https://terms-en.ai-term-hub.com/zh/tags/visualization/Recent content in Visualization on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000https://terms-en.ai-term-hub.com/zh/terms/tensorboard/Sat, 18 Jul 2026 11:35:54 +0000https://terms-en.ai-term-hub.com/zh/terms/tensorboard/<h2 id="definition">Definition</h2> <p>TensorBoard 是一套用于检查和理解 TensorFlow 运行过程和计算图的 Web 应用程序套件。它提供了可视化损失和准确率等指标随时间变化的工具，以及查看模型图的功能。</p> <h3 id="summary">Summary</h3> <p>一个用于监控机器学习实验和调试模型性能的可视化工具包。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>可视化</li> <li>超参数调优</li> <li>图检查</li> <li>指标跟踪</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>调试训练收敛情况</li> <li>比较模型架构</li> <li>可视化嵌入空间</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">from</span> tensorboard.callback <span style="color:#f92672">import</span> TensorBoardCallback </span></span><span style="display:flex;"><span>callback <span style="color:#f92672">=</span> TensorBoardCallback(log_dir<span style="color:#f92672">=</span><span style="color:#e6db74">&#39;./logs&#39;</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/mlflow-mlflow%E5%B9%B3%E5%8F%B0/">MLflow (MLflow平台)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/weights-biases-w-b%E5%B9%B3%E5%8F%B0/">Weights &amp; Biases (W&amp;B平台)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/tensorflow-tensorflow%E6%A1%86%E6%9E%B6/">TensorFlow (TensorFlow框架)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/experiment-tracking-%E5%AE%9E%E9%AA%8C%E8%B7%9F%E8%B8%AA/">Experiment Tracking (实验跟踪)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/learning_curve/Sat, 18 Jul 2026 11:23:53 +0000https://terms-en.ai-term-hub.com/zh/terms/learning_curve/<h2 id="definition">Definition</h2> <p>通常，学习曲线在y轴上显示训练得分和验证得分，在x轴上显示训练样本数量或迭代次数。它有助于诊断模型是否存在高偏差（欠拟合）或高方差（过拟合）问题。</p> <h3 id="summary">Summary</h3> <p>学习曲线将模型的性能指标与训练数据量或训练轮数进行绘图，以可视化学习进度。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>训练得分</li> <li>验证得分</li> <li>欠拟合与过拟合</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>诊断模型性能问题</li> <li>确定样本量需求</li> <li>监控训练收敛情况</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/validation-set-%E9%AA%8C%E8%AF%81%E9%9B%86/">Validation set (验证集)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/overfitting-%E8%BF%87%E6%8B%9F%E5%90%88/">Overfitting (过拟合)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/convergence-%E6%94%B6%E6%95%9B/">Convergence (收敛)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/k_line/Sat, 18 Jul 2026 11:22:59 +0000https://terms-en.ai-term-hub.com/zh/terms/k_line/<h2 id="definition">Definition</h2> <p>K线（在西方市场常称为蜡烛图）是一种图形化表示证券、衍生品或货币价格动态的方法。它展示了四个关键数据点：开盘价、收盘价、最高价和最低价，帮助投资者分析市场趋势和价格行为。</p> <h3 id="summary">Summary</h3> <p>一种金融图表，也称为蜡烛图，用于可视化特定时间间隔内的价格变动。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>蜡烛图</li> <li>OHLC数据</li> <li>技术分析</li> <li>市场趋势</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>股票市场技术分析</li> <li>加密货币交易可视化</li> <li>识别支撑位和阻力位</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%8A%98%E7%BA%BF%E5%9B%BE-line-chart/">折线图 (Line Chart)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%9D%A1%E5%BD%A2%E5%9B%BE-bar-chart/">条形图 (Bar Chart)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E7%A7%BB%E5%8A%A8%E5%B9%B3%E5%9D%87%E7%BA%BF-moving-average/">移动平均线 (Moving Average)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/%E6%88%90%E4%BA%A4%E9%87%8F%E5%88%86%E5%B8%83-volume-profile/">成交量分布 (Volume Profile)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/data_exploration/Sat, 18 Jul 2026 11:12:36 +0000https://terms-en.ai-term-hub.com/zh/terms/data_exploration/<h2 id="definition">Definition</h2> <p>数据探索，通常称为探索性数据分析（EDA），是机器学习工作流程中至关重要的初步步骤。它涉及总结数据的主要特征，经常使用可视化技术来揭示数据的内在结构和分布情况。</p> <h3 id="summary">Summary</h3> <p>在正式建模之前，对数据集进行初步分析，以发现模式、识别异常并验证假设。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>探索性数据分析</li> <li>可视化</li> <li>模式识别</li> <li>异常检测</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>在模型训练前识别特征之间的相关性</li> <li>检测和处理缺失值或异常值</li> <li>验证数据质量和分布假设</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> pandas <span style="color:#66d9ef">as</span> pd </span></span><span style="display:flex;"><span><span style="color:#f92672">import</span> seaborn <span style="color:#66d9ef">as</span> sns </span></span><span style="display:flex;"><span>df <span style="color:#f92672">=</span> pd<span style="color:#f92672">.</span>read_csv(<span style="color:#e6db74">&#39;data.csv&#39;</span>) </span></span><span style="display:flex;"><span>sns<span style="color:#f92672">.</span>pairplot(df) </span></span><span style="display:flex;"><span>plt<span style="color:#f92672">.</span>show() </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/feature_engineering-%E7%89%B9%E5%BE%81%E5%B7%A5%E7%A8%8B/">feature_engineering (特征工程)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/data_cleaning-%E6%95%B0%E6%8D%AE%E6%B8%85%E6%B4%97/">data_cleaning (数据清洗)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/eda-%E6%8E%A2%E7%B4%A2%E6%80%A7%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90/">EDA (探索性数据分析)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/statistical_analysis-%E7%BB%9F%E8%AE%A1%E5%88%86%E6%9E%90/">statistical_analysis (统计分析)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/class_activation_mapping/Sat, 18 Jul 2026 11:10:07 +0000https://terms-en.ai-term-hub.com/zh/terms/class_activation_mapping/<h2 id="definition">Definition</h2> <p>CAM 在输入图像上叠加热力图，以显示哪些像素对模型针对特定类别标签的决策贡献最大。它通过对最终卷积层应用全局平均池化来工作，从而定位关键特征区域。</p> <h3 id="summary">Summary</h3> <p>类激活映射（CAM）是一种可视化技术，用于高亮显示输入图像中对特定预测类别贡献最大的区域。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>热力图可视化</li> <li>可解释性</li> <li>特征重要性</li> <li>全局平均池化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>医学影像诊断验证</li> <li>自动驾驶物体检测调试</li> <li>可解释 AI 报告</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/grad-cam-%E6%A2%AF%E5%BA%A6%E5%8A%A0%E6%9D%83%E7%B1%BB%E6%BF%80%E6%B4%BB%E6%98%A0%E5%B0%84/">Grad-CAM (梯度加权类激活映射)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/saliency-maps-%E6%98%BE%E8%91%97%E6%80%A7%E5%9B%BE/">Saliency Maps (显著性图)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/explainable-ai-%E5%8F%AF%E8%A7%A3%E9%87%8A%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/">Explainable AI (可解释人工智能)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/convolutional-neural-networks-%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">Convolutional Neural Networks (卷积神经网络)</a></li> </ul>https://terms-en.ai-term-hub.com/zh/terms/graphs/Sat, 18 Jul 2026 10:51:41 +0000https://terms-en.ai-term-hub.com/zh/terms/graphs/<h2 id="definition">Definition</h2> <p>虽然单数“图”指抽象的数据结构，但“graphs”通常指多个不同的图实例，或在机器学习监控中使用的可视化图表。在可视化中，包括折线图或条形图等。</p> <h3 id="summary">Summary</h3> <p>复数形式，指多个图结构或机器学习中的数据趋势可视化表示。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>多个结构</li> <li>可视化</li> <li>指标绘图</li> <li>数据集合</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>训练损失可视化</li> <li>多图数据集</li> <li>性能基准测试图表</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/plot-%E7%BB%98%E5%9B%BE/">Plot (绘图)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/chart-%E5%9B%BE%E8%A1%A8/">Chart (图表)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/gnn-%E5%9B%BE%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C/">GNN (图神经网络)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/visualization-%E5%8F%AF%E8%A7%86%E5%8C%96/">Visualization (可视化)</a></li> </ul>