Skip to content
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Commit 1d50363

Browse files
committedJun 11, 2020
Add figures for chapter 9
1 parent ac0c02d commit 1d50363

19 files changed

+28
-5
lines changed
 

‎README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ We diversify our practical skills in a variety of topics and tools, ranging from
6464

6565
Work smart, not hard. We utilize the power of cloud AI platforms from Google, Microsoft, Amazon, IBM and Clarifai in under 15 minutes. For tasks not solved with existing APIs, we then use custom classification services to train classifiers without coding. And then we pit them against each other in an open benchmark, you might be surprised who won.
6666

67-
[**Chapter 9 - Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-9) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch09.html)
67+
[**Chapter 9 - Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow**](https://github.com/practicaldl/Practical-Deep-Learning-Book/tree/master/code/chapter-9) | [Read online](https://learning.oreilly.com/library/view/practical-deep-learning/9781492034858/ch09.html) | [Figures](figures/chapter-9)
6868

6969
We take our custom trained model to the cloud/on-premises to scalably serve from tens to millions of requests. We explore Flask, Google Cloud ML Engine, TensorFlow Serving, and KubeFlow, showcasing the effort, scenario, and cost-benefit analysis.
7070

‎figures/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ This directory contains references to the figures used within the book. All imag
1616
| [Chapter 6 - Maximizing Speed and Performance of TensorFlow: A Handy Checklist](chapter-6/) |
1717
| Chapter 7 - Practical Tools, Tips, and Tricks |
1818
| [Chapter 8 - Cloud APIs for Computer Vision: Up and Running in 15 Minutes](chapter-8/) |
19-
| Chapter 9 - Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow |
19+
| [Chapter 9 - Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow](chapter-9/) |
2020
| Chapter 10 - AI in the Browser with TensorFlow.js and ml5.js |
2121
| Chapter 11 - Real-Time Object Classification on iOS with Core ML |
2222
| Chapter 12 - Not Hotdog on iOS with Core ML and Create ML |

‎figures/chapter-8/README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
# Chapter 6 - Maximizing Speed and Performance of TensorFlow: A Handy Checklist
1+
# Chapter 8 - Cloud APIs for Computer Vision: Up and Running in 15 Minutes
22

33
Note: All images in this directory, unless specified otherwise, are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
44

55
## Figure List
66

7-
| Figure number | Description | Notes |
8-
|:---|:---|:---|
7+
| Figure number | Description |
8+
|:---|:---|
99
| [8-1](1-clarifai-results.png) | Sample of Clarifai’s results |
1010
| [8-2](2-cognitive-results.png) | Sample of Microsoft Cognitive Services results |
1111
| [8-3](3-google-cloud-results.png) | Sample of Google Cloud Vision’s results |

‎figures/chapter-9/1-stacks-chart.png

79.2 KB
Loading

‎figures/chapter-9/10-uri-gcs.png

41 KB
Loading
189 KB
Loading
Loading
Loading
161 KB
Loading
44.6 KB
Loading
32.8 KB
Loading
132 KB
Loading
70.9 KB
Loading
44.3 KB
Loading
48.4 KB
Loading
Loading
Loading
119 KB
Loading

‎figures/chapter-9/README.md

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
# Chapter 9 - Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow
2+
3+
Note: All images in this directory, unless specified otherwise, are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
4+
5+
## Figure List
6+
7+
| Figure number | Description | Notes |
8+
|:---|:---|:---|
9+
| [9-1](1-stacks-chart.png) | A high-level overview and comparison of different inference serving options | |
10+
| [9-2](2-flask-hello-world.png) | Navigate to http://localhost:5000/hello within a web browser to view the “Hello World!” web page | |
11+
| [9-3](3-mlmodels-listing.png) | Listing page for machine learning models on the Google Cloud ML Engine dashboard | |
12+
| [9-4](4-model-creation-page.png) | Model creation page on Google Cloud ML Engine | |
13+
| [9-5](5-models-listing-page.png) | Model listings page on Google Cloud ML Engine | |
14+
| [9-6](6-model-detail-page.png) | Details page of the just-created Dog/Cat classifier | |
15+
| [9-7](7-cloudml-model-create-version.png) | Creating a new version for a machine learning model | |
16+
| [9-8](8-creating-storage-bucket.png) | Creating a new Google Cloud Storage bucket within the ML model version creation page | |
17+
| [9-9](9-bucket-details.png) | Google Cloud Storage Browser page showing the uploaded Dog/Cat classifier model in TensorFlow format | |
18+
| [9-10](10-uri-gcs.png) | Add the URI for the model you uploaded to Google Cloud Storage | |
19+
| [9-11](11-kubeflow-pipeline.png) | An end-to-end pipeline illustrated in KubeFlow | |
20+
| [9-12](12-kubeflow-notebook-server.png) | Creating a new Jupyter Notebook server on KubeFlow | |
21+
| [9-13](13-kubeflow-creation-obfuscated.png) | Creating a KubeFlow deployment on GCP using the browser | |
22+
| [9-14](14-model-monitoring.png) | Google Cloud ML Engine showing incoming queries and latency of serving the calls, with end-to-end latency at user’s end of about 3.5 seconds | |
23+
| [9-15](15-cost-vs-qps-gcml-byos.png) | Cost comparison of infrastructure as a service (Google Cloud ML Engine) versus building your own stack over virtual machines (Azure VM) (costs as of August 2019) | |

0 commit comments

Comments
 (0)
Please sign in to comment.