我们使用 PyTorch 的目标是构建可能表达深度学习算法的最灵活的框架。我们专注执行，并在相对较短的开发时间内为开发者市场构建了一个成熟的产品。如果我们没有站在巨人的肩膀上，这是不可能达成的。PyTorch 的代码库中有很大一部分源自 2007 年由 Ronan Collobert 和其他人开始的 Torch7 项目，而该项目亦源自由 Yann LeCun 和 Leon Bottou 倡导的 Lush 编程语言。这份丰富的历史使我们能够专注于改变什么，而不是从零开始。
目录
- Front Matter
- Part 1. Core PyTorch
- 1 Introducing deep learning and the PyTorch Library
- 2 Pretrained networks
- 3 It starts with a tensor
- 3.1 The world as floating-point numbers
- 3.2 Tensors: Multidimensional arrays
- 3.3 Indexing tensors
- 3.4 Named tensors
- 3.5 Tensor element types
- 3.6 The tensor API
- 3.7 Tensors: Scenic views of storage
- 3.8 Tensor metadata: Size, offset, and stride
- 3.9 Moving tensors to the GPU
- 3.10 NumPy interoperability
- 3.11 Generalized tensors are tensors, too
- 3.12 Serializing tensors
- 3.13 Conclusion
- 3.14 Exercises
- 3.15 Summary
- 4 Real-world data representation using tensors
- 5 The mechanics of learning
- 6 Using a neural network to fit the data
- 7 Telling birds from airplanes: Learning from images
- 8 Using convolutions to generalize
- Part 2. Learning from images in the real world: Early detection of lung cancer
- 9 Using PyTorch to fight cancer
- 10 Combining data sources into a unified dataset
- 11 Training a classification model to detect suspected tumors
- 11.1 A foundational model and training loop
- 11.2 The main entry point for our application
- 11.3 Pretraining setup and initialization
- 11.4 Our first-pass neural network design
- 11.5 Training and validating the model
- 11.6 Outputting performance metrics
- 11.7 Running the training script
- 11.8 Evaluating the model: Getting 99.7% correct means we’re done, right?
- 11.9 Graphing training metrics with TensorBoard
- 11.10 Why isn’t the model learning to detect nodules?
- 11.11 Conclusion
- 11.12 Exercises
- 11.13 Summary
- 12 Improving training with metrics and augmentation
- 12.1 High-level plan for improvement
- 12.2 Good dogs vs. bad guys: False positives and false negatives
- 12.3 Graphing the positives and negatives
- 12.4 What does an ideal dataset look like?
- 12.5 Revisiting the problem of overfitting
- 12.6 Preventing overfitting with data augmentation
- 12.7 Conclusion
- 12.8 Exercises
- 12.9 Summary
- 13 Using segmentationto find suspected nodules
- 13.1 Adding a second model to our project
- 13.2 Various types of segmentation
- 13.3 Semantic segmentation: Per-pixel classification
- 13.4 Updating the model for segmentation
- 13.5 Updating the dataset for segmentation
- 13.6 Updating the training script for segmentation
- 13.7 Results
- 13.8 Conclusion
- 13.9 Exercises
- 13.10 Summary
- 14 End-to-end nodule analysis, and where to go next
- 14.1 Towards the finish line
- 14.2 Independence of the validation set
- 14.3 Bridging CT segmentation and nodule candidate classification
- 14.4 Quantitative validation
- 14.5 Predicting malignancy
- 14.6 What we see when we diagnose
- 14.7 What next? Additional sources of inspiration (and data)
- 14.8 Conclusion
- 14.9 Exercises
- 14.10 Summary
- Part 3. Deployment
- 15 Deploying to production
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论