Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
142
datasets available to search
ShareScore release 0.9.0
Dataset results
142 results for “Zoo”
Galaxy Zoo 2: Images from Original Sample
<p>The Galaxy Zoo team regularly receives requests for subject images for various versions of Galaxy Zoo, in order to facilitate other investigations, e.g. machine learning projects. This repository is an updated attempt to provide those in a way that is useful to the wider community.</p> <p>The images here are meant to be used with the data tables available at <a href="http://data.galaxyzoo.org">data.galaxyzoo.org</a>. They are the "original" sample of subject images in Galaxy Zoo 2 (Willett et al. 2013, MNRAS, 435, 2835, DOI: <a href="https://doi.org/10.1093/mnras/stt1458">10.1093/mnras/stt1458</a>) as identified in Table 1 of Willett et al. and also in Hart et al. (2016, MNRAS, 461, 3663, DOI: <a href="https://doi.org/10.1093/mnras/stw1588">10.1093/mnras/stw1588</a>). The original GZ2 subjects also gave the option to view an inverted version of the subject image; these inverted images are not provided but are easily reproducible from the included subject images. </p> <p><strong>If you use this dataset, please cite</strong> Willett et al. (2013) as the general data release and <em>also</em> cite the DOI for this dataset; if you use the updated debiased tables from Hart et al. (2016) please cite that as well.</p> <p>There are 243,434 images in total. This is off by about 0.08% from the total count in the tables - it's not clear what the cause of the discrepancy is, but we don't think the missing images have any particular sampling bias, so this sample should be useful for research.</p> <p>The images are available in a single zip file (<strong>images_gz2.zip</strong>).</p> <p>The most recent and reliable source for morphology measurements is "GZ2 - Table 1 - Normal-depth sample with new debiasing method – CSV" (from Hart et al. 2016), which is available at <a href="https://data.galaxyzoo.org">data.galaxyzoo.org</a>. To cross-reference the images with Table 1, this sample includes another CSV table (<strong>gz2_filename_mapping.csv</strong>) which contains three columns and 355,990 rows. The columns are:</p> <ul> <li><strong>objid</strong>: the Data Release 7 (DR7) object ID for each galaxy. This should match the first column in Table 1.</li> <li><strong>sample</strong>: string indicating the subsampling of the galaxy. </li> <li><strong>asset_id</strong>: an integer that corresponds to the filename of the image in the zipped file linked above.</li> </ul> <p>As an example row:</p> <p>587722981742084144,original,16</p> <p>The galaxy is 587722981741363294, which is in Table 1 and was identified by GZ2 volunteers as a barred spiral galaxy with a mild bulge and two tightly-wound arms (morphology='Sc2t'). It is in the original GZ2 sample, and can be found in the zipped file as 16.jpg. </p> <p>The overlap between the set of images, the attached table, and Table 1 is not 100%; there are a few rows in the tables that don't have a corresponding image. Again, it's not clear what the exact reason is for this, but we suggest just dropping any missing rows/images from your analysis unless you have a need for analyzing specific subjects. If you do need a 100% complete sample, you can obtain the missing images directly from SDSS. </p> <p>Based on spot checks the mappings between asset ID and DR7 object ID appear correct, but we strongly suggest that you pick some random images and verify on your own that the image seems to match the label/classifications that are listed in Table 1. </p> <p>If you have any issues using this dataset, please contact the Galaxy Zoo team, in particular Brooke Simmons (b.simmons@lancaster.ac.uk). Should Dr Simmons be unavailable, try contacting Karen Masters or Chris Lintott.</p> <p>- the GZ team, 5 Dec 2019<br> </p>
Doodleverse/Segmentation Zoo Res-UNet model for NOAA ERI/4-class segmentation of RGB 512x512 images
<p>This Residual-UNet model is trained on 1,179 pairs of human-generated segmentation labels and images from Emergency Response Imagery (ERI) collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Barry, Delta, Dorian, Florence, Ida, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon. The dataset is available here: https://doi.org/10.5281/zenodo.7268082</p> <p>Models have been created using Segmentation Gym:</p> <p>Code - https://github.com/Doodleverse/segmentation_gym</p> <p>Paper - https://doi.org/10.1029/2022EA002332</p> <p> </p> <p>The model takes input images that are 512 x 512 x 3 pixels, and the output is 512 x 512 x 4, corresponding to 4 classes:</p> <ol> <li>water</li> <li>bare sediment</li> <li>vegetation</li> <li>development (roads, buildings, power lines, parking lots, etc.)</li> </ol> <p> </p> <p>Included here are 6 files with the same root name:</p> <ol> <li> '.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.</li> <li>'.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`.</li> <li> '_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`</li> <li> '.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`</li> <li>'.zip' of the model in the Tensorflow ‘saved model’ format. It is created by the Segmentation Gym function `utils/gen_saved_model.py`</li> <li>'_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</li> </ol> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p>
Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
<p>This repository contains the data released in the paper "Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies" <em>(DOI to follow on publication).</em></p> <p>We release detailed morphology catalogues, both volunteer and automated, for Galaxy Zoo DECaLS.</p> <p>- gz_decals_volunteers_1_and_2 contains volunteer classifications for galaxies classified during the GZD-1 and GZD-2 campaigns.</p> <p>- gz_decals_volunteers_5 similarly contains classifications from the GZD-5 campaign. Note that GZD-5 used a modified schema designed to better detect mergers and weak bars, and includes many galaxies with only approx. five volunteer responses.</p> <p>- gz_decals_auto_posteriors contains the predicted posteriors for volunteer responses to all galaxies used in any campaign. The full posteriors are recorded as Dirichlet distribution concentrations. gz_decals_auto_posteriors also summarises these posteriors as the automated equivalent of previous Galaxy Zoo data releases;<strong> the expected vote fractions (mean posteriors)</strong>. Note that not all posteriors/vote fractions are relevant for every galaxy; we suggest assessing relevance using the estimated fraction of volunteers that would have been asked each question.</p> <p>We include a schema document, schema.md, to define the column names in each catalogue.</p> <p>We also release the galaxy images shown to volunteers on www.galaxyzoo.org during GZD-5. The images on which the automated classifier was trained may be derived from these volunteer-facing images. These images are split into four zip files, each of which contains images named by iauname inside a subfolder named by the first four characters in their iauname. Not all images were labelled during GZD-5 - refer to the catalog for training labels. We are working with the Zenodo team to add these large files to this repository - meanwhile, you can download them from The University of Manchester <a href="https://docs.google.com/document/d/1YgpnxiSJ7ffOW6FY8pX0pw93LTu8rLIdPL2PYhxW1fo/edit?usp=sharing">here</a>.</p> <p>The .csv and .parquet files contain identical data. Parquet is a fast column-oriented binary format which can be read with pd.read_parquet(loc, columns=[some columns]).</p> <p>You may also be interested in the <a href="https://github.com/mwalmsley/zoobot">github repository</a> which contains code to reproduce the model and to fine-tune it for new tasks (including pretrained weights).</p> <p>We will release updates if needed via Zenodo versioning. We recommend using the latest version of this repository. You can check the version you are currently viewing on the right-hand sidebar.</p> <p>Please cite the paper (DOI to follow on publication) when using the data in this repository.</p> <p>---</p> <p>History</p> <p>v0.0.1 (submission) provides the catalog files.</p> <p>v0.0.2 (first revision) renames the catalog files, adds flags for poorly sized galaxies, and includes the galaxy images via the University of Manchester</p>
Model Zoo: A Dataset of Diverse Populations of Neural Network Models - CIFAR10
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 24 model zoos with varying hyperparameter combinations are generated and includes 47’360 unique neural network models resulting in over 2’415’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the zoos trained on CIFAR10. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p>This repository contains two types of files: the raw model zoos as collections of models (file names beginning with "cifar_"), as well as preprocessed model zoos wrapped in a custom pytorch dataset class (filenames beginning with "dataset"). Zoos are trained with small and large CNN models, in three configurations varying the seed only (seed), varying hyperparameters with fixed seeds (hyp_fix) or varying hyperparameters with random seeds (hyp_rand). The index_dict.json files contain information on how to read the vectorized models.</p> <p>For more information on the zoos and code to access and use the zoos, please see www.modelzoos.cc.</p>
Model Zoo: A Dataset of Diverse Populations of Neural Network Models - STL10 - Raw Datasets
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 24 model zoos with varying hyperparameter combinations are generated and includes 47’360 unique neural network models resulting in over 2’415’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the zoos trained on the labelled samples from STL10. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p>This repository contains the raw model zoos as collections of models (file names beginning with "cifar_"). Zoos are trained with small and large CNN models, in three configurations varying the seed only (seed), varying hyperparameters with fixed seeds (hyp_fix) or varying hyperparameters with random seeds (hyp_rand). Due to the large filesize, the preprocessed datasets are hosted in a separate repository. The index_dict.json files contain information on how to read the vectorized models.</p> <p>For more information on the zoos and code to access and use the zoos, please see www.modelzoos.cc.</p>
Model Zoo: A Dataset of Diverse Populations of Neural Network Models - SVHN
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 24 model zoos with varying hyperparameter combinations are generated and includes 47’360 unique neural network models resulting in over 2’415’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the zoos trained on the labelled samples from SVHN. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p>This repository contains two types of files: the raw model zoos as collections of models (file names beginning with "svhn_"), as well as preprocessed model zoos wrapped in a custom pytorch dataset class (filenames beginning with "dataset"). Zoos are trained in three configurations varying the seed only (seed), varying hyperparameters with fixed seeds (hyp_fix) or varying hyperparameters with random seeds (hyp_rand). The index_dict.json files contain information on how to read the vectorized models.</p> <p>For more information on the zoos and code to access and use the zoos, please see www.modelzoos.cc.</p>
Model Zoo: A Dataset of Diverse Populations of Neural Network Models - Fashion-MNIST
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 24 model zoos with varying hyperparameter combinations are generated and includes 47’360 unique neural network models resulting in over 2’415’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the zoos trained on the labelled samples from Fashion-MNIST. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p>This repository contains two types of files: the raw model zoos as collections of models (file names beginning with "fmnist_"), as well as preprocessed model zoos wrapped in a custom pytorch dataset class (filenames beginning with "dataset"). Zoos are trained in three configurations varying the seed only (seed), varying hyperparameters with fixed seeds (hyp_fix) or varying hyperparameters with random seeds (hyp_rand). The index_dict.json files contain information on how to read the vectorized models.</p> <p>For more information on the zoos and code to access and use the zoos, please see www.modelzoos.cc.</p>
Model Zoo: A Dataset of Diverse Populations of Neural Network Models - MNIST
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 24 model zoos with varying hyperparameter combinations are generated and includes 47’360 unique neural network models resulting in over 2’415’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the zoos trained on the labelled samples from MNIST. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p>This repository contains two types of files: the raw model zoos as collections of models (file names beginning with "mnist_"), as well as preprocessed model zoos wrapped in a custom pytorch dataset class (filenames beginning with "dataset"). Zoos are trained in three configurations varying the seed only (seed), varying hyperparameters with fixed seeds (hyp_fix) or varying hyperparameters with random seeds (hyp_rand). The index_dict.json files contain information on how to read the vectorized models.</p> <p>For more information on the zoos and code to access and use the zoos, please see www.modelzoos.cc.</p>
Model Zoo Dataset Samples for Scalable Weight Space Learning
<p>This dataset contains small versions of model zoo datasets for our ICML 2024 paper "Towards Scalable and Versatile Weight Space Learning". These datasets are intended for testing and rapid pipeline evaluation of the code in the <a title="https://github.com/HSG-AIML/SANE" href="https://github.com/HSG-AIML/SANE">corresponding </a><a href="https://github.com/HSG-AIML/SANE">repository</a>. For full model zoos, please see <a href="modelzoos.cc">modelzoos.cc</a>.</p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on 1-band NDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>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.</p> <p>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.</p> <p>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</p> <p>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`</p> <p>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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*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</p> <p>** 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</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 5-band (RGB+NIR+SWIR) images of coasts.
<p>These Residual-UNet model data are based on 5-band RGB+NIR+SWIR (red, green, blue, near-infrared, and short-wave infrared) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571 </a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** 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. <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571</a></p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p> </p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on 1-band MNDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>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.</p> <p>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.</p> <p>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</p> <p>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`</p> <p>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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*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</p> <p>** 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</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, D. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on NDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on MNDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p>
Doodleverse/Segmentation Zoo Res-UNet models for Aerial/NOAA ERI/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for Aerial/NOAA ERI/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images</strong></em></p> <p>Residual-UNet models are trained on 1,179 pairs of human-generated segmentation labels and images from Emergency Response Imagery (ERI) collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Barry, Delta, Dorian, Florence, Ida, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon.</p> <p>The dataset is available here**: https://doi.org/10.5281/zenodo.7268082</p> <p>Models have been created using Segmentation Gym*:</p> <p>Code - https://github.com/Doodleverse/segmentation_gym</p> <p>Paper - https://doi.org/10.1029/2022EA002332</p> <p><br> The model takes input images that are 512 x 512 x 3 pixels, and the output is 512 x 512 x 2, corresponding to 2 classes:</p> <p>1. water <br> 2. other<br> </p> <p>Included here are 6 files with the same root name:</p> <p> '.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.<br> '.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`.<br> '_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`<br> '.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`<br> '.zip' of the model in the Tensorflow ‘saved model’ format. It is created by the Segmentation Gym function `utils/gen_saved_model.py`<br> '_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</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p>References</p> <p><br> *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</p> <p><br> ** Goldstein, Evan B., Buscombe, Daniel, Budavi, Priyanka, Favela, Jaycee, Fitzpatrick, Sharon, Gabbula, Sai Ram Ajay Krishna, Ku, Venus, Lazarus, Eli D., McCune, Ryan, Shah, Manish, Sigdel, Rajesh, & Tagner, Steven. (2022). Segmentation Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon (Version v1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7268083</p>
Doodleverse/Segmentation Zoo Res-UNet models for Aerial/planecam/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for Aerial/planecam/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images</strong></em></p> <p>These Residual-UNet models have been created using Segmentation Gym*</p> <p>Image size used by model: 1024 x 768 x 3 pixels</p> <p>classes:</p> <ol> <li>water</li> <li>other</li> </ol> <p><br> <strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>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.</p> <p>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.</p> <p>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</p> <p>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`</p> <p>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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><strong>References</strong></p> <p><br> *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</p> <p> </p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for Aerial/nadir/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for Aerial/nadir/2-class (water, nowater) segmentation of RGB 1024x768 high-res. images</strong></em></p> <p>These Residual-UNet models have been created using Segmentation Gym* using the following dataset**:</p> <p>Image size used by model: 1024 x 768 x 3 pixels</p> <p>classes:</p> <ol> <li>water</li> <li>other</li> </ol> <p><br> <strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>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.</p> <p>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.</p> <p>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</p> <p>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`</p> <p>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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><strong>References</strong></p> <p><br> *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</p> <p>**</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p><em><strong>Version 3: Updated 2023-04-25</strong></em></p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>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.</p> <p>2.<strong> '.h5'</strong> 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.</p> <p>3.<strong> '_modelcard.json'</strong> 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</p> <p>4. <strong> '_model_history.npz'</strong> 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`</p> <p>5. <strong> '.png'</strong> 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`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, D. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.