https://terms-en.ai-term-hub.com/zh/tags/images/Recent content in Images on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:44 +0000https://terms-en.ai-term-hub.com/zh/terms/convolutional_neural_network/Sat, 18 Jul 2026 07:44:21 +0000https://terms-en.ai-term-hub.com/zh/terms/convolutional_neural_network/<h2 id="definition">Definition</h2> <p>卷积神经网络（CNN）旨在从视觉输入中自动且自适应地学习特征的空间层次结构。它们利用卷积层应用滤波器来检测局部模式，并通过池化等操作逐步提取高层语义特征。</p> <h3 id="summary">Summary</h3> <p>一类专门用于处理网格状数据（如图像）的深度神经网络，通过应用卷积滤波器来实现。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>卷积层</li> <li>池化</li> <li>特征图</li> <li>空间层次</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>图像分类</li> <li>视频流中的目标检测</li> <li>医学影像诊断</li> </ul> <h2 id="code-example">Code Example</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">import</span> tensorflow <span style="color:#66d9ef">as</span> tf </span></span><span style="display:flex;"><span>model <span style="color:#f92672">=</span> tf<span style="color:#f92672">.</span>keras<span style="color:#f92672">.</span>Sequential([ </span></span><span style="display:flex;"><span> tf<span style="color:#f92672">.</span>keras<span style="color:#f92672">.</span>layers<span style="color:#f92672">.</span>Conv2D(<span style="color:#ae81ff">32</span>, (<span style="color:#ae81ff">3</span>, <span style="color:#ae81ff">3</span>), activation<span style="color:#f92672">=</span><span style="color:#e6db74">&#39;relu&#39;</span>, input_shape<span style="color:#f92672">=</span>(<span style="color:#ae81ff">28</span>, <span style="color:#ae81ff">28</span>, <span style="color:#ae81ff">1</span>)), </span></span><span style="display:flex;"><span> tf<span style="color:#f92672">.</span>keras<span style="color:#f92672">.</span>layers<span style="color:#f92672">.</span>MaxPooling2D((<span style="color:#ae81ff">2</span>, <span style="color:#ae81ff">2</span>)), </span></span><span style="display:flex;"><span> tf<span style="color:#f92672">.</span>keras<span style="color:#f92672">.</span>layers<span style="color:#f92672">.</span>Flatten(), </span></span><span style="display:flex;"><span> tf<span style="color:#f92672">.</span>keras<span style="color:#f92672">.</span>layers<span style="color:#f92672">.</span>Dense(<span style="color:#ae81ff">10</span>) </span></span><span style="display:flex;"><span>]) </span></span></code></pre></div><h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/deep-learning-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/">Deep Learning (深度学习)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/computer-vision-%E8%AE%A1%E7%AE%97%E6%9C%BA%E8%A7%86%E8%A7%89/">Computer Vision (计算机视觉)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/backpropagation-%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD/">Backpropagation (反向传播)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/neural-network-%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">Neural Network (神经网络)</a></li> </ul>