The location, name, and size of existing fitness stations in the City of Casey. This data was captured for Recreation Planning Assessments in 2019, extracted from the City of Casey's Asset Management System and GIS databases.

===###

This synthetic dataset, centred on ART for HIV, was synthesised employing the model outlined in reference [1], incorporating the techniques of WGAN-GP+G_EOT+VAE+Buffer.

This dataset serves as a principal resource for the Centre for Big Data Research in Health (CBDRH) Datathon (see: CBDRH Health Data Science Datathon 2023 (cbdrh-hds-datathon-2023.github.io)). Its primary purpose is to advance the Health Data Analytics (HDAT) courses at the University of New South Wales (UNSW), providing students with exposure to synthetic yet realistic datasets that simulate real-world data.

The dataset is composed of 534,960 records, distributed over 15 distinct columns, and is preserved in a CSV format with a size of 39.1 MB. It contains information about 8,916 synthetic patients over a period of 60 months, with data summarised on a monthly basis. The total number of records corresponds to the product of the synthetic patient count and the record duration in months, thus equating to 8,916 multiplied by 60.

The dataset's structure encompasses 15 columns, which include 13 variables pertinent to ART for HIV as delineated in reference [1], a unique patient identifier, and a further variable signifying the specific time point.

===

This dataset forms part of a continuous series of work, building upon reference [2]. For further details, kindly refer to our papers: [1] Kuo, Nicholas I., Louisa Jorm, and Sebastiano Barbieri. "Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIV." arXiv preprint arXiv:2208.08655 (2022). [2] Kuo, Nicholas I-Hsien, et al. "The Health Gym: synthetic health-related datasets for the development of reinforcement learning algorithms." Scientific Data 9.1 (2022): 693.

===

Latest edit: 16th May 2023.

Doodleverse/Segmentation Zoo/Seg2Map Res-UNet models for DeepGlobe/7-class segmentation of RGB 512x512 high-res. images

These Residual-UNet model data are based on the DeepGlobe dataset

Models have been created using Segmentation Gym* using the following dataset**: https://www.kaggle.com/datasets/balraj98/deepglobe-land-cover-classification-dataset

Image size used by model: 512 x 512 x 3 pixels

classes: 1. urban 2. agricultural 3. rangeland 4. forest 5. water 6. bare 7. unknown

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function train_model.py. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function seg_images_in_folder.py. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the config file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function train_model.py

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function train_model.py

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References *Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D. and Raskar, R., 2018. Deepglobe 2018: A challenge to parse the earth through satellite images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 172-181).

Location of outdoor gyms (i.e. exercise stations or trim trails) within the Dún Laoghaire-Rathdown administrative area. These files contain data relating to the location of trim trails/exercise stations managed by Dún Laoghaire-Rathdown County Council. Exercise station is an area where outdoor gym equipment is located in a group and trim trail is where they are located throughout a Park or open space. Additional information type of facility and ITM coordinates. Information is indicative only and may be subject to update.

The “All Activity Trend” shows the number of positive cases that were interviewed (bar graph) and the percentage of those interviewed who reported each select high to moderate exposure activity types (i.e. personal care, dining out, social-related activities, work, travel, gym/fitness, sports, and faith-related events) during their exposure period (trend lines) on a weekly basis.Note: Data subject to change on a daily basis. Data are restricted to positive cases with a completed contact tracing interview. Possible exposure data are collected during the contact tracing interview as self-reported activities occurring within the 2-week period before the date of symptom onset for symptomatic individuals or the date of test sample collection for asymptomatic individuals. Data collection methods were altered starting the week of Dec 11 for gym/fitness and sports, so should not be compared to previous values.* High to Moderate Exposure Activity Types are not exhaustive and include travel, personal care, faith events, work, dining out, social events, gym/fitness, and sports.Data is updated on a weekly basis.

The “Event Size” figure shows cumulative data since July 31, 2020 of positive cases interviewed who reported attending an event with at least five attendees and stated the event size (i.e. 5-10, 11-20, 21-50, 51-74, 75+ attendees).Note: Data subject to change on a daily basis. Data are restricted to positive cases with a completed contact tracing interview. Possible exposure data are collected during the contact tracing interview as self-reported activities occurring within the 2-week period before the date of symptom onset for symptomatic individuals or the date of test sample collection for asymptomatic individuals. Data collection methods were altered starting the week of Dec 11 for gym/fitness and sports, so should not be compared to previous values.* High to Moderate Exposure Activity Types are not exhaustive and include travel, personal care, faith events, work, dining out, social events, gym/fitness, and sports.Data is updated on a weekly basis.

Doodleverse/Segmentation Zoo/Seg2Map Res-UNet models for OpenEarthMap/9-class segmentation of RGB 512x512 high-res. images

These Residual-UNet model data are based on the [OpenEarthMap dataset](https://open-earth-map.org/)

Models have been created using Segmentation Gym* using the following dataset**: https://zenodo.org/record/7223446#.Y9gtWHbMIuV

Image size used by model: 512 x 512 x 3 pixels

classes:
1. bareland
2. rangeland
3. development
4. road
5. tree
6. water
7. agricultural
8. building
9. nodata

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References
*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Xia, Yokoya, Adriano, & Broni-Bediako. (2022). OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7223446

Source: National Sport & Exercise Participation Survey (NSPS). NSPS is a nationwide survey conducted by Sport Singapore to track sport and physical activity participation amongst Singapore Residents aged 13+ years, with data collected continously across the year and with robust annual sample sizes of at least 4,500 and weighted to reflect the population. This data shows trend of top sports and exercise participated in the past 4 weeks. For more details on the National Sport & Exercise Participation Survey and access to related datasets, please visit the Sport Data Exchange Singapore (SportDexSG) portal at www.sportdexsg.gov.sg/. SportDexSG is a digital platform developed by Sport Singapore to facilitate the sharing of data and insights between sport ecosystem players in Singapore and beyond.

Flux Gym

Dead simple web UI for training FLUX LoRA with LOW VRAM (12GB/16GB/20GB) support.

Frontend: The WebUI forked from AI-Toolkit (Gradio UI created by https://x.com/multimodalart) Backend: The Training script powered by Kohya Scripts

FluxGym supports 100% of Kohya sd-scripts features through an Advanced tab, which is hidden by default.

  What is this?

I wanted a super simple UI for training Flux LoRAs The AI-Toolkit project is great, and the gradio UI… See the full description on the dataset page: https://huggingface.co/datasets/crystantine/fluxgym.

Tutkimuksessa kartoitettiin peruskoulun kuudesluokkalaisten käsityksiä leikistä, koulusta, harrastuksista ja vapaa-ajasta. Aluksi kysyttiin, onko vastaajien mielestä kaikilla lapsilla oikeus leikkiä, onko oikeus leikkiin lakisääteistä, milloin lapset yleensä lopettavat leikkimisen, lopettavatko liian aikaisin ja miksi vastaajat itse lopettivat leikkimisen. Seuraavaksi esitettiin kysymyksiä koulusta ja välitunneista. Kysyttiin, onko luokassa tai koulussa säännöt, joita kaikkien tulee noudattaa, puhutaanko niissä kiusaamisesta, reiluudesta ja toisten huomioon ottamisesta sekä onko koulupihalla tarpeeksi leikki- ja pelipaikkoja. Lisäksi kysyttiin, montako kaveria vastaajilla on omassa koulussaan ja ovatko liikuntatunnit kivoja useimmiten, joskus, harvoin vai ei koskaan. Harvoin tai ei koskaan vastanneilta kysyttiin myös syitä vastaukseensa (esim. liiallinen kilpailu, liiallinen leikkiminen, kaikki eivät pääse pelaamaan yhtä paljon, epätasapuolinen kohtelu tai kiusaaminen liikuntatunneilla). Välitunteihin liittyen esitettiin vielä väittämiä, joissa käsiteltiin yksinäisyyttä, kiusatuksi tulemista ja kiusaamista. Tämän jälkeen selvitettiin, miten vastaajat käyttävät vapaa-aikansa. Lueteltuja vapaa-ajan viettotapoja olivat muun muassa liikkuminen ja leikkiminen, ohjatut harrastukset ja kerhot, internet, tietokonepelit, lukeminen, kotityöt, käsityöt, kavereiden kanssa oleilu, musiikin kuuntelu ja lemmikkien hoito. Lisäksi kysyttiin, onko ympäristössä vastaajien ikäisille tarpeeksi leikki- ja oleskelupaikkoja, onko vastaajilla riittävästi kavereita sekä kuinka usein nämä tapaavat kavereitaan vapaa-ajalla. Loput kysymykset liittyivät ohjattuihin vapaa-ajan harrastuksiin. Aluksi kysyttiin ovatko vastaajat mukana tai olleet joskus mukana ohjatussa harrastustoiminnassa. Niitä, jotka vastasivat ei, pyydettiin erittelemään syitä, kuten perheen rahatilanne, harrastusmahdollisuuksien puute, ajan puute, vanhempien hyväksynnän puute tai kiinnostuksen puute. Vastaajat, jotka olivat joskus olleet mukana ohjatussa harrastustoiminnassa, mutta lopettaneet sen, erittelivät myös syitään lopettamiselle. Ohjatussa harrastustoiminnassa mukana olevilta kysyttiin, kuinka usein he käyvät harrastuksissa, onko harrastusten määrä sopiva ja mitä he harrastavat. Lopuksi esitettiin väittämiä, joissa käsiteltiin muun muassa harrastuksiin liittyviä ponnisteluita, vaativuutta, lahjakkaimpien suosimista, totisuutta, kilpailuhenkeä ja menestyksen tärkeyttä. Taustatietoina aineistossa ovat vastaajan sukupuoli, vanhempien akateemisuus, pysyvät näkyvät sairaudet tai vammat, vastaajia ulkonäössään häiritsevät seikat ja suhtautuminen omaan ulkonäköön sekä etninen tausta. The study investigated the views of Finnish sixth graders in primary education on play, school, hobbies and leisure time. First, the respondents were asked questions relating to play. These covered whether they thought all children have the right to play, whether all children have the right to play according to the law, the school grade on which children stop playing, whether childhood play ends too soon and their own reasons for not playing any more. The second set of questions focused on school and recess time. The respondents were asked whether there were general rules and rules against teasing in their school, whether the school playground was big enough, how many friends they had in school and whether they liked gym class (physical education). Those who answered that they rarely or never liked gym class were asked what the reason was (e.g. the classes are too competitive, the gym teacher does not treat all students equally). The respondents were presented with some statements relating to recess time (e.g. "they tease me during recess") and were asked how often the things described in the statements occurred in their school. The third set of questions surveyed the respondents' free time. Views were probed on how the respondents spent their free time (what they did most often and second most often), whether there were enough places to play and hang out in their surroundings, whether they had enough friends and how often they saw their friends in their free time. The final section investigated supervised activities and hobbies. Those who had never taken part in any supervised activity were asked the reasons for this ("my family has no money for hobbies" etc.). Those who had taken part in supervised activities, but no longer did were asked why they had quit (e.g. "my hobby was too expensive", "I was teased because of my hobby"). Those who took part in supervised activities at the moment of survey were asked how often they took part in such activities, whether they had too many, too few or the right number of hobbies and which hobbies were the most important and second most important to them. Finally, those with a supervised hobby were asked to select a statement best describing their most important and second most important hobbies each (e.g. "my hobby is too demanding", "I enjoy my hobby very much"). For background variables, the respondents were asked their gender, whether their parent(s) had an academic degree, whether they suffered from a permanent, visible handicap or injury (and what this illness had an effect on), whether there was something in their appearance that disturbed them and that others noticed, how they saw themselves and what their ethnic background was.

This report presents information on obesity, physical activity and diet drawn together from a variety of sources for England. More information can be found in the source publications which contain a wider range of data and analysis. Each section provides an overview of key findings, as well as providing links to relevant documents and sources. Some of the data have been published previously by NHS Digital. A data visualisation tool (link provided within the key facts) allows users to select obesity related hospital admissions data for any Local Authority (as contained in the data tables), along with time series data from 2013/14. Regional and national comparisons are also provided. The report includes information on: Obesity related hospital admissions, including obesity related bariatric surgery. Obesity prevalence. Physical activity levels. Walking and cycling rates. Prescriptions items for the treatment of obesity. Perception of weight and weight management. Food and drink purchases and expenditure. Fruit and vegetable consumption. Key facts cover the latest year of data available: Hospital admissions: 2018/19 Adult obesity: 2018 Childhood obesity: 2018/19 Adult physical activity: 12 months to November 2019 Children and young people's physical activity: 2018/19 academic year

Doodleverse/Segmentation Zoo/Seg2Map Res-UNet models for CoastTrain 5-class segmentation of RGB 768x768 NAIP images

These Residual-UNet model data are based on Coast Train images and associated labels. https://coasttrain.github.io/CoastTrain/docs/Version%201:%20March%202022/data

Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.1038/s41597-023-01929-2

Image size used by model: 768 x 768 x 3 pixels

classes:

water

whitewater

sediment

other_bare_natural_terrain

other_terrain

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function train_model.py. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function seg_images_in_folder.py. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the config file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function train_model.py

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function train_model.py

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References *Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Buscombe, D., Wernette, P., Fitzpatrick, S. et al. A 1.2 Billion Pixel Human-Labeled Dataset for Data-Driven Classification of Coastal Environments. Sci Data 10, 46 (2023). https://doi.org/10.1038/s41597-023-01929-2

Doodleverse/Segmentation Zoo/Seg2Map SegFormer models for segmentation of xBD/damaged buildings in RGB 768x768 high-res. images

Models have been created using Segmentation Gym* using the following dataset**: https://arxiv.org/abs/1911.09296

These SegFormer model data are based on 1m spatial footprint images and associated labels of undamaged/damaged buildings.

Image size used by model: 768 x 768 x 3 pixels

classes: no-damage minor-damage major-damage unclassified

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function train_model.py. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function seg_images_in_folder.py. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the config file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function train_model.py

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function train_model.py

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References *Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Ritwik Gupta, Bryce Goodman, Nirav Patel, Ricky Hosfelt, Sandra Sajeev, Eric Heim, Jigar Doshi, Keane Lucas, Howie Choset, and Matthew Gaston. Creating xbd: A dataset for assessing building damage from satellite imagery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2019. https://arxiv.org/abs/1911.09296

Doodleverse/Segmentation Zoo/Seg2Map Res-UNet models for segmentation of buildings of RGB 1024x1024 high-res. images

Models have been created using Segmentation Gym* using the following dataset**: https://github.com/FrontierDevelopmentLab/multi3net

These Residual-UNet model data are based on 1m spatial footprint images and associated labels of buildings in Houston. Imagery made available through DigitalGlobe***

Image size used by model: 1024 x 1024 x 3 pixels

classes: other building

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function train_model.py. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function seg_images_in_folder.py. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the config file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function train_model.py

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function train_model.py

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References *Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Rudner, T. G. J.; Rußwurm, M.; Fil, J.; Pelich, R.; Bischke, B.; Kopačková, V.; Biliński, P. Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery. In AAAI 2019. https://arxiv.org/pdf/1812.01756.pdf

***DigitalGlobe. 2018. DigitalGlobe Open Data Program. https://www.digitalglobe.com/opendata. Online; accessed 2018-09-01.

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other)

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts (water, other)

Description

3649 images and 3649 associated labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts. The 2 classes are 1=water, 0=other. Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue, near-infrared, and short-wave infrared bands only

These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.

Two data sources have been combined

Dataset 1

* 579 image-label pairs from the following data release**** https://doi.org/10.5281/zenodo.7344571
* Labels have been reclassified from 4 classes to 2 classes.
* Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 2 classes.
* These images and labels have been made using the Doodleverse software package, Doodler*.

Dataset 2

• 3070 image-label pairs from the Sentinel-2 Water Edges Dataset (SWED)***** dataset, https://openmldata.ukho.gov.uk/, described by Seale et al. (2022)******
• A subset of the original SWED imagery (256 x 256 x 12) and labels (256 x 256 x 1) have been chosen, based on the criteria of more than 2.5% of the pixels represent water

File descriptions

• classes.txt, a file containing the class names
• images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents
• labels.zip, a zipped folder containing the 1-band label images
• nir.zip, a zipped folder containing the 1-band near-infrared (NIR) images
• swir.zip, a zipped folder containing the 1-band shorttwave infrared (SWIR) images
• overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (red=1=water, blue=0=other)
• resized_images.zip, RGB images resized to 512x512x3 pixels
• resized_labels.zip, label images resized to 512x512x1 pixels
• resized_nir.zip, NIR images resized to 512x512x1 pixels
• resized_swir.zip, SWIR images resized to 512x512x1 pixels

References

*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085https://doi.org/10.1029/2021EA002085. See https://github.com/Doodleverse/dash_doodler.

**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information

****Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571

*****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/

******Seale, C., Redfern, T., Chatfield, P., Luo, C. and Dempsey, K., 2022. Coastline detection in satellite imagery: A deep learning approach on new benchmark data. Remote Sensing of Environment, 278, p.113044.

Doodleverse/Segmentation Zoo/Seg2Map SegFormer models for CoastTrain/8-class segmentation of RGB 768x768 NAIP images

These Segformer model data are based on Coast Train images and associated labels. https://coasttrain.github.io/CoastTrain/docs/Version%201:%20March%202022/data

Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.1038/s41597-023-01929-2

Image size used by model: 768 x 768 x 3 pixels

classes:

water whitewater sediment other_bare_natural_terrain marsh_vegetation terrestrial_vegetation agricultural development

File descriptions

For each model, there are 5 files with the same root name:

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function train_model.py. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function seg_images_in_folder.py. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the config file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function train_model.py

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function train_model.py

Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU

References *Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Buscombe, D., Wernette, P., Fitzpatrick, S. et al. A 1.2 Billion Pixel Human-Labeled Dataset for Data-Driven Classification of Coastal Environments. Sci Data 10, 46 (2023). https://doi.org/10.1038/s41597-023-01929-2

The “Event Distancing Trend” indicates the number of positive cases interviewed per week who reported attending an event with five or more individuals and where social distancing was NOT maintained.Note: Data subject to change on a daily basis. Data are restricted to positive cases with a completed contact tracing interview. Possible exposure data are collected during the contact tracing interview as self-reported activities occurring within the 2-week period before the date of symptom onset for symptomatic individuals or the date of test sample collection for asymptomatic individuals. Data collection methods were altered starting the week of Dec 11 for gym/fitness and sports, so should not be compared to previous values.* High to Moderate Exposure Activity Types are not exhaustive and include travel, personal care, faith events, work, dining out, social events, gym/fitness, and sports.Data is updated on a weekly basis.

1393 Active Global Gym Equipment buyers list and Global Gym Equipment importers directory compiled from actual Global import shipments of Gym Equipment.

The Camden outdoor gym programme is the largest of any borough in the UK. Eight sites opened in 2009 and a further 9th site was installed in 2012. Most Camden residents live within 20 minutes of an outdoor gym. The investment in outdoor gyms followed on from a physical activity needs assessment, which identified that people in Camden found cost and access both barriers to being more physically active. This report is the first stage of the evaluation of Camden’s outdoor gyms which aims to identify: use of outdoor gyms; increases in individual levels of physical activity as a result of outdoor gym use; and to establish what the barriers are preventing other Camden resident’s from using the outdoor gyms.

Doodleverse/Segmentation Gym SegFormer models for 2-class (wood, other) segmentation of RGB aerial orthomosaic imagery

This model release is part of the Doodleverse: https://github.com/Doodleverse

These Residual-UNet model data are based on RGB (red, green, and blue) images of alluvial river corridors and associated labels. Models are designed to identify subaerial accumulations of large woody debris in orthomosaic imagery. Models have been created using Segmentation Gym* using a dataset of images published here:

Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.

Classes: {0=other, 1=large woody debris / driftwood}. See https://github.com/Doodleverse for more information about how this model was trained, and how to use it for inference

File descriptions

1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.

2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.

3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model

4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`

5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`

Additionally,

1. BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU
2. sample_images.zip contains a few example input files, for model testing

3. example_validation_outputs.zip contain 50 example validation outputs, consisting of images of ground truth (right) and model output (left). This provides a visually interpretable product to assess model accuracy

References

*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym

**Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.