao g\u1ed3m h\u00ecnh \u1ea3nh jpeg c\u1ee7a hoa t\u1eeb b\u1ed9 d\u1eef li\u1ec7u c\u1ee7a h\u00ecnh \u1ea3nh.\u00a0C\u00e1c m\u00f4 h\u00ecnh kh\u00e1c Resnet50, VGG16, InceptionV3, \u0111\u00e3 s\u1eed d\u1ee5ng d\u1eef li\u1ec7u t\u1ed5ng h\u1ee3p, \u0111\u01b0\u1ee3c \u0111o b\u1eb1ng c\u00e1ch s\u1eed d\u1ee5ng d\u1eef li\u1ec7u m\u00e0 kh\u00f4ng c\u00f3 b\u1ea5t k\u1ef3 s\u1eeda \u0111\u1ed5i n\u00e0o \u0111\u01b0\u1ee3c th\u1ef1c hi\u1ec7n trong su\u1ed1t chu k\u1ef3 th\u1eed nghi\u1ec7m.\u00a0C\u00e1c th\u1eed nghi\u1ec7m \u0111\u00e3 ch\u1ea1y b\u1eb1ng c\u00e1ch s\u1eed d\u1ee5ng g\u00f3i python-pip trong th\u1eddi gian ch\u1ea1y Anaconda theo quy \u0111\u1ecbnh trong t\u00e0i li\u1ec7u c\u00e0i \u0111\u1eb7t TensorFlow.<\/p>\n<p>C\u00e1c t\u1eadp l\u1ec7nh chu\u1ea9n \u0111\u00e3 \u0111\u01b0\u1ee3c t\u1ea3i xu\u1ed1ng t\u1eeb github ch\u00ednh th\u1ee9c c\u1ee7a TensorFlow, c\u00f9ng v\u1edbi c\u00e1c m\u00f4 h\u00ecnh \u0111\u01b0\u1ee3c x\u00e2y d\u1ef1ng tr\u01b0\u1edbc.\u00a0Trong m\u1ed7i tr\u01b0\u1eddng h\u1ee3p, c\u00e1c bi\u1ebfn duy nh\u1ea5t thay \u0111\u1ed5i t\u1eeb ch\u1ea1y sang ch\u1ea1y l\u00e0:\u00a0\u00a0num_gpus\u00a0\u00a0v\u00e0\u00a0m\u00f4 h\u00ecnh\u00a0.\u00a0T\u1ea5t c\u1ea3 c\u00e1c th\u00f4ng s\u1ed1 kh\u00e1c kh\u00f4ng thay \u0111\u1ed5i trong su\u1ed1t th\u1eddi gian c\u1ee7a c\u00e1c th\u00ed nghi\u1ec7m n\u00e0y.\u00a0K\u00edch th\u01b0\u1edbc h\u00e0ng lo\u1ea1t \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng l\u00e0 64 cho t\u1ea5t c\u1ea3 \u0111\u00e0o t\u1ea1o, ch\u1ea1y \u1edf m\u1eb7c \u0111\u1ecbnh, \u0111\u1ed9 ch\u00ednh x\u00e1c \u0111\u01a1n (fp32).<\/p>\n<h2>Th\u00f4ng s\u1ed1 k\u1ef9 thu\u1eadt h\u1ec7 th\u1ed1ng m\u00e1y tr\u1ea1m RTX 2080 Ti<\/h2>\n<table>\n<colgroup>\n<col \/>\n<col \/><\/colgroup>\n<tbody>\n<tr>\n<td colspan=\"1\">CPU<\/td>\n<td colspan=\"1\">\u00a02 x Intel Xeon Gold 6148 2.4GHz CPU<\/td>\n<\/tr>\n<tr>\n<td>RAM<\/td>\n<td>192GB DDR4-2666<\/td>\n<\/tr>\n<tr>\n<td>SSD<\/td>\n<td>500 GB SSD<\/td>\n<\/tr>\n<tr>\n<td>GPU<\/td>\n<td>1, 2, 4x NVIDIA GeForce RTX 2080 Ti (blower model)<\/td>\n<\/tr>\n<tr>\n<td>OS<\/td>\n<td>Ubuntu Server 16.04<\/td>\n<\/tr>\n<tr>\n<td>DRIVER<\/td>\n<td>NVIDIA version 396.44<\/td>\n<\/tr>\n<tr>\n<td>CUDA<\/td>\n<td>CUDA Toolkit 9.2<\/td>\n<\/tr>\n<tr>\n<td>Python<\/td>\n<td>v 2.7, pip v8, Anaconda<\/td>\n<\/tr>\n<tr>\n<td>TensorFlow<\/td>\n<td>1.12<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\nNVIDIA GeForce RTX 2080 Ti Deep Learning Benchmark tr\u00ean TensorFlow: c\u1ea5u h\u00ecnh 1, 2 v\u00e0 4 GPU<\/h2>\n<h3>Nasnet Images\/Sec (Real Data)<\/h3>\n<h3><img decoding=\"async\" src=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/tgmc-blog-5da7f0e6da451.jpg\" alt=\"\" \/><\/h3>\n<h3>ResNet-50 Images\/Sec (Synthetic Data)<\/h3>\n<h3><img decoding=\"async\" src=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/tgmc-blog-5da7f0e94cfa8.jpg\" alt=\"\" \/><\/h3>\n<h3>Inception V3 Images\/Sec (Synthetic Data)<\/h3>\n<p><img decoding=\"async\" src=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/tgmc-blog-5da7f0eaf38fb.jpg\" alt=\"\" \/><\/p>\n<h3>VGG16 Images\/Sec (Synthetic Data)<\/h3>\n<h3><img decoding=\"async\" src=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/tgmc-blog-5da7f0ec6ecf1.jpg\" alt=\"\" \/><\/h3>\n<h2>C\u00e1c l\u1ec7nh Nasnet Benchmark &amp; Output tr\u00ean TensorFlow<\/h2>\n<p>B\u00ean d\u01b0\u1edbi c\u00e1c l\u1ec7nh c\u1ee5 th\u1ec3 \u0111\u1ec3 ch\u1ea1y t\u1eebng k\u1ecbch b\u1ea3n \u0111\u01b0\u1ee3c ghi l\u1ea1i tr\u00ean k\u1ebft qu\u1ea3 \u0111i\u1ec3m chu\u1ea9n.\u00a0\u0110\u1ec3 thay \u0111\u1ed5i c\u00e1c m\u00f4 h\u00ecnh m\u1ea1ng th\u1ea7n kinh, ch\u1ec9 c\u1ea7n thay \u0111\u1ed5i\u00a0\u00a0m\u00f4 h\u00ecnh\u00a0\u00a0l\u00e1 c\u1edd t\u1ee9c l\u00e0\u00a0\u00a0m\u00f4 h\u00ecnh = resnet50\u00a0\u0111\u1ec3 \u0111\u00e0o t\u1ea1o c\u00e1c m\u00f4 h\u00ecnh Resnet50 v\u1edbi t\u1ea5t c\u1ea3 c\u00e1c bi\u1ebfn kh\u00e1c nh\u01b0 v\u1eady.<\/p>\n<h2>Nasnet 1 GPU<\/h2>\n<table>\n<tbody>\n<tr>\n<td><code>python tf_cnn_benchmarks.py --data_format=NCHW --batch_size=64 --model=nasnet --optimizer=momentum -- variable_update=replicated --nodistortions --gradient_repacking=8 --num_gpus=1 --num_epochs=90 --weight_decay=1e-4 --data_dir=\/data --train_dir=\/data\/scratch --data_name=imagenet<br \/>\n<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Step Img\/sec total_loss<br \/>\n1 images\/sec: 156.8 +\/- 0 (jitter = 0.0) 7.496<br \/>\n10 images\/sec: 156.7 +\/- 0.5 (jitter = 2.5) 7.345<br \/>\n20 images\/sec: 156.5 +\/- 0.4 (jitter = 1.9) 7.52<br \/>\n30 images\/sec: 156 +\/- 0.3 (jitter = 2.0) 7.41<br \/>\n40 images\/sec: 156.6 +\/- 0.3 (jitter = 2.1) 7.473<br \/>\n50 images\/sec: 156.5 +\/- 0.3 (jitter = 2.1) 7.504<br \/>\n60 images\/sec: 156.2 +\/- 0.3 (jitter = 2.0) 7.509<br \/>\n70 images\/sec: 156.4 +\/- 0.3 (jitter = 2.1) 7.54<br \/>\n80 images\/sec: 156.3 +\/- 0.2 (jitter = 2.0) 7.332<br \/>\n90 images\/sec: 156.3 +\/- 0.2 (jitter = 1.9) 7.583<br \/>\n100 images\/sec: 156.3 +\/- 0.2 (jitter = 2.1) 7.43<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<br \/>\ntotal images\/sec: 156.2<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<\/p>\n<h2>Nasnet 2 GPU<\/h2>\n<table>\n<tbody>\n<tr>\n<td><code>python tf_cnn_benchmarks.py --data_format=NCHW --batch_size=64 --model=nasnet --optimizer=momentum -- variable_update=replicated --nodistortions --gradient_repacking=8 --num_gpus=2 --num_epochs=90 --weight_decay=1e-4 --data_dir=\/data --train_dir=\/data\/scratch --data_name=imagenet<br \/>\n<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Step Img\/sec total_loss<br \/>\n1 images\/sec: 285.8 +\/- 0 (jitter = 0.0) 7.482<br \/>\n10 images\/sec: 288.2 +\/- 1.4 (jitter = 4.6) 7.537<br \/>\n20 images\/sec: 281.7 +\/- 2.5 (jitter = 7.7) 7.488<br \/>\n30 images\/sec: 282.1 +\/- 1.7 (jitter = 6.7) 7.508<br \/>\n40 images\/sec: 282.3 +\/- 1.4 (jitter = 7.7) 7.367<br \/>\n50 images\/sec: 281.1 +\/- 1.2 (jitter = 8.5) 7.498<br \/>\n60 images\/sec: 281.4 +\/- 1.1 (jitter = 8.4) 7.465<br \/>\n70 images\/sec: 280.5 +\/- 1.1 (jitter = 8.6) 7.387<br \/>\n80 images\/sec: 280.3 +\/- 1 (jitter = 9.0) 7.433<br \/>\n90 images\/sec: 279.8 +\/- 0.9 (jitter = 8.5) 7.442<br \/>\n100 images\/sec: 279.9 +\/- 0.8 (jitter = 8.0) 7.353<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<br \/>\ntotal images\/sec: 279.85<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<\/p>\n<h2>Nasnet 4 GPU<\/h2>\n<table>\n<tbody>\n<tr>\n<td><code>python tf_cnn_benchmarks.py --data_format=NCHW --batch_size=64 --model=nasnet --optimizer=momentum -- variable_update=replicated --nodistortions --gradient_repacking=8 --num_gpus=4 --num_epochs=90 --weight_decay=1e-4 --data_dir=\/data --train_dir=\/data\/scratch --data_name=imagenet<br \/>\n<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Step Img\/sec total_loss<br \/>\n1 images\/sec: 507.3 +\/- 0 (jitter = 0.0) 7.549<br \/>\n10 images\/sec: 475.4 +\/- 7.1 (jitter = 29.7) 7.487<br \/>\n20 images\/sec: 467.7 +\/- 7 (jitter = 16.8) 7.525<br \/>\n30 images\/sec: 470.8 +\/- 4.9 (jitter = 11.8) 7.459<br \/>\n40 images\/sec: 473 +\/- 4.1 (jitter = 18.5) 7.419<br \/>\n50 images\/sec: 474.6 +\/- 3.4 (jitter = 18.4) 7.458<br \/>\n60 images\/sec: 477.1 +\/- 3 (jitter = 17.1) 7.481<br \/>\n70 images\/sec: 476.7 +\/- 3.1 (jitter = 18.0) 7.454<br \/>\n80 images\/sec: 477.3 +\/- 2.8 (jitter = 15.7) 7.499<br \/>\n90 images\/sec: 477.9 +\/- 2.5 (jitter = 15.4) 7.411<br \/>\n100 images\/sec: 478.8 +\/- 2.3 (jitter = 15.6) 7.485<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<br \/>\ntotal images\/sec: 478.68<br \/>\n\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014-<\/p>\n<div>____<br \/><b>B\u00e0i vi\u1ebft li\u00ean quan<\/b><\/div>\n<ul>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=23322\">NVIDIA RTX PRO 4500 Blackwell Server Edition: B\u01b0\u1edbc nh\u1ea3y v\u1ecdt t\u1eeb th\u1ebf h\u1ec7 L4 cho h\u1ea1 t\u1ea7ng AI suy lu\u1eadn hi\u1ec7u n\u0103ng cao<\/a><\/li>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=22403\">Th\u1eed so s\u00e1nh m\u00e1y t\u00ednh DGX Spark v\u00e0 m\u1ed9t PC c\u1ea5u h\u00ecnh cao v\u1edbi GPU RTX 5080<\/a><\/li>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=22258\">NVIDIA hi\u1ec7n \u0111ang cung c\u1ea5p nh\u1eefng d\u00f2ng GPU n\u00e0o?<\/a><\/li>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=20284\">H\u01b0\u1edbng d\u1eabn l\u1ef1a ch\u1ecdn GPU ph\u00f9 h\u1ee3p cho AI, Machine Learning<\/a><\/li>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=20884\">C\u1ea3i thi\u1ec7n kh\u1ea3 n\u0103ng l\u00e0m m\u00e1t GPU trong h\u1ea1 t\u1ea7ng AI<\/a><\/li>\n<li><a href=\"https:\/\/thegioimaychu.vn\/blog\/?post_type=post&#038;p=20361\">\u0110\u00e1nh gi\u00e1 GPU m\u00e1y tr\u1ea1m: Nvidia RTX 6000 Ada Generation<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Trong blog n&agrave;y, ch&uacute;ng t&ocirc;i &#273;&atilde; ki&#7875;m tra &#273;i&#7875;m chu&#7849;n GPU NVIDIA GeForce RTX 2080 Ti tr&ecirc;n khung h&#7885;c s&acirc;u c&#7911;a TensorFlow . K&#7871;t qu&#7843; c&#7911;a ch&uacute;ng t&ocirc;i cho th&#7845;y RTX 2080 Ti cung c&#7845;p gi&aacute; tr&#7883; &#273;&aacute;ng kinh ng&#7841;c cho gi&aacute; c&#7843;. Ch&uacute;ng t&ocirc;i &#273;&atilde; ch&#7841;y th&#7917; nghi&#7879;m tr&ecirc;n m&#7897;t trong nh&#7919;ng m&aacute;y tr&#7841;m&#8230;<\/p>\n","protected":false},"author":2,"featured_media":2694,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[3,44],"tags":[304,671,111],"class_list":["post-2689","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-hpc","category-product","tag-geforce","tag-gpu","tag-rtx"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu\" \/>\n<meta name=\"twitter:description\" content=\"Trong blog n&agrave;y, ch&uacute;ng t&ocirc;i &#273;&atilde; ki&#7875;m tra &#273;i&#7875;m chu&#7849;n GPU NVIDIA GeForce RTX 2080 Ti tr&ecirc;n khung h&#7885;c s&acirc;u c&#7911;a TensorFlow . K&#7871;t qu&#7843; c&#7911;a ch&uacute;ng t&ocirc;i cho th&#7845;y RTX 2080 Ti cung c&#7845;p gi&aacute; tr&#7883; &#273;&aacute;ng kinh ng&#7841;c cho gi&aacute; c&#7843;. Ch&uacute;ng t&ocirc;i &#273;&atilde; ch&#7841;y th&#7917; nghi&#7879;m tr&ecirc;n m&#7897;t trong nh&#7919;ng m&aacute;y tr&#7841;m...\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Vanito Hoang\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/\"},\"author\":{\"name\":\"Vanito Hoang\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#\\\/schema\\\/person\\\/feccec179330cfebfaa805639a357d18\"},\"headline\":\"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow\",\"datePublished\":\"2019-10-17T04:41:03+00:00\",\"dateModified\":\"2019-10-23T04:03:22+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/\"},\"wordCount\":888,\"publisher\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2019\\\/10\\\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg\",\"keywords\":[\"geforce\",\"gpu\",\"RTX\"],\"articleSection\":[\"AI - HPC\",\"S\u1ea3n ph\u1ea9m\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/\",\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/\",\"name\":\"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2019\\\/10\\\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg\",\"datePublished\":\"2019-10-17T04:41:03+00:00\",\"dateModified\":\"2019-10-23T04:03:22+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#primaryimage\",\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2019\\\/10\\\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg\",\"contentUrl\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2019\\\/10\\\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg\",\"width\":700,\"height\":393},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/ai-hpc\\\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Trang ch\u1ee7\",\"item\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI - HPC\",\"item\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/.\\\/ai-hpc\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/\",\"name\":\"Blog | TheGioiMayChu\",\"description\":\"C\u1eadp nh\u1eadt xu h\u01b0\u1edbng c\u00f4ng ngh\u1ec7 m\u00e1y ch\u1ee7\",\"publisher\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#organization\",\"name\":\"Blog | TheGioiMayChu\",\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2018\\\/08\\\/cropped-ntcnlog-logo-2.png\",\"contentUrl\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/wp-content\\\/uploads\\\/2018\\\/08\\\/cropped-ntcnlog-logo-2.png\",\"width\":500,\"height\":73,\"caption\":\"Blog | TheGioiMayChu\"},\"image\":{\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/thegioimaychu\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/#\\\/schema\\\/person\\\/feccec179330cfebfaa805639a357d18\",\"name\":\"Vanito Hoang\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g\",\"caption\":\"Vanito Hoang\"},\"url\":\"https:\\\/\\\/thegioimaychu.vn\\\/blog\\\/author\\\/vanito\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/","twitter_card":"summary_large_image","twitter_title":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu","twitter_description":"Trong blog n&agrave;y, ch&uacute;ng t&ocirc;i &#273;&atilde; ki&#7875;m tra &#273;i&#7875;m chu&#7849;n GPU NVIDIA GeForce RTX 2080 Ti tr&ecirc;n khung h&#7885;c s&acirc;u c&#7911;a TensorFlow . K&#7871;t qu&#7843; c&#7911;a ch&uacute;ng t&ocirc;i cho th&#7845;y RTX 2080 Ti cung c&#7845;p gi&aacute; tr&#7883; &#273;&aacute;ng kinh ng&#7841;c cho gi&aacute; c&#7843;. Ch&uacute;ng t&ocirc;i &#273;&atilde; ch&#7841;y th&#7917; nghi&#7879;m tr&ecirc;n m&#7897;t trong nh&#7919;ng m&aacute;y tr&#7841;m...","twitter_image":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg","twitter_misc":{"Written by":"Vanito Hoang","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#article","isPartOf":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/"},"author":{"name":"Vanito Hoang","@id":"https:\/\/thegioimaychu.vn\/blog\/#\/schema\/person\/feccec179330cfebfaa805639a357d18"},"headline":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow","datePublished":"2019-10-17T04:41:03+00:00","dateModified":"2019-10-23T04:03:22+00:00","mainEntityOfPage":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/"},"wordCount":888,"publisher":{"@id":"https:\/\/thegioimaychu.vn\/blog\/#organization"},"image":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#primaryimage"},"thumbnailUrl":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg","keywords":["geforce","gpu","RTX"],"articleSection":["AI - HPC","S\u1ea3n ph\u1ea9m"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/","url":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/","name":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow - Blog | TheGioiMayChu","isPartOf":{"@id":"https:\/\/thegioimaychu.vn\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#primaryimage"},"image":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#primaryimage"},"thumbnailUrl":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg","datePublished":"2019-10-17T04:41:03+00:00","dateModified":"2019-10-23T04:03:22+00:00","breadcrumb":{"@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#primaryimage","url":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg","contentUrl":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2019\/10\/NVIDIA-GeForce-RTX-2080-Ti-Graphics-Card11.jpg","width":700,"height":393},{"@type":"BreadcrumbList","@id":"https:\/\/thegioimaychu.vn\/blog\/ai-hpc\/diem-benchmark-hieu-nang-deep-learning-cua-rtx-2080-ti-tren-tensorflow-p2689\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Trang ch\u1ee7","item":"https:\/\/thegioimaychu.vn\/blog\/"},{"@type":"ListItem","position":2,"name":"AI - HPC","item":"https:\/\/thegioimaychu.vn\/blog\/.\/ai-hpc\/"},{"@type":"ListItem","position":3,"name":"\u0110i\u1ec3m benchmark hi\u1ec7u n\u0103ng deep learning c\u1ee7a RTX 2080 Ti tr\u00ean TensorFlow"}]},{"@type":"WebSite","@id":"https:\/\/thegioimaychu.vn\/blog\/#website","url":"https:\/\/thegioimaychu.vn\/blog\/","name":"Blog | TheGioiMayChu","description":"C\u1eadp nh\u1eadt xu h\u01b0\u1edbng c\u00f4ng ngh\u1ec7 m\u00e1y ch\u1ee7","publisher":{"@id":"https:\/\/thegioimaychu.vn\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/thegioimaychu.vn\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/thegioimaychu.vn\/blog\/#organization","name":"Blog | TheGioiMayChu","url":"https:\/\/thegioimaychu.vn\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/thegioimaychu.vn\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2018\/08\/cropped-ntcnlog-logo-2.png","contentUrl":"https:\/\/thegioimaychu.vn\/blog\/wp-content\/uploads\/2018\/08\/cropped-ntcnlog-logo-2.png","width":500,"height":73,"caption":"Blog | TheGioiMayChu"},"image":{"@id":"https:\/\/thegioimaychu.vn\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/thegioimaychu\/"]},{"@type":"Person","@id":"https:\/\/thegioimaychu.vn\/blog\/#\/schema\/person\/feccec179330cfebfaa805639a357d18","name":"Vanito Hoang","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e8187f37f72d74f9380a1367c8c530debee44f226a3301f0765c68f7cc1f3fa4?s=96&d=mm&r=g","caption":"Vanito Hoang"},"url":"https:\/\/thegioimaychu.vn\/blog\/author\/vanito\/"}]}},"_links":{"self":[{"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/posts\/2689","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/comments?post=2689"}],"version-history":[{"count":2,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/posts\/2689\/revisions"}],"predecessor-version":[{"id":2770,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/posts\/2689\/revisions\/2770"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/media\/2694"}],"wp:attachment":[{"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/media?parent=2689"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/categories?post=2689"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/thegioimaychu.vn\/blog\/wp-json\/wp\/v2\/tags?post=2689"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}