license: etalab-2.0
tags:
- segmentation
- pytorch
- aerial imagery
- landcover
- IGN
model-index:
- name: FLAIR-INC_RVBIE_unetresnet34_15cl_norm
results:
- task:
type: semantic-segmentation
dataset:
name: IGNF/FLAIR#1-TEST
type: earth-observation-dataset
metrics:
- name: mIoU
type: mIoU
value: 54.72
- name: Overall Accuracy
type: OA
value: 76.37
- name: Fscore
type: Fscore
value: 67.6
- name: Precision
type: Precision
value: 69.35
- name: Recall
type: Recall
value: 67.65
- name: IoU Buildings
type: IoU
value: 82.3
- name: IoU Pervious surface
type: IoU
value: 53.24
- name: IoU Impervious surface
type: IoU
value: 74.17
- name: IoU Bare soil
type: IoU
value: 60.4
- name: IoU Water
type: IoU
value: 87.59
- name: IoU Coniferous
type: IoU
value: 46.35
- name: IoU Deciduous
type: IoU
value: 67.45
- name: IoU Brushwood
type: IoU
value: 30.23
- name: IoU Vineyard
type: IoU
value: 82.93
- name: IoU Herbaceous vegetation
type: IoU
value: 55.03
- name: IoU Agricultural land
type: IoU
value: 52.01
- name: IoU Plowed land
type: IoU
value: 40.84
- name: IoU Swimming pool
type: IoU
value: 48.44
- name: IoU Greenhouse
type: IoU
value: 39.44
pipeline_tag: image-segmentation
Lorem ipsum dolor sit amet. Hic galisum tenetur et perspiciatis odit et aliquid perferendis ut galisum quisquam. Ad veritatis optio ut quaerat tempora sit quae tenetur et quam iste! Et mollitia natus eum facere debitis ut nisi voluptatum qui voluptas iusto hic adipisci voluptas ab reiciendis fuga id nisi quia.
Aut omnis architecto ut quis culpa quo molestiae animi sit explicabo quae ea necessitatibus magni. Et voluptatem velit et quia laudantium aut voluptatem fugit aut labore consequatur et maxime eius aut perferendis placeat. Vel expedita tenetur et dolores cupiditate sed dolorum ratione id quia odio quo sint molestiae ut dicta quos.
Ut iste unde in delectus quia aut reiciendis voluptatem ut voluptatem velit et dolore quia rem quia accusamus. Ab maiores tempore 33 deleniti ipsam a molestiae dolor eos optio optio aut perferendis quasi et expedita ipsum vel similique accusamus.
Model Informations
- Repository: https://github.com/IGNF/FLAIR-1-AI-Challenge
- Paper [optional]: https://arxiv.org/pdf/2211.12979.pdf
- Developed by: IGN
- Compute infrastructure:
- software: python, pytorch-lightning
- hardware: GENCI, XXX
- License: : Apache 2.0
Uses
Bias, Risks, and Limitations
{{ bias_risks_limitations | default("[More Information Needed]", true)}}
Recommendations
{{ bias_recommendations | default("Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", true)}}
How to Get Started with the Model
Use the code below to get started with the model.
{{ get_started_code | default("[More Information Needed]", true)}}
Training Details
Training Data
{{ training_data | default("[More Information Needed]", true)}}
Training Procedure
Preprocessing [optional]
{{ preprocessing | default("[More Information Needed]", true)}}
Training Hyperparameters
- Training regime: {{ training_regime | default("[More Information Needed]", true)}}
Speeds, Sizes, Times [optional]
{{ speeds_sizes_times | default("[More Information Needed]", true)}}
Evaluation
Testing Data, Factors & Metrics
Testing Data
{{ testing_data | default("[More Information Needed]", true)}}
Metrics
{{ testing_metrics | default("[More Information Needed]", true)}}
Results
{{ results | default("[More Information Needed]", true)}}
Summary
{{ results_summary | default("", true) }}
Technical Specifications [optional]
Model Architecture and Objective
{{ model_specs | default("[More Information Needed]", true)}}
Citation [optional]
BibTeX:
{{ citation_bibtex | default("[More Information Needed]", true)}}
APA:
{{ citation_apa | default("[More Information Needed]", true)}}