使用 Google Colab 进行深度学习

Deep Learning with Google Colab

您还未登录,请点击这里登录

上一讲： 2. Tensor operations

下一讲： 4. Turning on your Colab GPU

视频列表

1. Getting started in Google Colab
1. Introduction
2. Registering for a Google account
3. Navigating to Google Colab
4. Exploring your Google Colab Notebook
5. The definition of notebooks
6. Running your first Google Colab code cell
7. The markup language Markdown
8. Writing Markdown in Google Colab
9. Writing LaTeX in Google Colab
10. Section conclusion
2. The ecosystem of Google Colab
1. Installing packages in Google Colab
2. Working with files using Google Drive
3. Working with files directly in Google Colab
4. Sharing files via Google Drive
5. Introduction to version control with Git and GitHub
6. Sending Google Colab notebooks to GitHub
3. Introduction to PyTorch
1. Creating a tensor
2. Tensor operations
3. GPUs in the context of deep learning
4. Turning on your Colab GPU
5. Limits of the Colab GPU
6. Neural network basics
7. Gradients and backpropagation
8. Automatic differentiation in PyTorch
9. Training a model
10. Saving and loading models
11. Problem statement and setup
12. Approaches and solutions
4. Working with datasets
1. Downloading a built-in dataset
2. Working with PyTorch datasets
3. Loading a dataset into Colab
4. Building a PyTorch dataset
5. Image augmentation fundamentals
6. Image augmentation in PyTorch
5. Recognizing handwritten digits
1. Downloading the dataset
2. Understanding the dataset
3. Implementing a starting solution
4. Training and evaluating
5. Choosing the size of input and output layers
6. Choosing the size of hidden layers
7. Loss functions
8. Activation functions and weight initialization
9. Optimizers
6. Transfer learning for object recognition
1. Downloading the dataset
2. Understanding the dataset
3. What is transfer learning
4. The transfer learning workflow
5. Training and evaluating
6. Pretrained models for transfer learning
7. Recognizing fashion items
1. Downloading the dataset
2. Understanding the dataset
3. Convolutional network fundamentals
4. Implementation in PyTorch
5. Residual network fundamentals
6. Residual blocks in convolutional networks
7. Implementation in PyTorch
8. Deep learning best practices
1. General ensembling in machine learning
2. Ensembling in deep learning
3. Data versioning
4. Reproducibility
5. When not to use deep learning