Detailed System Requirements
Abstract
Deep learning object detection is an advanced capability that generalizes the annotations from your training documents and dynamically applies them when possible. If your documents have a fixed format and the fields are located in the same places, you don't typically need this capability. When deep learning object detection is disabled, IBM Automation Document Processing extracts the fields from the same positions where they were annotated in the page. This works well on those fixed-format documents such as tax forms. If your documents have a dynamic format or sections with variable length, such as invoices, using deep learning object detection may yield better accuracy.
If you disable deep learning object detection, the performance is improved for document processing and data extraction training.
Content
ca_configuration:
ocrextraction:
deep_learning_object_detection:
enabled: false
Small profile recommendations for Content Analyzer components:
ca_configuration:
global:
deployment_profile_size: small
Component |
CPU Request (m) |
CPU Limit (m) |
Memory Request (Mi) |
Memory Limit (Mi) |
Number of Replicas |
Pods are licensed for production/non-production |
OCR Extraction |
200 |
1000 |
1024 |
2048 |
5 |
Yes |
Classify Process |
200 |
500 |
400 |
2048 |
1 |
Yes |
Processing Extraction |
500 |
1000 |
1024 |
3584 |
3 |
Yes |
Natural Language Extractor |
200 |
500 |
600 |
1440 |
2 |
Yes |
Callerapi |
200 |
600 |
600 |
1024 |
1 |
No |
Postprocessing |
200 |
600 |
400 |
800 |
1 |
No |
Setup |
200 |
600 |
600 |
1024 |
2 |
No |
UpdateFileDetail |
200 |
600 |
400 |
600 |
1 |
No |
Backend |
200 |
600 |
400 |
1024 |
2 |
No |
Redis |
100 |
250 |
100 |
640 |
1 |
No |
RabbitMQ |
100 |
1000 |
100 |
1024 |
2 |
No |
Medium profile recommendations for Content Analyzer components:
ca_configuration:
global:
deployment_profile_size: medium
Component |
CPU Request (m) |
CPU Limit (m) |
Memory Request (Mi) |
Memory Limit (Mi) |
Number of Replicas |
Pods are licensed for production/non-production |
OCR Extraction |
200 |
1000 |
1024 |
2048 |
8 |
Yes |
Classify Process |
200 |
500 |
400 |
2048 |
2 |
Yes |
Processing Extraction |
500 |
1000 |
1024 |
3584 |
3 |
Yes |
Natural Language Extractor |
200 |
500 |
600 |
1440 |
2 |
Yes |
Callerapi |
200 |
600 |
600 |
1024 |
2 |
No |
Postprocessing |
200 |
600 |
400 |
800 |
2 |
No |
Setup |
200 |
600 |
600 |
1024 |
4 |
No |
UpdateFileDetail |
200 |
600 |
400 |
600 |
2 |
No |
Backend |
200 |
600 |
400 |
1024 |
4 |
No |
Redis |
100 |
250 |
100 |
640 |
1 |
No |
RabbitMQ |
100 |
1000 |
100 |
1024 |
3 |
No |
Large profile recommendations for Content Analyzer components:
ca_configuration:
global:
deployment_profile_size: large
Component |
CPU Request (m) |
CPU Limit (m) |
Memory Request (Mi) |
Memory Limit (Mi) |
Number of Replicas |
Pods are licensed for production/non-production |
OCR Extraction |
200 |
1000 |
1024 |
2048 |
14 |
Yes |
Classify Process |
200 |
500 |
400 |
2048 |
2 |
Yes |
Processing Extraction |
500 |
1000 |
1024 |
3584 |
6 |
Yes |
Natural Language Extractor |
200 |
500 |
600 |
1440 |
2 |
Yes |
Callerapi |
200 |
600 |
600 |
1024 |
2 |
No |
Postprocessing |
200 |
600 |
400 |
800 |
2 |
No |
Setup |
200 |
600 |
600 |
1024 |
6 |
No |
UpdateFileDetail |
200 |
600 |
400 |
600 |
2 |
No |
Backend |
200 |
600 |
400 |
1024 |
6 |
No |
Redis |
100 |
250 |
100 |
640 |
1 |
No |
RabbitMQ |
100 |
1000 |
100 |
1024 |
3 |
No |
Was this topic helpful?
Document Information
Modified date:
14 November 2022
UID
ibm16590199