Deepomatic Platform
Search…
Deepomatic Platform
v2.3.1
Overview
Release notes
Deepomatic Drive
Getting started
Adding and managing data
Configuring Visual Automation Applications
Training models and model versions
Available architectures
Evaluating performances
Understanding models
Assembling workflows
Publishing Visual Automation Apps
Sharing models among organizations
Harnessing the continuous improvement loop
Deepomatic Engage
Deploying Visual Automation Applications
Integrating Visual Automation Applications
Using Mobile application to capture visual insights on the field
Managing your business operations with customisable solutions
Deepomatic CLI
Presentation
Installation
Setup your API key
Platform commands
Site commands
FAQ
Security
Security
Data Protection
Powered By
GitBook
Available architectures
Here is the complete list of all the neural network architectures available in Studio. When available, links to the research papers are provided.
Classification and tagging architectures
Backbone
Trained on
Input size
Batch size
Research paper
EfficientNet B0
ImageNet
224x224
32
arXiv
EfficientNet B1
ImageNet
240x240
32
arXiv
EfficientNet B2
ImageNet
260x260
32
arXiv
EfficientNet B3
ImageNet
300x300
32
arXiv
EfficientNet B4
ImageNet
380x380
16
arXiv
EfficientNet B5
ImageNet
456x456
8
arXiv
EfficientNet B6
ImageNet
528x528
4
arXiv
Inception-Resnet v2
ImageNet
299x299
32
arXiv
ResNet-50 v2
ImageNet
224x224
32
arXiv
ResNet-101 v2
ImageNet
224x224
32
arXiv
ResNet-152 v2
ImageNet
224x224
32
arXiv
Inception v1
ImageNet
224x224
32
arXiv
Inception v2
ImageNet
224x224
32
arXiv
Inception v3
ImageNet
299x299
32
arXiv
Inception v4
ImageNet
299x299
32
arXiv
VGG 16
ImageNet
224x224
32
arXiv
VGG 19
ImageNet
224x224
32
arXiv
Detection architectures
Architecture
Backbone
Trained on
Input size
Batch size
Research paper
EfficientDet
Eff. Net B0
COCO 2018
512x512
16
arXiv
Eff. Net B1
COCO 2018
640x640
8
arXiv
Eff. Net B2
COCO 2018
768x768
4
arXiv
Eff. Net B3
COCO 2018
896x896
2
arXiv
Eff. Net B4
COCO 2018
1024x1024
1
arXiv
Eff. Net B5
COCO 2018
1280x1280
1
arXiv
Yolo
v2
VOC 2007
416x416
64
arXiv
v3
ImageNet 2012
416x416
64
arXiv
Faster-RCNN
Resnet-50
COCO 2018
1024x1024*
1
arXiv
Resnet-101
COCO 2018
1024x1024*
1
arXiv
RFCN
Resnet-101
COCO 2018
1024x1024*
1
arXiv
SSD
Inception v2
COCO 2018
300x300
24
arXiv
MobileNet v1
COCO 2018
300x300
24
arXiv
MobileNet v2
COCO 2018
300x300
24
arXiv
SSDLite
MobileNet v2
COCO 2018
300x300
24
arXiv
(*) Faster-RCNN
and
RFCN
do not require a fixed image input size. As such they can accept images from 600 to 1024 pixel.
Previous
Training models and model versions
Next
Evaluating performances
Last modified
1mo ago
Copy link
Outline
Classification and tagging architectures
Detection architectures