Find research datasets worth reusing

opencc-by-4.0Mar 2023View details →

Radio Galaxy Zoo: Tagging Radio Subjects using Text

RadioTalk is a communication platform that enabled members of the Radio Galaxy Zoo (RGZ) citizen science project to engage in discussion threads and provide further descriptions of the radio subjects they were observing in the form of tags and comments. It contains a wealth of auxiliary information which is useful for the morphology identification of complex and extended radio sources. In this paper, we present this new dataset, and for the first time in radio astronomy, we combine text and images to automatically classify radio galaxies using a multi-modal learning approach. We found incorporating text features improved classification performance which demonstrates that text annotations are rare but valuable sources of information for classifying astronomical sources, and suggests the importance of exploiting multi-modal information in future citizen science projects. We also discovered over 10,000 new radio sources beyond the RGZ-DR1 catalogue in this dataset.

Fig. 3 in Motor Stereotypic Behaviors In Zoo Rhesus Monkeys: A Case Study Of The Central Zoo, Kathmandu, Nepal

Fig. 3. Motor stereotypic behavior performed by the captive rhesus monkeys; A — under different time of the day; B — under different begging intensities (ns = statistically not significant difference).

Fig. 4. Probable relationship between the MSB and begging. A in Motor Stereotypic Behaviors In Zoo Rhesus Monkeys: A Case Study Of The Central Zoo, Kathmandu, Nepal

Fig. 4. Probable relationship between the MSB and begging. A — by controlling for sex of the captive monkeys; and, B — by controlling for the different probability of the visitor-monkey interaction (Min. — minutes).

Fig. 2 in Motor Stereotypic Behaviors In Zoo Rhesus Monkeys: A Case Study Of The Central Zoo, Kathmandu, Nepal

Fig. 2. Motor stereotypic behavior shown by the captive rhesus monkeys: A — difference between males and females; and B — on the basis of the different rearing histories (*** statistically significant difference).

Fig. 1 in Motor Stereotypic Behaviors In Zoo Rhesus Monkeys: A Case Study Of The Central Zoo, Kathmandu, Nepal

Fig. 1. Mean time invested on motor stereotypic behavior per focal sampling bout of 30 minutes by adult males and females (*** statistically significant difference).

opencc-by-4.0Jul 2023View details →

EuroSAT Model Zoo: A Dataset of Diverse Populations of Neural Network Models - EuroSAT

Abstract 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 27 model zoos with varying hyperparameter combinations are generated and includes 50’360 unique neural network models resulting in over 2’585’360 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. Dataset This dataset is part of a larger collection of model zoos and contains the zoos trained on EuroSAT. All zoos with extensive information and code can be found at <a href="http://www.modelzoos.cc">www.modelzoos.cc</a>. This repository contains two types of model populations: the base model zoo ("eurosat_cnn_kaiming_uniform.zip"), as well as a collection of sparsified model zoos (filenames ending in "magn_XX.zip" or "ard.zip"). Zoos are trained with CNN models in configurations varying the seed only (seed), and sparsification is done through magnitude-based weight pruning ("magn_XX.zip") or  varational dropout ("ard.zip"). For more information on the zoos and code to access and use the zoos, please see <a href="http://www.modelzoos.cc">www.modelzoos.cc</a>.

opencc-by-4.0Jan 2022View details →

Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Zoo

# Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Gym ## Overview * Test datasets and files for testing the [segmentation gym](https://github.com/Doodleverse/segmentation_gym) program for image segmentation * Data set made by Daniel Buscombe, Marda Science LLC. This is version 5.0 * Dataset consists of a time-series of Landsat-8 images of Cape Hatteras National Seashore, courtesy of the U.S. Geological Survey. * Imagery spans the period February 2015 to September 2021. * Labels were created by Daniel Buscombe, Marda Science, using the labeling program [Doodler](https://github.com/Doodleverse/dash_doodler). Download this file and unzip to somewhere on your machine (although *not* inside the `segmentation_gym` folder), then see the relevant page on the [segmentation gym wiki](https://github.com/Doodleverse/segmentation_gym/wiki) for further explanation. This dataset and associated models were made by Dr Daniel Buscombe, Marda Science LLC, for the purposes of demonstrating the functionality of Segmentation Gym. The labels were created using [Doodler](https://github.com/Doodleverse/dash_doodler/). Previous versions: 1.0. https://zenodo.org/record/5895128#.Y1G5s3bMIuU original release, Oct 2021, conforming to Segmentation Gym functionality on Oct 2021 2.0 https://zenodo.org/record/7036025#.Y1G57XbMIuU, Jan 23 2022, conforming to Segmentation Gym functionality on Jan 23 2022 This is version 5.0, created 7/20/23, and has been tested with Segmentation Gym using doodleverse-utils 0.0.33 https://pypi.org/project/doodleverse-utils/0.0.33/   ## file structure ```{sh} /Users/Someone/my_segmentation_zoo_datasets                     │   ├── config                     │   |    └── *.json                     │   ├── capehatteras_data                     |   |   ├── fromDoodler                     |   |   |     ├──images                     │   |   |     └──labels                     |   |   ├──npzForModel                     │   |   └──toPredict                     │   └── modelOut                     │       └── *.png                     │   └── weights                     │       └── *.h5 ``` ## config There are 4 config files: 1. `/config/hatteras_l8_resunet.json` 2. `/config/hatteras_l8_vanilla_unet.json` 3. `/config/hatteras_l8_resunet_model2.json` 4. `/config/hatteras_l8_segformer.json`     The first two are for res-unet and unet models respectively. The third one differs from the first only with specification of kernel size. It is provided as an example of how to conduct model training experiments, modifying one hyperparameter at a time in the effort to create an optimal model. The last one is based on the new Segformer model architecture. They all contain the same essential information and differ as indicated below ``` {   "TARGET_SIZE": [768,768], # the size of the imagery you wish the model to train on. This may not be the original size   "MODEL": "resunet", # model name. Otherwise, "unet" or "segformer"   "NCLASSES": 4, # number of classes   "KERNEL":9, # horizontal size of convolution kernel in pixels   "STRIDE":2, # stride in convolution kernel   "BATCH_SIZE": 7, # number of images/labels per batch   "FILTERS":6, # number of filters   "N_DATA_BANDS": 3, # number of image bands   "DROPOUT":0.1, # amount of dropout   "DROPOUT_CHANGE_PER_LAYER":0.0, # change in dropout per layer   "DROPOUT_TYPE":"standard", # type of dropout. Otherwise "spatial"   "USE_DROPOUT_ON_UPSAMPLING":false, # if true, dropout is used on upsampling as well as downsampling   "DO_TRAIN": false, # if false, the model will not train, but you will select this config file, data directory, and the program will load the model weights and test the model on the validation subset   if true, the model will train from scratch (warning! this will overwrite the existing weights file in h5 format)   "LOSS":"dice", # model training loss function, otherwise "cat" for categorical cross-entropy   "PATIENCE": 10, # number of epochs of no model improvement before training is aborted   "MAX_EPOCHS": 100, # maximum number of training epochs   "VALIDATION_SPLIT": 0.6, #proportion to use for validation   "RAMPUP_EPOCHS": 20, # [LR-scheduler] rampup to maximim   "SUSTAIN_EPOCHS": 0.0, # [LR-scheduler] sustain at maximum   "EXP_DECAY": 0.9, # [LR-scheduler] decay rate   "START_LR":  1e-7, # [LR-scheduler] start lr   "MIN_LR": 1e-7, # [LR-scheduler] min lr   "MAX_LR": 1e-4, # [LR-scheduler] max lr   "FILTER_VALUE": 0, #if >0, the size of a median filter to apply on outputs (not recommended unless you have noisy outputs)   "DOPLOT": true, #make plots   "ROOT_STRING": "hatteras_l8_aug_768", #data file (npz) prefix string   "USEMASK": false, # use the convention 'mask' in label image file names, instead of the preferred 'label'   "AUG_ROT": 5, # [augmentation] amount of rotation in degrees   "AUG_ZOOM": 0.05, # [augmentation] amount of zoom as a proportion   "AUG_WIDTHSHIFT": 0.05, # [augmentation] amount of random width shift as a proportion   "AUG_HEIGHTSHIFT": 0.05,# [augmentation] amount of random width shift as a proportion   "AUG_HFLIP": true, #  [augmentation] if true, randomly apply horizontal flips   "AUG_VFLIP": false, #  [augmentation] if true, randomly apply vertical flips   "AUG_LOOPS": 10, #[augmentation] number of portions to split the data into (recommended > 2 to save memory)   "AUG_COPIES": 5  #[augmentation] number iof augmented copies to make   "SET_GPU": "0" #which GPU to use. If multiple, list separated by a comma, e.g. '0,1,2'. If CPU is requested, use "-1"   "WRITE_MODELMETADATA": false, #if true, the prompts `seg_images_in_folder.py` to write detailed metadata for each sample file   "LOSS_WEIGHTS": false, #if true, apply per-class weights to loss function   "SET_PCI_BUS_ID": true, #if true, make keras aware of the PCI BUS ID (advanced or nonstandard GPU usage)   "TESTTIMEAUG": true, #if true, apply test-time augmentation when model in inference mode   "WRITE_MODELMETADATA": true,# if true, write model metadata per image when model in inference mode   "OTSU_THRESHOLD": true# if true, and NCLASSES=2 only, use per-image Otsu threshold rather than decision boundary of 0.5 on softmax scores } ``` ## capehatteras_data Folder containing all the model input data ```{sh}                     │   ├── capehatteras_data: folder containing all the model input data                     |   |   ├── fromDoodler: folder containing images and labels exported from Doodler using [this program](https://github.com/dbuscombe-usgs/dash_doodler/blob/main/utils/gen_images_and_labels_4_zoo.py)                     |   |   |     ├──images: jpg format files, one per label image                     │   |   |     └──labels: jpg format files, one per image                     |   |   ├──npz4gym npz format files for model training using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/train_model.py) that have been created following the workflow [documented here](https://github.com/dbuscombe-usgs/segmentation_zoo/wiki/Create-a-model-ready-dataset) using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/make_nd_dataset.py)                     │   |   └──toPredict: a folder of images to test model prediction using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/seg_images_in_folder.py) ``` ## modelOut PNG format files containing example model outputs from the train ('_train_' in filename) and validation ('_val_' in filename) subsets as well as an image showing training loss and accuracy curves with `trainhist` in the filename. There are two sets of these files, those associated with the residual unet trained with dice loss contain `resunet` in their name, and those from the UNet are named with `vanilla_unet`. ## weights There are model weights files associated with each config files.

opencc-zeroMar 2019View details →

Miniatura zoo-antropomorfa Diaguita

Miniatura zoo-antropomorfa Diaguita elaborada en piedra. Representa un tipo de conejo antropomorfo en posición incada el cual sostiene un hacha en una sus manos y una posible tableta de alucinógenos en la otra. Fue donado por Ricardo Latcham en 1937 y proviene de Ovalle. (modelo por F.G.) Source: Objaverse 1.0 / Sketchfab

opencc-by-4.0Mar 2024View details →

Harmonized data and R code for "Coherent response of zoo- and phytoplankton assemblages to global warming since the Last Glacial Maximum"

Harmonized data and R code for "Coherent response of zoo- and phytoplankton assemblages to global warming since the Last Glacial Maximum" by Tonke Strack, Lukas Jonkers, Marina C. Rillo, Karl-Heinz Baumann, Helmut Hillebrand and Michal Kucera (submitted to Global Ecology and Biogeography, 2024). STRUCTURED ABSTRACT Aim: We use the fossil record of different marine plankton groups to determine how their biodiversity changed during past climate warming comparable to projected future warming. Location: North Atlantic Ocean and adjacent seas. Time series cover a latitudinal range of 75°N to 6°S. Time period: Past 24,000 years, i.e., from the Last Glacial Maximum (LGM) to the current warm period covering the last deglaciation. Major taxa studied: Planktonic foraminifera, dinoflagellates and coccolithophores. Methods: We analyse time series of fossil plankton communities using principal component analysis and generalised additive models to estimate the overall trend of temporal compositional change in each plankton group and identify periods of significant change. We further analyse local biodiversity change by analysing species richness, species gains and losses, and the effective number of species in each sample and compare alpha diversity to the LGM mean. Results: All plankton groups show remarkably similar trends in the rates and spatio-temporal dynamics of local biodiversity change and a pronounced non-linearity with climate change in the current warm period. Assemblages of planktonic foraminifera and dinoflagellates started to significantly change with the onset of global warming around 15,500 to 17,000 years ago and continued to change at the same pace during the current warm period until at least 5,000 years ago, while coccolithophores assemblages changed at a constant rate throughout the past 24,000 years seemingly irrespective of the prevailing temperature change. Main conclusions: The climate change during the transition from the LGM to the current warm period led to a long-lasting reshuffling of the zoo- and phytoplankton assemblages likely associated with the emergence of new ecological interactions and possibly a shift in the dominant drivers of plankton assemblage change from more abiotic-dominated causes during the last deglaciation to more biotic-dominated causes with the onset of the Holocene. CONTENT This dataset includes the harmonized assemblage data of the three investigated plankton groups (planktonic foraminifera, dinoflagellates and coccolithophores) as well as all the R code needed to re-produce the results of this study and it's main figures. Scripts written by Tonke Strack DATA SOURCES 1)  GMST: Osman, M. B. et al. Globally resolved surface temperatures since the Last Glacial Maximum.            Nature 599, 239-244, doi:10.1038/s41586-021-03984-4 (2021). 2) WOA18: Locarnini, R. A. et al. World Ocean Atlas 2018, Volume 1: Temperature. A. Mishonov, Technical Editor.            NOAA Atlas NESDIS 81, 52 (2019). 3) plankton assemblage data: individual data references provided in CoreList.csv DATA 1. Harmonized assemblage data*: FullDataTable_PF_harmonized.txt 2. Core list of additional information on time series: CoreList.csv 3. Reference lists for species names names: ReferenceList_PlanktonicForaminifera.csv, ReferenceList_Dino.csv, ReferenceList_Cocco.csv CODE 1. 01_LoadData.R: loads harmonized assemblage data from planktonic foraminifera, dinocyst and coccolithophores 2. 02_GMST_import.R: loads loads the globally resolved surface temperature since the LGM from Osman et al. (2011) 3. 03_DataAnalysis_PCA_GAM.R:  PCA/GAM analysis on the plankton assemblage data (results shown in Figure 2 and 3), sensititvity analysis (results shown in Figure 4), and some summary statistics 4. 04_DataAnalysis_MH_GAM_AlternativeApproach.R: alternative GAM approach using Morisita-Horn index (results shown in Figure S2, S3 and S4) 5. 05_DataAnalysis_BiodiversityChange.R: local biodiversity change analysis of individual time series  (results shown in Figure 5, 6 and S9) *Assemblage data of individual time series were manually downloaded, quality checked, taxonomically harmonized, and combined into one data file. Planktonic foraminifera data were harmonized following Siccha and Kuchera (2017). We merged Globigerinoides ruber ruber and Globigerinoides ruber  albus, because some studies only reported them together as Globigerinoides ruber. Also, P/D intergrades (an informal category of morphological intermediates between Neogloboquadrina incompta and Neogloboquadrina dutertrei) were merged with Neogloboquadrina incompta. Dinocyst taxonomy was harmonized following de Vernal et al. (2020) with slight additions following Zonneveld et al. (2013). Names that could not be resolved using synonym lists and assigned a harmonized name following de Vernal et al. (2020) and Zonneveld et al. (2013) were treated as unidentified specimens and were excluded from the assemblage analyses. These specimens were present in 4 time series and were rare taxa (relative abundances < 3%). The protoperidinoids were also excluded from further assemblage analyses as this category includes all unidentified brownish cysts (de Vernal et al., 2020). Coccolithophore taxonomy follows Young et al. (2003) and coccolith countings were conducted on a scanning-electron microscope (SEM) to ensure that all specimens are resolved to the species level. We merged Coccolithus pelagicus subspecies, because they were not distinguished in all studies.  Species not reported in the time series data were assumed to be absent (that is, zero abundance) which is in accordance with the completeness of the counts reported in the original studies. The original data were either given in absolute or relative abundances, and after excluding unnecessary columns (unidentified or rare taxa that could not be harmonised) the abundances were recalculated to 100 %. In total, 41 species of planktonic foraminifera, 30 species of coccolithophores and 53 species of organic-walled dinocysts were observed in our study. REFERENCES de Vernal, A., Radi, T., Zaragosi, S., Van Nieuwenhove, N., Rochon, A., Allan, E., . . . Richerol, T. (2020). Distribution of common modern dinoflagellate cyst taxa in surface sediments of the Northern Hemisphere in relation to environmental parameters: The new n=1968 database. Mar. Micropaleontol., 159. doi:10.1016/j.marmicro.2019.101796 Siccha, M. & Kucera, M. ForCenS, a curated database of planktonic foraminifera census counts in marine surface sediment samples. Sci. Data 4, 170109, doi:10.1038/sdata.2017.109 (2017). Young, J. R., Geisen, M., Cros, L., Kleijne, A., Sprengel, C., Probert, I., & Østergaard, J. B. (2003). A guide to extant coccolithophore taxonomy. Journal of Nannoplankton Research Special Issue, 1, 1-125. doi:10.58998/jnr2297 Zonneveld, K. A. F., Marret, F., Versteegh, G. J. M., Bogus, K., Bonnet, S., Bouimetarhan, I., . . . Young, M. (2013). Atlas of modern dinoflagellate cyst distribution based on 2405 data points. Rev. Palaeobot. Palynol., 191, 1-197. doi:10.1016/j.revpalbo.2012.08.003

Segmentation Zoo UNet models for Landsat-8 satellite imagery, Coast Train v1 Landsat-8 4-class subset.

Doodleverse/Segmentation Zoo UNet models for Landsat-8 satellite imagery, Coast Train v1 Landsat-8 4-class subset. These UNet model data are based on the Coast Train v1 Landsat-8 labeled imagery subset. Models have been fitted to 4 different types of data 1. NDWI (1 band): (g-nir)/(g+nir) 2. MNDWI (1 band): (swir-g)/(swir+g) 3. RGB (3 band): red, green, blue 4. RGB-NIR-SWIR (5 band): red, green, blue, nir, swir Classes are: {0: water, 1: whitewater, 2:sediment, 3:other}. These classes have been remapped from the original 11 classes   These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym

Segmentation Zoo Res-UNet models for Landsat-8 satellite imagery, Coast Train v1 Landsat-8 4-class subset.

Doodleverse/Segmentation Zoo models for Landsat-8 satellite imagery, Coast Train v1 Landsat-8 4-class subset. These model data are based on the Coast Train v1 Landsat-8 labeled imagery subset. Models have been fitted to 4 different types of data 1. NDWI (1 band): (g-nir)/(g+nir) 2. MNDWI (1 band): (swir-g)/(swir+g) 3. RGB (3 band): red, green, blue 4. RGB-NIR-SWIR (5 band): red, green, blue, nir, swir Classes are: {0: water, 1: whitewater, 2:sediment, 3:other}. These classes have been remapped from the original 11 classes   These files are used in conjunction with Segmentation Zoo* For each model, there are 3 files: 1. 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. 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   3. model card file: this is a json file containing the following 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   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym

Doodleverse/Segmentation Zoo Res-UNet models for identifying coins in photos of sediment.

Doodleverse/Segmentation Zoo models for identifying coins in photos of sediment. These model data are based on images of sand and coins and associated labels. Models have been fitted to the following types of data 1. RGB (3 band): red, green, blue Classes are: {0: other, 1: coin}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in oblique aerial photos of coasts.

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in oblique aerial photos of coasts. These model data are based on images of coasts and associated labels. Models have been fitted to the following types of data 1. RGB (3 band): red, green, blue Classes are: {0: water, 1: land}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym

opencc-by-4.0Apr 2022View details →

Doodleverse/Segmentation Zoo UNet models for identifying water in orthomosaic photos of coasts.

Doodleverse/Segmentation Zoo UNet models for identifying water in orthomosaic photos of coasts.   Based on Coast Train data 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, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>. These model data are based on images of coasts and associated labels. Models have been fitted to the following types of data 1. RGB (3 band): red, green, blue Classes are: {0: null, 1: water}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym

opencc-by-4.0Jul 2022View details →

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 MNDWI images of coasts.

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 MNDWI images of coasts. Based on SWED*** data https://openmldata.ukho.gov.uk/ These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data 1. MNDWI (1 band): mndwi MNDWI = (Green - SWIR) / (Green + SWIR)    Green = pixel values from the green band    SWIR = pixel values from the short-wave infrared band Reference: Xu, H. "Modification of Normalised Difference Water Index (NDWI) to Enhance Open Water Features in Remotely Sensed Imagery." International Journal of Remote Sensing 27, No. 14 (2006): 3025-3033." (ESRI, 2018) Classes are: {0: null, 1: water}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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 References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym *** https://www.sciencedirect.com/science/article/abs/pii/S0034425722001584

opencc-by-4.0Aug 2022View details →

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 and Landsat RGB images of coasts. CoastTrain-only version

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 and Landsat RGB images of coasts. Based on Coast Train*** data These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data 1. RGB (3 band): red, green, blue Classes are: {0: null, 1: water}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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. '_history.npz' files contain model training metrics   One additional file, BEST_MODEL.txt, contains the name of the model with the highest validation accuracy   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym *** https://dbuscombe-usgs.github.io/CoastTrain/docs/Version%201:%20March%202022/data

opencc-by-4.0Jul 2022View details →

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts. SWED-only version

Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts. Based on SWED*** data https://openmldata.ukho.gov.uk/ These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data 1. RGB (3 band): red, green, blue Classes are: {0: null, 1: water}. These files are used in conjunction with Segmentation Zoo* For each model, there are 3 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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images   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. '_history.npz' files contain model training metrics   One additional file, BEST_MODEL.txt, contains the name of the model with the highest validation accuracy   References * https://github.com/Doodleverse/segmentation_zoo ** https://github.com/Doodleverse/segmentation_gym *** https://www.sciencedirect.com/science/article/abs/pii/S0034425722001584

opencc-bySep 2020View details →

Budapest Zoo - Mini model

This beautuful mini model is locate in the Budapest Zoo showing the most significant buildings of the zoo. Source: Objaverse 1.0 / Sketchfab

opencc-by-4.0Dec 2016View details →

Behavioural Impact of Enclosure Relocation on Asiatic Elephants (Elephas maximus) in Artis Royal Zoo, Amsterdam.

It can have negative consequences when the standards of well-being of animal are not met in a captive environment. The main priority of this study was to determine whether a more enriched enclosure could reduce stereotypic behaviour and increase natural behaviours in captive Asiatic elephants, and thus increase well-being. In order to answer this question the Asiatic elephants in Artis Royal Zoo were studied. Artis Royal Zoo had built a new enclosure to improve the well-being of their elephants. Activity budgets of the three elephants of both the new and old enclosure were studied. Observation was done over a period of three months ,between April 2017 and July 2017 for a total of 26 days. Only Thong-Thai, mother of Yindee and Sanuk, exhibited stereotypic behaviour. There was a significant difference found between the stereotypic behaviour averages per enclosure when consume/forage behaviour and enclosures were included in the model. Both Thong-Thai and Yindee reduced their consume/foraging behaviour when relocated. All three elephants increased in walking behaviour when relocated with a maximum difference exhibited by Yindee. Only Yindee increased in enrichment use behaviour. Also, like Rees (2009), a negative correlation was found between stereotypic behaviour and consume/foraging behaviour in both enclosures. The behavioural data can only give an indication of improved well-being and we may not have seen extreme positive signs yet but we can say that the new enclosure provides a more abundant set of options to the elephants. These extra options remove mental and physical barriers and stimulate the animal to exhibit natural behaviour which can only be a good thing (McPhee & Carlstead, 2010).