| { |
| "cells": [ |
| { |
| "cell_type": "markdown", |
| "metadata": {}, |
| "source": [ |
| "# Train CIFAR-10 CNN model\n", |
| "using MXNet's \"Module\" interface" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 1, |
| "metadata": { |
| "collapsed": false |
| }, |
| "outputs": [], |
| "source": [ |
| "import mxnet\n", |
| "import mxnet as mx\n", |
| "import train_cifar10" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 2, |
| "metadata": { |
| "collapsed": true |
| }, |
| "outputs": [], |
| "source": [ |
| "# Set up the hyper-parameters\n", |
| "args = train_cifar10.command_line_args(defaults=True)\n", |
| "args.gpus = \"0\"\n", |
| "#args.network = \"lenet\" # Fast, not very accurate\n", |
| "#args.network = \"inception-bn-28-small\" # Much more accurate & slow" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 3, |
| "metadata": { |
| "collapsed": false |
| }, |
| "outputs": [ |
| { |
| "data": { |
| "text/html": [ |
| "\n", |
| " <div class=\"bk-root\">\n", |
| " <a href=\"http://bokeh.pydata.org\" target=\"_blank\" class=\"bk-logo bk-logo-small bk-logo-notebook\"></a>\n", |
| " <span id=\"32effd9a-c11b-4a18-86b1-2c6781cf5027\">Loading BokehJS ...</span>\n", |
| " </div>" |
| ] |
| }, |
| "metadata": {}, |
| "output_type": "display_data" |
| }, |
| { |
| "data": { |
| "application/javascript": [ |
| "\n", |
| "(function(global) {\n", |
| " function now() {\n", |
| " return new Date();\n", |
| " }\n", |
| "\n", |
| " var force = \"1\";\n", |
| "\n", |
| " if (typeof (window._bokeh_onload_callbacks) === \"undefined\" || force !== \"\") {\n", |
| " window._bokeh_onload_callbacks = [];\n", |
| " window._bokeh_is_loading = undefined;\n", |
| " }\n", |
| "\n", |
| "\n", |
| " \n", |
| " if (typeof (window._bokeh_timeout) === \"undefined\" || force !== \"\") {\n", |
| " window._bokeh_timeout = Date.now() + 5000;\n", |
| " window._bokeh_failed_load = false;\n", |
| " }\n", |
| "\n", |
| " var NB_LOAD_WARNING = {'data': {'text/html':\n", |
| " \"<div style='background-color: #fdd'>\\n\"+\n", |
| " \"<p>\\n\"+\n", |
| " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", |
| " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", |
| " \"</p>\\n\"+\n", |
| " \"<ul>\\n\"+\n", |
| " \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n", |
| " \"<li>use INLINE resources instead, as so:</li>\\n\"+\n", |
| " \"</ul>\\n\"+\n", |
| " \"<code>\\n\"+\n", |
| " \"from bokeh.resources import INLINE\\n\"+\n", |
| " \"output_notebook(resources=INLINE)\\n\"+\n", |
| " \"</code>\\n\"+\n", |
| " \"</div>\"}};\n", |
| "\n", |
| " function display_loaded() {\n", |
| " if (window.Bokeh !== undefined) {\n", |
| " Bokeh.$(\"#32effd9a-c11b-4a18-86b1-2c6781cf5027\").text(\"BokehJS successfully loaded.\");\n", |
| " } else if (Date.now() < window._bokeh_timeout) {\n", |
| " setTimeout(display_loaded, 100)\n", |
| " }\n", |
| " }\n", |
| "\n", |
| " function run_callbacks() {\n", |
| " window._bokeh_onload_callbacks.forEach(function(callback) { callback() });\n", |
| " delete window._bokeh_onload_callbacks\n", |
| " console.info(\"Bokeh: all callbacks have finished\");\n", |
| " }\n", |
| "\n", |
| " function load_libs(js_urls, callback) {\n", |
| " window._bokeh_onload_callbacks.push(callback);\n", |
| " if (window._bokeh_is_loading > 0) {\n", |
| " console.log(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", |
| " return null;\n", |
| " }\n", |
| " if (js_urls == null || js_urls.length === 0) {\n", |
| " run_callbacks();\n", |
| " return null;\n", |
| " }\n", |
| " console.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", |
| " window._bokeh_is_loading = js_urls.length;\n", |
| " for (var i = 0; i < js_urls.length; i++) {\n", |
| " var url = js_urls[i];\n", |
| " var s = document.createElement('script');\n", |
| " s.src = url;\n", |
| " s.async = false;\n", |
| " s.onreadystatechange = s.onload = function() {\n", |
| " window._bokeh_is_loading--;\n", |
| " if (window._bokeh_is_loading === 0) {\n", |
| " console.log(\"Bokeh: all BokehJS libraries loaded\");\n", |
| " run_callbacks()\n", |
| " }\n", |
| " };\n", |
| " s.onerror = function() {\n", |
| " console.warn(\"failed to load library \" + url);\n", |
| " };\n", |
| " console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", |
| " document.getElementsByTagName(\"head\")[0].appendChild(s);\n", |
| " }\n", |
| " };var element = document.getElementById(\"32effd9a-c11b-4a18-86b1-2c6781cf5027\");\n", |
| " if (element == null) {\n", |
| " console.log(\"Bokeh: ERROR: autoload.js configured with elementid '32effd9a-c11b-4a18-86b1-2c6781cf5027' but no matching script tag was found. \")\n", |
| " return false;\n", |
| " }\n", |
| "\n", |
| " var js_urls = ['https://cdn.pydata.org/bokeh/release/bokeh-0.12.3.min.js', 'https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.3.min.js'];\n", |
| "\n", |
| " var inline_js = [\n", |
| " function(Bokeh) {\n", |
| " Bokeh.set_log_level(\"info\");\n", |
| " },\n", |
| " \n", |
| " function(Bokeh) {\n", |
| " \n", |
| " Bokeh.$(\"#32effd9a-c11b-4a18-86b1-2c6781cf5027\").text(\"BokehJS is loading...\");\n", |
| " },\n", |
| " function(Bokeh) {\n", |
| " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-0.12.3.min.css\");\n", |
| " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.3.min.css\");\n", |
| " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.3.min.css\");\n", |
| " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.3.min.css\");\n", |
| " }\n", |
| " ];\n", |
| "\n", |
| " function run_inline_js() {\n", |
| " \n", |
| " if ((window.Bokeh !== undefined) || (force === \"1\")) {\n", |
| " for (var i = 0; i < inline_js.length; i++) {\n", |
| " inline_js[i](window.Bokeh);\n", |
| " }if (force === \"1\") {\n", |
| " display_loaded();\n", |
| " }} else if (Date.now() < window._bokeh_timeout) {\n", |
| " setTimeout(run_inline_js, 100);\n", |
| " } else if (!window._bokeh_failed_load) {\n", |
| " console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n", |
| " window._bokeh_failed_load = true;\n", |
| " } else if (!force) {\n", |
| " var cell = $(\"#32effd9a-c11b-4a18-86b1-2c6781cf5027\").parents('.cell').data().cell;\n", |
| " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", |
| " }\n", |
| "\n", |
| " }\n", |
| "\n", |
| " if (window._bokeh_is_loading === 0) {\n", |
| " console.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", |
| " run_inline_js();\n", |
| " } else {\n", |
| " load_libs(js_urls, function() {\n", |
| " console.log(\"Bokeh: BokehJS plotting callback run at\", now());\n", |
| " run_inline_js();\n", |
| " });\n", |
| " }\n", |
| "}(this));" |
| ] |
| }, |
| "metadata": {}, |
| "output_type": "display_data" |
| }, |
| { |
| "data": { |
| "text/html": [ |
| "\n", |
| "\n", |
| " <div class=\"bk-root\">\n", |
| " <div class=\"plotdiv\" id=\"8813280e-065e-435d-846c-31a252dddcc7\"></div>\n", |
| " </div>\n", |
| "<script type=\"text/javascript\">\n", |
| " \n", |
| " (function(global) {\n", |
| " function now() {\n", |
| " return new Date();\n", |
| " }\n", |
| " \n", |
| " var force = \"\";\n", |
| " \n", |
| " if (typeof (window._bokeh_onload_callbacks) === \"undefined\" || force !== \"\") {\n", |
| " window._bokeh_onload_callbacks = [];\n", |
| " window._bokeh_is_loading = undefined;\n", |
| " }\n", |
| " \n", |
| " \n", |
| " \n", |
| " if (typeof (window._bokeh_timeout) === \"undefined\" || force !== \"\") {\n", |
| " window._bokeh_timeout = Date.now() + 0;\n", |
| " window._bokeh_failed_load = false;\n", |
| " }\n", |
| " \n", |
| " var NB_LOAD_WARNING = {'data': {'text/html':\n", |
| " \"<div style='background-color: #fdd'>\\n\"+\n", |
| " \"<p>\\n\"+\n", |
| " \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n", |
| " \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n", |
| " \"</p>\\n\"+\n", |
| " \"<ul>\\n\"+\n", |
| " \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n", |
| " \"<li>use INLINE resources instead, as so:</li>\\n\"+\n", |
| " \"</ul>\\n\"+\n", |
| " \"<code>\\n\"+\n", |
| " \"from bokeh.resources import INLINE\\n\"+\n", |
| " \"output_notebook(resources=INLINE)\\n\"+\n", |
| " \"</code>\\n\"+\n", |
| " \"</div>\"}};\n", |
| " \n", |
| " function display_loaded() {\n", |
| " if (window.Bokeh !== undefined) {\n", |
| " Bokeh.$(\"#8813280e-065e-435d-846c-31a252dddcc7\").text(\"BokehJS successfully loaded.\");\n", |
| " } else if (Date.now() < window._bokeh_timeout) {\n", |
| " setTimeout(display_loaded, 100)\n", |
| " }\n", |
| " }if ((window.Jupyter !== undefined) && Jupyter.notebook.kernel) {\n", |
| " comm_manager = Jupyter.notebook.kernel.comm_manager\n", |
| " comm_manager.register_target(\"29afa51c-a944-4f51-8ffa-a03b925a1f47\", function () {});\n", |
| " }\n", |
| " \n", |
| " function run_callbacks() {\n", |
| " window._bokeh_onload_callbacks.forEach(function(callback) { callback() });\n", |
| " delete window._bokeh_onload_callbacks\n", |
| " console.info(\"Bokeh: all callbacks have finished\");\n", |
| " }\n", |
| " \n", |
| " function load_libs(js_urls, callback) {\n", |
| " window._bokeh_onload_callbacks.push(callback);\n", |
| " if (window._bokeh_is_loading > 0) {\n", |
| " console.log(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n", |
| " return null;\n", |
| " }\n", |
| " if (js_urls == null || js_urls.length === 0) {\n", |
| " run_callbacks();\n", |
| " return null;\n", |
| " }\n", |
| " console.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", |
| " window._bokeh_is_loading = js_urls.length;\n", |
| " for (var i = 0; i < js_urls.length; i++) {\n", |
| " var url = js_urls[i];\n", |
| " var s = document.createElement('script');\n", |
| " s.src = url;\n", |
| " s.async = false;\n", |
| " s.onreadystatechange = s.onload = function() {\n", |
| " window._bokeh_is_loading--;\n", |
| " if (window._bokeh_is_loading === 0) {\n", |
| " console.log(\"Bokeh: all BokehJS libraries loaded\");\n", |
| " run_callbacks()\n", |
| " }\n", |
| " };\n", |
| " s.onerror = function() {\n", |
| " console.warn(\"failed to load library \" + url);\n", |
| " };\n", |
| " console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", |
| " document.getElementsByTagName(\"head\")[0].appendChild(s);\n", |
| " }\n", |
| " };var element = document.getElementById(\"8813280e-065e-435d-846c-31a252dddcc7\");\n", |
| " if (element == null) {\n", |
| " console.log(\"Bokeh: ERROR: autoload.js configured with elementid '8813280e-065e-435d-846c-31a252dddcc7' but no matching script tag was found. \")\n", |
| " return false;\n", |
| " }\n", |
| " \n", |
| " var js_urls = [];\n", |
| " \n", |
| " var inline_js = [\n", |
| " function(Bokeh) {\n", |
| " Bokeh.$(function() {\n", |
| " var docs_json = {\"f847dff6-ab8a-4fd1-8be0-e79b39334749\":{\"roots\":{\"references\":[{\"attributes\":{\"months\":[0,6]},\"id\":\"dd14ae70-3ab7-4fd4-8fae-0e8db050826a\",\"type\":\"MonthsTicker\"},{\"attributes\":{\"months\":[0,1,2,3,4,5,6,7,8,9,10,11]},\"id\":\"e21f9d30-e2e0-491a-abaf-5ead1f475c72\",\"type\":\"MonthsTicker\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"line_width\":{\"value\":2},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"6aa5fde0-6aa4-434b-8f87-1bb3def62ed1\",\"type\":\"Circle\"},{\"attributes\":{\"line_color\":{\"value\":\"green\"},\"line_width\":{\"value\":2},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"4d07fb5a-33b4-404a-9379-5ab6938da677\",\"type\":\"Line\"},{\"attributes\":{\"data_source\":{\"id\":\"21f9bad6-481d-41fb-b974-57ea3ff7f1af\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"831a2985-7d96-4db7-a559-e2926d17a7f6\",\"type\":\"Line\"},\"hover_glyph\":null,\"nonselection_glyph\":{\"id\":\"8d48b39d-05ce-4f28-8b5d-9be03475c1d4\",\"type\":\"Line\"},\"selection_glyph\":null},\"id\":\"7f62ddb4-114c-4896-86c3-96750fb8def6\",\"type\":\"GlyphRenderer\"},{\"attributes\":{},\"id\":\"74e596f1-3572-46b8-a214-6df3913ca9fb\",\"type\":\"BasicTicker\"},{\"attributes\":{},\"id\":\"29773c7b-27c0-48ff-b0f6-d0a88692670d\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"months\":[0,4,8]},\"id\":\"b194d165-b586-46fa-bb52-8f0f4bd493c4\",\"type\":\"MonthsTicker\"},{\"attributes\":{\"max_interval\":500.0,\"num_minor_ticks\":0},\"id\":\"774141d7-0706-4a09-9db0-86453495a676\",\"type\":\"AdaptiveTicker\"},{\"attributes\":{\"callback\":null,\"column_names\":[\"y\",\"x\"],\"data\":{\"x\":[],\"y\":[]}},\"id\":\"6d64ac4e-6e15-4c79-8309-b4764aca4f61\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"base\":60,\"mantissas\":[1,2,5,10,15,20,30],\"max_interval\":1800000.0,\"min_interval\":1000.0,\"num_minor_ticks\":0},\"id\":\"6f4ee18d-44f0-447c-96d4-4cbd2630f382\",\"type\":\"AdaptiveTicker\"},{\"attributes\":{\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"line_width\":{\"value\":2},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"d030fc41-922e-4c4a-9636-c12f9e0ba354\",\"type\":\"Line\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"size\":{\"units\":\"screen\",\"value\":1.5},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"9108b55f-4dfc-4d16-a21a-5a85cc88b4c4\",\"type\":\"Circle\"},{\"attributes\":{\"plot\":null,\"text\":null},\"id\":\"f886da61-3674-459d-aaae-4baaed554f3d\",\"type\":\"Title\"},{\"attributes\":{\"num_minor_ticks\":5},\"id\":\"6d5a77bf-c5d8-40ca-b997-29e48d5dc622\",\"type\":\"DatetimeTicker\"},{\"attributes\":{\"callback\":null},\"id\":\"d2fe6612-09b0-46be-8673-4e609aafb3fb\",\"type\":\"DataRange1d\"},{\"attributes\":{\"callback\":null},\"id\":\"8a4f53ae-29b3-4b01-80f2-68f274c3bc2b\",\"type\":\"DataRange1d\"},{\"attributes\":{\"data_source\":{\"id\":\"ea1acf82-c85c-43eb-9140-b309fa0b0017\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"6632addc-9e3a-4324-8684-1c3eeef1a580\",\"type\":\"Circle\"},\"hover_glyph\":null,\"nonselection_glyph\":{\"id\":\"9108b55f-4dfc-4d16-a21a-5a85cc88b4c4\",\"type\":\"Circle\"},\"selection_glyph\":null,\"visible\":false},\"id\":\"ea4cefb9-dbd6-45d8-bab8-326a9ca2833e\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"93dfa78a-816c-488a-b683-d46589aff77c\",\"type\":\"WheelZoomTool\"},{\"attributes\":{\"axis_label\":\"Training time\",\"formatter\":{\"id\":\"72c7824a-3c1f-49c1-a876-008f33b70b68\",\"type\":\"DatetimeTickFormatter\"},\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"6d5a77bf-c5d8-40ca-b997-29e48d5dc622\",\"type\":\"DatetimeTicker\"}},\"id\":\"185f2429-2cf6-47c4-b89d-143b83f8eb6e\",\"type\":\"DatetimeAxis\"},{\"attributes\":{\"line_alpha\":{\"value\":0.3},\"line_color\":{\"value\":\"#1f77b4\"},\"line_dash\":[2,4],\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"831a2985-7d96-4db7-a559-e2926d17a7f6\",\"type\":\"Line\"},{\"attributes\":{\"data_source\":{\"id\":\"728724cd-5ad3-467e-8694-65cfd5c8892b\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"4d07fb5a-33b4-404a-9379-5ab6938da677\",\"type\":\"Line\"},\"hover_glyph\":null,\"nonselection_glyph\":{\"id\":\"d030fc41-922e-4c4a-9636-c12f9e0ba354\",\"type\":\"Line\"},\"selection_glyph\":null},\"id\":\"583cb19e-e81f-4229-a03e-300ccdad69cb\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"ba102579-4371-4d46-8efe-bb63bf5ac700\",\"type\":\"HelpTool\"},{\"attributes\":{\"months\":[0,2,4,6,8,10]},\"id\":\"b4273502-7ddf-4316-ba03-e9d77406d017\",\"type\":\"MonthsTicker\"},{\"attributes\":{\"days\":[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31]},\"id\":\"9b38934f-2246-4fd5-9629-5fed9577c817\",\"type\":\"DaysTicker\"},{\"attributes\":{\"base\":24,\"mantissas\":[1,2,4,6,8,12],\"max_interval\":43200000.0,\"min_interval\":3600000.0,\"num_minor_ticks\":0},\"id\":\"a89af1c1-53cf-4c7f-a03e-4efb8298b516\",\"type\":\"AdaptiveTicker\"},{\"attributes\":{\"overlay\":{\"id\":\"05eb39ff-3243-4ceb-b390-6b539d2277e7\",\"type\":\"BoxAnnotation\"},\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"ea5c46b7-fbb1-41ec-89ec-915d4f00a7f3\",\"type\":\"BoxZoomTool\"},{\"attributes\":{\"bottom_units\":\"screen\",\"fill_alpha\":{\"value\":0.5},\"fill_color\":{\"value\":\"lightgrey\"},\"left_units\":\"screen\",\"level\":\"overlay\",\"line_alpha\":{\"value\":1.0},\"line_color\":{\"value\":\"black\"},\"line_dash\":[4,4],\"line_width\":{\"value\":2},\"plot\":null,\"render_mode\":\"css\",\"right_units\":\"screen\",\"top_units\":\"screen\"},\"id\":\"05eb39ff-3243-4ceb-b390-6b539d2277e7\",\"type\":\"BoxAnnotation\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"7eea0ddb-db8d-46ce-9fe0-96366980bfd2\",\"type\":\"ResetTool\"},{\"attributes\":{\"items\":[{\"id\":\"ef08bd27-c2f3-49ee-a09f-d729c90b644b\",\"type\":\"LegendItem\"},{\"id\":\"a9a5b513-4ef8-40df-b5c1-4edb707de048\",\"type\":\"LegendItem\"}],\"location\":\"bottom_right\",\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"30269d85-9497-46a2-b4f0-115998ba1f00\",\"type\":\"Legend\"},{\"attributes\":{},\"id\":\"72c7824a-3c1f-49c1-a876-008f33b70b68\",\"type\":\"DatetimeTickFormatter\"},{\"attributes\":{\"data_source\":{\"id\":\"6d64ac4e-6e15-4c79-8309-b4764aca4f61\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"bcd89277-296a-4318-b2eb-0591d6520177\",\"type\":\"Circle\"},\"hover_glyph\":null,\"nonselection_glyph\":{\"id\":\"6aa5fde0-6aa4-434b-8f87-1bb3def62ed1\",\"type\":\"Circle\"},\"selection_glyph\":null},\"id\":\"809e6336-d5b0-43d3-9337-3d380d4b02a9\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"days\":[1,4,7,10,13,16,19,22,25,28]},\"id\":\"4e9b3062-36eb-4149-adad-c7a4b0ba96aa\",\"type\":\"DaysTicker\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.3},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.3},\"line_color\":{\"value\":\"#1f77b4\"},\"size\":{\"units\":\"screen\",\"value\":1.5},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"6632addc-9e3a-4324-8684-1c3eeef1a580\",\"type\":\"Circle\"},{\"attributes\":{\"callback\":null,\"column_names\":[\"y\",\"x\"],\"data\":{\"x\":[],\"y\":[]}},\"id\":\"21f9bad6-481d-41fb-b974-57ea3ff7f1af\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"active_drag\":\"auto\",\"active_scroll\":\"auto\",\"active_tap\":\"auto\",\"tools\":[{\"id\":\"4217886e-0f96-45d8-be38-754aac40e061\",\"type\":\"PanTool\"},{\"id\":\"93dfa78a-816c-488a-b683-d46589aff77c\",\"type\":\"WheelZoomTool\"},{\"id\":\"ea5c46b7-fbb1-41ec-89ec-915d4f00a7f3\",\"type\":\"BoxZoomTool\"},{\"id\":\"f00d301e-eb5f-475a-999f-05da8346f3a1\",\"type\":\"SaveTool\"},{\"id\":\"7eea0ddb-db8d-46ce-9fe0-96366980bfd2\",\"type\":\"ResetTool\"},{\"id\":\"ba102579-4371-4d46-8efe-bb63bf5ac700\",\"type\":\"HelpTool\"}]},\"id\":\"ab630684-4927-4f7d-92fc-a7e63db0f9c0\",\"type\":\"Toolbar\"},{\"attributes\":{\"callback\":null,\"column_names\":[\"y\",\"x\"],\"data\":{\"x\":[],\"y\":[]}},\"id\":\"728724cd-5ad3-467e-8694-65cfd5c8892b\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"below\":[{\"id\":\"185f2429-2cf6-47c4-b89d-143b83f8eb6e\",\"type\":\"DatetimeAxis\"}],\"left\":[{\"id\":\"98eaea83-2f3a-4f09-a273-b5102bb1e852\",\"type\":\"LinearAxis\"}],\"renderers\":[{\"id\":\"185f2429-2cf6-47c4-b89d-143b83f8eb6e\",\"type\":\"DatetimeAxis\"},{\"id\":\"5964d98a-e17a-438b-b745-f21169bd1fb2\",\"type\":\"Grid\"},{\"id\":\"98eaea83-2f3a-4f09-a273-b5102bb1e852\",\"type\":\"LinearAxis\"},{\"id\":\"87b53edb-380a-4245-8c59-a548946c329a\",\"type\":\"Grid\"},{\"id\":\"05eb39ff-3243-4ceb-b390-6b539d2277e7\",\"type\":\"BoxAnnotation\"},{\"id\":\"30269d85-9497-46a2-b4f0-115998ba1f00\",\"type\":\"Legend\"},{\"id\":\"7f62ddb4-114c-4896-86c3-96750fb8def6\",\"type\":\"GlyphRenderer\"},{\"id\":\"ea4cefb9-dbd6-45d8-bab8-326a9ca2833e\",\"type\":\"GlyphRenderer\"},{\"id\":\"583cb19e-e81f-4229-a03e-300ccdad69cb\",\"type\":\"GlyphRenderer\"},{\"id\":\"809e6336-d5b0-43d3-9337-3d380d4b02a9\",\"type\":\"GlyphRenderer\"}],\"title\":{\"id\":\"f886da61-3674-459d-aaae-4baaed554f3d\",\"type\":\"Title\"},\"tool_events\":{\"id\":\"d34d14c5-5ce6-4e0a-b4a6-6dd2716c6aeb\",\"type\":\"ToolEvents\"},\"toolbar\":{\"id\":\"ab630684-4927-4f7d-92fc-a7e63db0f9c0\",\"type\":\"Toolbar\"},\"x_range\":{\"id\":\"d2fe6612-09b0-46be-8673-4e609aafb3fb\",\"type\":\"DataRange1d\"},\"y_range\":{\"id\":\"8a4f53ae-29b3-4b01-80f2-68f274c3bc2b\",\"type\":\"DataRange1d\"}},\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"},{\"attributes\":{\"days\":[1,8,15,22]},\"id\":\"1f26da1d-bc54-4d8c-a3b7-8cda2999af19\",\"type\":\"DaysTicker\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"4217886e-0f96-45d8-be38-754aac40e061\",\"type\":\"PanTool\"},{\"attributes\":{\"axis_label\":\"accuracy\",\"formatter\":{\"id\":\"29773c7b-27c0-48ff-b0f6-d0a88692670d\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"74e596f1-3572-46b8-a214-6df3913ca9fb\",\"type\":\"BasicTicker\"}},\"id\":\"98eaea83-2f3a-4f09-a273-b5102bb1e852\",\"type\":\"LinearAxis\"},{\"attributes\":{\"days\":[1,15]},\"id\":\"e4644a83-5617-4c12-92d6-d388a49e81a7\",\"type\":\"DaysTicker\"},{\"attributes\":{},\"id\":\"d34d14c5-5ce6-4e0a-b4a6-6dd2716c6aeb\",\"type\":\"ToolEvents\"},{\"attributes\":{\"callback\":null,\"column_names\":[\"y\",\"x\"],\"data\":{\"x\":[],\"y\":[]}},\"id\":\"ea1acf82-c85c-43eb-9140-b309fa0b0017\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"6d5a77bf-c5d8-40ca-b997-29e48d5dc622\",\"type\":\"DatetimeTicker\"}},\"id\":\"5964d98a-e17a-438b-b745-f21169bd1fb2\",\"type\":\"Grid\"},{\"attributes\":{\"fill_color\":{\"value\":\"#1f77b4\"},\"line_color\":{\"value\":\"green\"},\"line_width\":{\"value\":2},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"bcd89277-296a-4318-b2eb-0591d6520177\",\"type\":\"Circle\"},{\"attributes\":{\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"}},\"id\":\"f00d301e-eb5f-475a-999f-05da8346f3a1\",\"type\":\"SaveTool\"},{\"attributes\":{},\"id\":\"cfd5663b-aa9e-4931-9fc1-732dbe3e382f\",\"type\":\"YearsTicker\"},{\"attributes\":{\"label\":{\"value\":\"train\"},\"renderers\":[{\"id\":\"7f62ddb4-114c-4896-86c3-96750fb8def6\",\"type\":\"GlyphRenderer\"},{\"id\":\"ea4cefb9-dbd6-45d8-bab8-326a9ca2833e\",\"type\":\"GlyphRenderer\"}]},\"id\":\"ef08bd27-c2f3-49ee-a09f-d729c90b644b\",\"type\":\"LegendItem\"},{\"attributes\":{\"label\":{\"value\":\"validation\"},\"renderers\":[{\"id\":\"583cb19e-e81f-4229-a03e-300ccdad69cb\",\"type\":\"GlyphRenderer\"}]},\"id\":\"a9a5b513-4ef8-40df-b5c1-4edb707de048\",\"type\":\"LegendItem\"},{\"attributes\":{\"dimension\":1,\"plot\":{\"id\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"74e596f1-3572-46b8-a214-6df3913ca9fb\",\"type\":\"BasicTicker\"}},\"id\":\"87b53edb-380a-4245-8c59-a548946c329a\",\"type\":\"Grid\"},{\"attributes\":{\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"line_dash\":[2,4],\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"8d48b39d-05ce-4f28-8b5d-9be03475c1d4\",\"type\":\"Line\"}],\"root_ids\":[\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\"]},\"title\":\"Bokeh Application\",\"version\":\"0.12.3\"}};\n", |
| " var render_items = [{\"docid\":\"f847dff6-ab8a-4fd1-8be0-e79b39334749\",\"elementid\":\"8813280e-065e-435d-846c-31a252dddcc7\",\"modelid\":\"01107ba2-ae75-41b0-bddc-5e93690ea7e8\",\"notebook_comms_target\":\"29afa51c-a944-4f51-8ffa-a03b925a1f47\"}];\n", |
| " \n", |
| " Bokeh.embed.embed_items(docs_json, render_items);\n", |
| " });\n", |
| " },\n", |
| " function(Bokeh) {\n", |
| " }\n", |
| " ];\n", |
| " \n", |
| " function run_inline_js() {\n", |
| " \n", |
| " if ((window.Bokeh !== undefined) || (force === \"1\")) {\n", |
| " for (var i = 0; i < inline_js.length; i++) {\n", |
| " inline_js[i](window.Bokeh);\n", |
| " }if (force === \"1\") {\n", |
| " display_loaded();\n", |
| " }} else if (Date.now() < window._bokeh_timeout) {\n", |
| " setTimeout(run_inline_js, 100);\n", |
| " } else if (!window._bokeh_failed_load) {\n", |
| " console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n", |
| " window._bokeh_failed_load = true;\n", |
| " } else if (!force) {\n", |
| " var cell = $(\"#8813280e-065e-435d-846c-31a252dddcc7\").parents('.cell').data().cell;\n", |
| " cell.output_area.append_execute_result(NB_LOAD_WARNING)\n", |
| " }\n", |
| " \n", |
| " }\n", |
| " \n", |
| " if (window._bokeh_is_loading === 0) {\n", |
| " console.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", |
| " run_inline_js();\n", |
| " } else {\n", |
| " load_libs(js_urls, function() {\n", |
| " console.log(\"Bokeh: BokehJS plotting callback run at\", now());\n", |
| " run_inline_js();\n", |
| " });\n", |
| " }\n", |
| " }(this));\n", |
| "</script>" |
| ] |
| }, |
| "metadata": {}, |
| "output_type": "display_data" |
| } |
| ], |
| "source": [ |
| "# Configure charts to plot while training\n", |
| "from mxnet.notebook.callback import LiveLearningCurve\n", |
| "cb_args = LiveLearningCurve('accuracy', 5).callback_args()" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 4, |
| "metadata": { |
| "collapsed": false, |
| "scrolled": false |
| }, |
| "outputs": [ |
| { |
| "name": "stderr", |
| "output_type": "stream", |
| "text": [ |
| "2016-11-04 18:05:30,714 Node[0] start with arguments Namespace(batch_size=128, data_dir='/efs/datasets/users/leodirac/code/workplace/leodirac/mxnet/example/image-classification/cifar10/', gpus='0', kv_store='local', load_epoch=None, lr=0.05, lr_factor=1, lr_factor_epoch=1, model_prefix=None, network='inception-bn-28-small', num_epochs=20, num_examples=60000, save_model_prefix=None)\n", |
| "2016-11-04 18:05:30,715 Node[0] running on ip-172-31-59-245\n", |
| "2016-11-04 18:05:32,172 Node[0] Starting with devices [gpu(0)]\n", |
| "2016-11-04 18:05:32,175 Node[0] start training for 20 epochs...\n", |
| "2016-11-04 18:07:11,468 Node[0] Epoch[0] Train-accuracy=0.566211\n", |
| "2016-11-04 18:07:11,469 Node[0] Epoch[0] Train-top_k_accuracy_5=0.948242\n", |
| "2016-11-04 18:07:11,470 Node[0] Epoch[0] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:07:11,471 Node[0] Epoch[0] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:07:11,471 Node[0] Epoch[0] Time cost=98.542\n", |
| "2016-11-04 18:07:17,454 Node[0] Epoch[0] Validation-accuracy=nan\n", |
| "2016-11-04 18:07:17,455 Node[0] Epoch[0] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:07:17,456 Node[0] Epoch[0] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:07:17,457 Node[0] Epoch[0] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:08:57,069 Node[0] Epoch[1] Train-accuracy=0.679883\n", |
| "2016-11-04 18:08:57,069 Node[0] Epoch[1] Train-top_k_accuracy_5=0.973047\n", |
| "2016-11-04 18:08:57,071 Node[0] Epoch[1] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:08:57,072 Node[0] Epoch[1] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:08:57,072 Node[0] Epoch[1] Time cost=99.614\n", |
| "2016-11-04 18:09:02,598 Node[0] Epoch[1] Validation-accuracy=nan\n", |
| "2016-11-04 18:09:02,599 Node[0] Epoch[1] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:09:02,599 Node[0] Epoch[1] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:09:02,600 Node[0] Epoch[1] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:10:42,219 Node[0] Epoch[2] Train-accuracy=0.742388\n", |
| "2016-11-04 18:10:42,221 Node[0] Epoch[2] Train-top_k_accuracy_5=0.981170\n", |
| "2016-11-04 18:10:42,222 Node[0] Epoch[2] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:10:42,223 Node[0] Epoch[2] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:10:42,223 Node[0] Epoch[2] Time cost=99.622\n", |
| "2016-11-04 18:10:47,755 Node[0] Epoch[2] Validation-accuracy=nan\n", |
| "2016-11-04 18:10:47,756 Node[0] Epoch[2] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:10:47,757 Node[0] Epoch[2] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:10:47,758 Node[0] Epoch[2] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:12:27,771 Node[0] Epoch[3] Train-accuracy=0.775586\n", |
| "2016-11-04 18:12:27,772 Node[0] Epoch[3] Train-top_k_accuracy_5=0.987891\n", |
| "2016-11-04 18:12:27,773 Node[0] Epoch[3] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:12:27,774 Node[0] Epoch[3] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:12:27,775 Node[0] Epoch[3] Time cost=100.017\n", |
| "2016-11-04 18:12:33,304 Node[0] Epoch[3] Validation-accuracy=nan\n", |
| "2016-11-04 18:12:33,305 Node[0] Epoch[3] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:12:33,306 Node[0] Epoch[3] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:12:33,307 Node[0] Epoch[3] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:14:13,252 Node[0] Epoch[4] Train-accuracy=0.793945\n", |
| "2016-11-04 18:14:13,253 Node[0] Epoch[4] Train-top_k_accuracy_5=0.991016\n", |
| "2016-11-04 18:14:13,253 Node[0] Epoch[4] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:14:13,254 Node[0] Epoch[4] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:14:13,255 Node[0] Epoch[4] Time cost=99.948\n", |
| "2016-11-04 18:14:18,787 Node[0] Epoch[4] Validation-accuracy=nan\n", |
| "2016-11-04 18:14:18,787 Node[0] Epoch[4] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:14:18,788 Node[0] Epoch[4] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:14:18,789 Node[0] Epoch[4] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:15:58,508 Node[0] Epoch[5] Train-accuracy=0.819311\n", |
| "2016-11-04 18:15:58,509 Node[0] Epoch[5] Train-top_k_accuracy_5=0.991987\n", |
| "2016-11-04 18:15:58,510 Node[0] Epoch[5] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:15:58,511 Node[0] Epoch[5] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:15:58,511 Node[0] Epoch[5] Time cost=99.722\n", |
| "2016-11-04 18:16:04,043 Node[0] Epoch[5] Validation-accuracy=nan\n", |
| "2016-11-04 18:16:04,044 Node[0] Epoch[5] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:16:04,045 Node[0] Epoch[5] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:16:04,046 Node[0] Epoch[5] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:17:43,899 Node[0] Epoch[6] Train-accuracy=0.829688\n", |
| "2016-11-04 18:17:43,900 Node[0] Epoch[6] Train-top_k_accuracy_5=0.993750\n", |
| "2016-11-04 18:17:43,901 Node[0] Epoch[6] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:17:43,902 Node[0] Epoch[6] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:17:43,903 Node[0] Epoch[6] Time cost=99.856\n", |
| "2016-11-04 18:17:49,441 Node[0] Epoch[6] Validation-accuracy=nan\n", |
| "2016-11-04 18:17:49,441 Node[0] Epoch[6] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:17:49,442 Node[0] Epoch[6] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:17:49,443 Node[0] Epoch[6] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:19:29,163 Node[0] Epoch[7] Train-accuracy=0.844151\n", |
| "2016-11-04 18:19:29,164 Node[0] Epoch[7] Train-top_k_accuracy_5=0.994992\n", |
| "2016-11-04 18:19:29,165 Node[0] Epoch[7] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:19:29,166 Node[0] Epoch[7] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:19:29,167 Node[0] Epoch[7] Time cost=99.723\n", |
| "2016-11-04 18:19:34,688 Node[0] Epoch[7] Validation-accuracy=nan\n", |
| "2016-11-04 18:19:34,689 Node[0] Epoch[7] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:19:34,689 Node[0] Epoch[7] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:19:34,690 Node[0] Epoch[7] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:21:15,117 Node[0] Epoch[8] Train-accuracy=0.862695\n", |
| "2016-11-04 18:21:15,118 Node[0] Epoch[8] Train-top_k_accuracy_5=0.995703\n", |
| "2016-11-04 18:21:15,118 Node[0] Epoch[8] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:21:15,120 Node[0] Epoch[8] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:21:15,121 Node[0] Epoch[8] Time cost=100.430\n", |
| "2016-11-04 18:21:21,087 Node[0] Epoch[8] Validation-accuracy=nan\n", |
| "2016-11-04 18:21:21,088 Node[0] Epoch[8] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:21:21,088 Node[0] Epoch[8] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:21:21,089 Node[0] Epoch[8] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:23:00,978 Node[0] Epoch[9] Train-accuracy=0.872070\n", |
| "2016-11-04 18:23:00,979 Node[0] Epoch[9] Train-top_k_accuracy_5=0.994141\n", |
| "2016-11-04 18:23:00,981 Node[0] Epoch[9] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:23:00,982 Node[0] Epoch[9] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:23:00,983 Node[0] Epoch[9] Time cost=99.893\n", |
| "2016-11-04 18:23:06,510 Node[0] Epoch[9] Validation-accuracy=nan\n", |
| "2016-11-04 18:23:06,511 Node[0] Epoch[9] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:23:06,511 Node[0] Epoch[9] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:23:06,512 Node[0] Epoch[9] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:24:46,159 Node[0] Epoch[10] Train-accuracy=0.878606\n", |
| "2016-11-04 18:24:46,160 Node[0] Epoch[10] Train-top_k_accuracy_5=0.997196\n", |
| "2016-11-04 18:24:46,161 Node[0] Epoch[10] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:24:46,162 Node[0] Epoch[10] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:24:46,163 Node[0] Epoch[10] Time cost=99.646\n", |
| "2016-11-04 18:24:51,684 Node[0] Epoch[10] Validation-accuracy=nan\n", |
| "2016-11-04 18:24:51,685 Node[0] Epoch[10] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:24:51,685 Node[0] Epoch[10] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:24:51,686 Node[0] Epoch[10] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:26:31,614 Node[0] Epoch[11] Train-accuracy=0.889062\n", |
| "2016-11-04 18:26:31,615 Node[0] Epoch[11] Train-top_k_accuracy_5=0.996094\n", |
| "2016-11-04 18:26:31,616 Node[0] Epoch[11] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:26:31,617 Node[0] Epoch[11] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:26:31,618 Node[0] Epoch[11] Time cost=99.931\n", |
| "2016-11-04 18:26:37,150 Node[0] Epoch[11] Validation-accuracy=nan\n", |
| "2016-11-04 18:26:37,151 Node[0] Epoch[11] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:26:37,152 Node[0] Epoch[11] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:26:37,152 Node[0] Epoch[11] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:28:17,021 Node[0] Epoch[12] Train-accuracy=0.895117\n", |
| "2016-11-04 18:28:17,023 Node[0] Epoch[12] Train-top_k_accuracy_5=0.997266\n", |
| "2016-11-04 18:28:17,024 Node[0] Epoch[12] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:28:17,025 Node[0] Epoch[12] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:28:17,026 Node[0] Epoch[12] Time cost=99.873\n", |
| "2016-11-04 18:28:22,553 Node[0] Epoch[12] Validation-accuracy=nan\n", |
| "2016-11-04 18:28:22,554 Node[0] Epoch[12] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:28:22,555 Node[0] Epoch[12] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:28:22,556 Node[0] Epoch[12] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:30:02,235 Node[0] Epoch[13] Train-accuracy=0.904447\n", |
| "2016-11-04 18:30:02,236 Node[0] Epoch[13] Train-top_k_accuracy_5=0.997997\n", |
| "2016-11-04 18:30:02,237 Node[0] Epoch[13] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:30:02,238 Node[0] Epoch[13] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:30:02,239 Node[0] Epoch[13] Time cost=99.683\n", |
| "2016-11-04 18:30:07,772 Node[0] Epoch[13] Validation-accuracy=nan\n", |
| "2016-11-04 18:30:07,773 Node[0] Epoch[13] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:30:07,774 Node[0] Epoch[13] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:30:07,774 Node[0] Epoch[13] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:31:47,692 Node[0] Epoch[14] Train-accuracy=0.902734\n", |
| "2016-11-04 18:31:47,693 Node[0] Epoch[14] Train-top_k_accuracy_5=0.998633\n", |
| "2016-11-04 18:31:47,694 Node[0] Epoch[14] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:31:47,695 Node[0] Epoch[14] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:31:47,696 Node[0] Epoch[14] Time cost=99.921\n", |
| "2016-11-04 18:31:53,226 Node[0] Epoch[14] Validation-accuracy=nan\n", |
| "2016-11-04 18:31:53,227 Node[0] Epoch[14] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:31:53,228 Node[0] Epoch[14] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:31:53,228 Node[0] Epoch[14] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:33:32,868 Node[0] Epoch[15] Train-accuracy=0.919471\n", |
| "2016-11-04 18:33:32,869 Node[0] Epoch[15] Train-top_k_accuracy_5=0.998798\n", |
| "2016-11-04 18:33:32,870 Node[0] Epoch[15] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:33:32,871 Node[0] Epoch[15] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:33:32,872 Node[0] Epoch[15] Time cost=99.643\n", |
| "2016-11-04 18:33:38,396 Node[0] Epoch[15] Validation-accuracy=nan\n", |
| "2016-11-04 18:33:38,397 Node[0] Epoch[15] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:33:38,398 Node[0] Epoch[15] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:33:38,398 Node[0] Epoch[15] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:35:18,826 Node[0] Epoch[16] Train-accuracy=0.915234\n", |
| "2016-11-04 18:35:18,827 Node[0] Epoch[16] Train-top_k_accuracy_5=0.997656\n", |
| "2016-11-04 18:35:18,828 Node[0] Epoch[16] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:35:18,829 Node[0] Epoch[16] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:35:18,830 Node[0] Epoch[16] Time cost=100.431\n", |
| "2016-11-04 18:35:24,759 Node[0] Epoch[16] Validation-accuracy=nan\n", |
| "2016-11-04 18:35:24,759 Node[0] Epoch[16] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:35:24,760 Node[0] Epoch[16] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:35:24,761 Node[0] Epoch[16] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:37:04,619 Node[0] Epoch[17] Train-accuracy=0.918555\n", |
| "2016-11-04 18:37:04,620 Node[0] Epoch[17] Train-top_k_accuracy_5=0.998437\n", |
| "2016-11-04 18:37:04,621 Node[0] Epoch[17] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:37:04,621 Node[0] Epoch[17] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:37:04,622 Node[0] Epoch[17] Time cost=99.861\n", |
| "2016-11-04 18:37:10,154 Node[0] Epoch[17] Validation-accuracy=nan\n", |
| "2016-11-04 18:37:10,155 Node[0] Epoch[17] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:37:10,156 Node[0] Epoch[17] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:37:10,156 Node[0] Epoch[17] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:38:49,811 Node[0] Epoch[18] Train-accuracy=0.924479\n", |
| "2016-11-04 18:38:49,812 Node[0] Epoch[18] Train-top_k_accuracy_5=0.998598\n", |
| "2016-11-04 18:38:49,813 Node[0] Epoch[18] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:38:49,814 Node[0] Epoch[18] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:38:49,814 Node[0] Epoch[18] Time cost=99.658\n", |
| "2016-11-04 18:38:55,339 Node[0] Epoch[18] Validation-accuracy=nan\n", |
| "2016-11-04 18:38:55,340 Node[0] Epoch[18] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:38:55,340 Node[0] Epoch[18] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:38:55,341 Node[0] Epoch[18] Validation-top_k_accuracy_20=nan\n", |
| "2016-11-04 18:40:35,220 Node[0] Epoch[19] Train-accuracy=0.927148\n", |
| "2016-11-04 18:40:35,222 Node[0] Epoch[19] Train-top_k_accuracy_5=0.998828\n", |
| "2016-11-04 18:40:35,222 Node[0] Epoch[19] Train-top_k_accuracy_10=1.000000\n", |
| "2016-11-04 18:40:35,223 Node[0] Epoch[19] Train-top_k_accuracy_20=1.000000\n", |
| "2016-11-04 18:40:35,224 Node[0] Epoch[19] Time cost=99.880\n", |
| "2016-11-04 18:40:40,751 Node[0] Epoch[19] Validation-accuracy=nan\n", |
| "2016-11-04 18:40:40,752 Node[0] Epoch[19] Validation-top_k_accuracy_5=nan\n", |
| "2016-11-04 18:40:40,753 Node[0] Epoch[19] Validation-top_k_accuracy_10=nan\n", |
| "2016-11-04 18:40:40,753 Node[0] Epoch[19] Validation-top_k_accuracy_20=nan\n" |
| ] |
| } |
| ], |
| "source": [ |
| "# Start training\n", |
| "train_cifar10.do_train(args, \n", |
| " callback_args=cb_args,\n", |
| ")" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": null, |
| "metadata": { |
| "collapsed": true |
| }, |
| "outputs": [], |
| "source": [] |
| } |
| ], |
| "metadata": { |
| "kernelspec": { |
| "display_name": "Python 2", |
| "language": "python", |
| "name": "python2" |
| }, |
| "language_info": { |
| "codemirror_mode": { |
| "name": "ipython", |
| "version": 2 |
| }, |
| "file_extension": ".py", |
| "mimetype": "text/x-python", |
| "name": "python", |
| "nbconvert_exporter": "python", |
| "pygments_lexer": "ipython2", |
| "version": "2.7.6" |
| } |
| }, |
| "nbformat": 4, |
| "nbformat_minor": 1 |
| } |
