Skip to content

Latest commit

 

History

History
59 lines (44 loc) · 9.07 KB

5.AnalysesOf3rdPartyTools.md

File metadata and controls

59 lines (44 loc) · 9.07 KB

Analyses of 3rd party tools

Labelling platforms

Wildlife Insights TrapTagger Trapper
Deployment SaaS SaaS Self-hosted
Scalability - - Python + celery
License Proprietary Open Source Open-source
Handle video
Handle photo
API
Manual upload
Data input Via Google Cloud Platform (GCP) Via Via Amazon S3 Via FTP
Deployment info - - There is no Docker image ready (but there is a Dockerfile), some adjustments in the original repository are necessary [1]
Assumptions - Data output is the same as data input - Data output is the same as data input - Data output is the same as data input

[1] Need AZURE to run with cloud-based storage

Training tools

Roboflow EdgeImpulse TensorFlow Lite
Deployment SaaS SaaS Framework
Dataset management ✅: different data itegration sources here including S3 ✅ : built-in & 3rd party [1] TFDataset: additional lib for dataset storage formating, for management consider DVC, for integration with S3 and other cloud storage formats
Dataset labeling ✅: on platform labeling here as well as integrations here ⚖️ : Built-in for object detection in images only ❌ : Needs integration with 3rd parties
Model training ✅: built-in here ✅: built-in ❌: For training models use TensorFlow
Model management ✅: built-in versioning and re-training ✅ : built-in versioning and re-training ❌ : Consider DVC Model Registry or MLFlow
Model deployment ✅: different deployment targets (here and here) ✅ (+ optimization for edge: export to different architectures) ✅ : Convert the model into an efficient format for edge compute; supported targets can be found here

[1] Edge Impulse : Dataset management

  • A storage bucket in the cloud (S3 compatible)
  • Organizational dataset (platform-hosted repository)

[2] Edge Impulse : Model deployment

  • Wide range of supported targets + custom integrations for Enterprise

Publishing platforms