Deep Learning Tuning and Visualization

互动构建和训练网络，管理实验，绘制训练进度，评估准确性，解释预测，调整培训选项以及可视化网络学到的功能

Use Deep Network Designer to interactively build, visualize, edit, and train deep learning network. Tune training options and improve network performance by sweeping hyperparameters or using Bayesian optimization. Use Experiment Manager to manage deep learning experiments that train networks under various initial conditions and compare the results. Monitor training progress using built-in plots of network accuracy and loss. To investigate trained networks, you can use visualization techniques such as Grad-CAM, occlusion sensitivity, LIME, and deep dream. You can also investigate network robustness using adversarial examples and test your trained network by making predictions using new data.

Frequently Viewed Topics

Featured Examples

使用深度学习对网络摄像头进行分类

Classify images from a webcam in real time using the pretrained deep convolutional neural network GoogLeNet.

打开脚本

Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions

Monitor vanishing gradients while training a deep neural network.

Open Live Script

Transfer Learning with Deep Network Designer

Interactively fine-tune a pretrained deep learning network to learn a new image classification task.

Open Live Script

Understand Network Predictions Using LIME

Use locally interpretable model-agnostic explanations (LIME) to understand why a deep neural network makes a classification decision.

Open Live Script

Try Multiple Pretrained Networks for Transfer Learning

配置一个实验that replaces layers of different pretrained networks for transfer learning.

Open Example

Choose Training Configurations for LSTM Using Bayesian Optimization

Find optimal data architecture and network configurations for sequence-to-sequence regression using Bayesian optimization.

Open Example

Use Experiment Manager to Train Generative Adversarial Networks (GANs)

Create a custom training experiment to generate images of flowers.

Open Example

Generate Untargeted and Targeted Adversarial Examples for Image Classification

Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.

Open Live Script

Deep Learning Tuning and Visualization

Frequently Viewed Topics

Categories

Featured Examples

使用深度学习对网络摄像头进行分类

Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions

Transfer Learning with Deep Network Designer

Understand Network Predictions Using LIME

Try Multiple Pretrained Networks for Transfer Learning

Choose Training Configurations for LSTM Using Bayesian Optimization

Use Experiment Manager to Train Generative Adversarial Networks (GANs)

Generate Untargeted and Targeted Adversarial Examples for Image Classification