github-starred/cs249r_book
2
0
Fork 0
mirror of https://github.com/harvard-edge/cs249r_book.git synced 2026-03-11 17:49:25 -05:00
Code Issues Packages Projects Releases Wiki Activity

Addressing the typos found

Browse Source
This commit is contained in:
Vijay Janapa Reddi
2024-08-14 12:05:37 -07:00
parent ed20e0647f
commit 8f5ce3b210
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
contents/frameworks/frameworks.qmd
View File

@@ -104,7 +104,7 @@ TensorFlow is a training and inference framework that provides built-in function
7. [TensorFlow Graphics](https://www.tensorflow.org/graphics): library for using TensorFlow to carry out graphics-related tasks, including 3D shapes and point clouds processing, using deep learning.
8. [TensorFlow Hub](https://www.tensorflow.org/hub): repository of reusable machine learning model components to allow developers to reuse pre-trained model components, facilitating transfer learning and model composition
8. [TensorFlow Hub](https://www.tensorflow.org/hub): repository of reusable machine learning model components to allow developers to reuse pre-trained model components, facilitating transfer learning and model composition.
9. [TensorFlow Serving](https://www.tensorflow.org/tfx/guide/serving): framework designed for serving and deploying machine learning models for inference in production environments. It provides tools for versioning and dynamically updating deployed models without service interruption.
@@ -220,7 +220,7 @@ To understand tensors, let us start from the familiar concepts in linear algebra
Tensors offer a flexible structure that can represent data in higher dimensions. For instance, to represent image data, the pixels at each position of an image are structured as matrices. However, images are not represented by just one matrix of pixel values; they typically have three channels where each channel is a matrix containing pixel values that represent the intensity of red, green, or blue. Together, these channels create a colored image. Without tensors, storing all this information from multiple matrices can be complex. With tensors, it is easy to contain image data in a single 3-dimensional tensor, with each number representing a certain color value at a specific location in the image.
![Visualization of colored image structure that can be easily stored as a 3D Tesnor. Credit: [Niklas Lang](https://towardsdatascience.com/what-are-tensors-in-machine-learning-5671814646ff)](images/png/color_channels_of_image.png){#fig-tensor-data-structure}
![Visualization of colored image structure that can be easily stored as a 3D Tensor. Credit: [Niklas Lang](https://towardsdatascience.com/what-are-tensors-in-machine-learning-5671814646ff)](images/png/color_channels_of_image.png){#fig-tensor-data-structure}
You don't have to stop there. If we wanted to store a series of images, we could use a 4-dimensional tensor, where the new dimension represents different images. This means you are storing multiple images, each having three matrices that represent the three color channels. This gives you an idea of the usefulness of tensors when dealing with multi-dimensional data efficiently.

2
contribute.md
View File

@@ -29,7 +29,7 @@ Fork the repository on GitHub and clone your fork to your local machine. We are
git clone https://github.com/YOUR_USERNAME/cs249r_book.git
```
### Naviage to the repository
### Navigate to the repository
```bash
cd cs249r_book