<div class="tags-box space">
							<span class="label">個人分類：</span>
															<a class="tag-link" href="https://blog.csdn.net/u012436149/article/category/6461700" target="_blank">tensorflow																</a>
						</div>
																				<div class="tags-box space">
							<span class="label">所屬專欄：</span>
															<a class="tag-link" href="https://blog.csdn.net/column/details/13300.html" target="_blank">tensorflow學習筆記</a>
															
						</div>
																</div>
			<div class="operating">
													</div>
		</div>
	</div>
</div>
<article>
	<div id="article_content" class="article_content clearfix csdn-tracking-statistics" data-pid="blog" data-mod="popu_307" data-dsm="post">
							<div class="article-copyright">
				版權宣告：本文為博主原創文章，轉載請註明出處。					https://blog.csdn.net/u012436149/article/details/78291545				</div>
							            <div class="markdown_views">
						<!-- flowchart 箭頭圖示 勿刪 -->
						<svg xmlns="http://www.w3.org/2000/svg" style="display: none;"><path stroke-linecap="round" d="M5,0 0,2.5 5,5z" id="raphael-marker-block" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0);"></path></svg>
						<p>當我們訓練自己的神經網路的時候，無一例外的就是都會加上一句 <code>sess.run(tf.global_variables_initializer())</code> ，這行程式碼的官方解釋是 初始化模型的引數。那麼，它到底做了些什麼？</p>