NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: new torch-based docling models (#120)

Browse Source 
---------

Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2024-10-03 18:42:33 +02:00
committed by GitHub
parent 9ebbbc1245
commit 2422f706a1
30 changed files with 1159 additions and 1185 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
tests/data/redp5695.md
View File

@@ -5,6 +5,27 @@ Front cover
## IBM Cloud Pak for Data on IBM Z
Jasmeet Bhatia
Ravi Gummadi
Srirama Sharma
<!-- image -->
<!-- image -->
<!-- image -->
<!-- image -->
<!-- image -->
<!-- image -->
@@ -180,7 +201,9 @@ For the airline industry, processes such as air traffic management, flight manag
In the following sections, we describe the following use cases:
GLYPH<SM590000> "Use case 1: Responsible AI augmented with risk and regulatory compliance" on page 12 AI model lifecycle governance, risk management, and regulatory compliance are key to the success of the enterprises. It is imperative to adopt a typical AI model lifecycle to protect new end-to-end risks.
GLYPH<SM590000> "Use case 1: Responsible AI augmented with risk and regulatory compliance" on page 12
AI model lifecycle governance, risk management, and regulatory compliance are key to the success of the enterprises. It is imperative to adopt a typical AI model lifecycle to protect new end-to-end risks.
GLYPH<SM590000> "Use case 2: Credit default risk assessment" on page 22
@@ -190,7 +213,9 @@ GLYPH<SM590000> "Use case 3: Clearing and settlement" on page 25
The use of AI can help to predict which trades or transactions have high risk exposures, and propose solutions for a more efficient settlement process.
GLYPH<SM590000> "Use case 4: Remaining Useful Life of an aircraft engine" on page 27 We describe how AI can help to avoid unplanned aircraft downtime by determining the remaining time or cycles that an aircraft engine is likely to operate before failure.
GLYPH<SM590000> "Use case 4: Remaining Useful Life of an aircraft engine" on page 27
We describe how AI can help to avoid unplanned aircraft downtime by determining the remaining time or cycles that an aircraft engine is likely to operate before failure.
GLYPH<SM590000> "Use case 5: AI-powered video analytics on an infant's motions for health prediction" on page 30
@@ -530,7 +555,9 @@ Video processing a stream of data from surveillance systems and then performing
AI is the current "market trend evolution" in video analytics and advancing the decision-making capabilities of the human mind. DL-based computer vision AI techniques are being widely adopted by various industries to solve real-time problems. These techniques improve the detection and prediction accuracy without increasing the hardware cost exponentially. For users, AI greatly reduces the workload of the monitoring staff and provides benefits by detecting unusual incidents and solving many video forensic problems.
S
CP4D was used to build and deploy the AI-powered video analytics on infant's motion for health prediction use case on IBM Z. IBM Z with AI accelerator enables faster inference for detecting face and body movements and performing angle analytics in real time.
Figure 24 shows an architectural diagram about how to design and develop an AI model for real-time body pose detection on IBM Z. A deep convolutional neural network architecture was trained on the task of infant pose estimation on the custom data set by leveraging IBM Cloud Pak for Data.
Figure 24 Architecture for AI-powered video analytics
<!-- image -->
@@ -549,10 +576,6 @@ GLYPH<SM590000> Mediapipe: A library that helps with video streaming processing
GLYPH<SM590000> OpenCV: A real-time computer vision library that helps perform image processing.
CP4D was used to build and deploy the AI-powered video analytics on infant's motion for health prediction use case on IBM Z. IBM Z with AI accelerator enables faster inference for detecting face and body movements and performing angle analytics in real time.
Figure 24 shows an architectural diagram about how to design and develop an AI model for real-time body pose detection on IBM Z. A deep convolutional neural network architecture was trained on the task of infant pose estimation on the custom data set by leveraging IBM Cloud Pak for Data.
WML was used for deployment of the pose detection model and generated notifications to users with web and mobile applications, and it integrates with Fitbit for push notifications so that hospitals and parents can take preventive actions.
## Additional resources
@@ -653,14 +676,11 @@ IBM, the IBM logo, and ibm.com are trademarks or registered trademarks of Intern
The following terms are trademarks or registered trademarks of International Business Machines Corporation, and might also be trademarks or registered trademarks in other countries.
Db2fi IBMfi IBM Blockchainfi IBM Cloudfi IBM Clou d Pakfi IBM Telum™
| Db2fi IBMfi | IBM Watsonfi | Redbooks (log o) fi Turbon |
|----------------------|----------------|------------------------------|
| | IBM z16™ | omicfi |
| IBM Blockchainfi | Instanafi | WebSpherefi |
| IBM Cloudfi IBM Clou | Open Libertyfi | z/OSfi |
| d Pakfi | OpenPagesfi | z16™ |
| IBM Telum™ | Redbooksfi | |
IBM Watsonfi IBM z16™ Instanafi Open Libertyfi OpenPagesfi Redbooksfi
Redbooks (log o) fi Turbon omicfi WebSpherefi z/OSfi z16™
The following terms are trademarks of other companies:
@@ -679,6 +699,9 @@ Other company, product, or service names may be trademarks or service marks of o
Back cover
<!-- image -->
REDP-5695-00
ISBN 0738461067