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.
40
datasets available to search
ShareScore release 0.9.0
Dataset results
40 results for “Deep learning framework”
UGS-1m: Fine-grained urban green space mapping of 34 major cities in China based on the deep learning framework
<p>Urban green space (UGS) is an important component in the urban ecosystem and has great significance to the urban ecological environment. The UGS-1m product provides the fine-grained UGS maps of 34 major cities/areas in China, which is generated based on a deep learning (DL) framework.</p> <p>The DL framework consists of a generator and a discriminator. The generator is a fully convolutional network designed for UGS extraction (UGSNet), which integrates attention mechanisms to improve the discrimination to UGS, and employs a point rending strategy for edge recovery. The discriminator is a fully connected network aiming to deal with the domain shift between images. To support the model training, an urban green space dataset (UGSet) with a total number of 4,454 samples of size 512×512 is provided. Code for the UGSet and the UGSet will be soon available at: https://github.com/liumency/UGS-1m. </p> <p>The main steps to obtain UGS-1m can be summarized as follows: a) Firstly, the UGSNet will be pre-trained on the UGSet in order to get a good starting training point for the generator; b) After pre-training on the UGSet, the discriminator is responsible to adapt the pre-trained UGSNet to different cities/areas through adversarial training; c) Finally, the UGS results of the 34 major cities/areas in China (UGS-1m) are obtained using 2,343 Google Earth images with a data frame of 7'30" in longitude and 5'00" in latitude, and a spatial resolution of nearly 1.1 meters. Evaluating the performance of the proposed approach on samples from Guangzhou city shows the validity of the UGS-1m products, with an overall accuracy of 87.4% and an F1 score of 81.14%. </p>
On Reporting Performance and Accuracy Bugs for Deep Learning Frameworks: An Exploratory Study from GitHub
<p>This repository aims to store the dataset of performance and accuracy bug reports, which belongs to <em>"On Reporting Performance and Accuracy Bugs for Deep Learning Frameworks: An Exploratory Study from GitHub"</em></p>
Assemblies generated in the manuscript "Geometric deep learning framework for de novo genome assembly"
<p>Assemblies evaluated in the manuscript "Geometric deep learning framework for de novo genome assembly". All the assemblies were generated by us, except CHM13.ONT.Flye-2.9.fa.gz which was generated by <a href="https://www.nature.com/articles/s41587-019-0072-8">Kolmogorov et al. (2019)</a>.</p>
A deep learning framework combining molecular image and protein structural representation identifies candidate drugs for chronic pain
<p>Official dataset for <i>A deep learning framework combining molecular image and protein structural representation identifies candidate drugs for chronic pain</i>. </p><p>The related code can be found at <a href="https://github.com/yuxin212/GPCR-public">here</a> and <a href="https://github.com/ChengF-Lab/LISA-CPI">here</a>. </p><p>The dataset is now public. </p>
A Deep Learning Framework for Pediatric TLE Detection Using 18F-FDG-PET Imaging
ClinicalTrials.gov study NCT04169581. IPD Sharing: NO. Countries: 1. Publications: 1.
A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians - Transfer Learning Application to 7T - Additional Data
<p><strong>Automatically Generated Segmentation Masks for Data Science Bowl Cardiac Challenge Data</strong></p> <p>These segmentation masks have been automatically generated with the <a href="https://github.com/baiwenjia/ukbb_cardiac">ukbb_cardiac</a> network by Bai et al. (2018, <a href="https://doi.org/10.1186/s12968-018-0471-x">doi:10.1186/s12968-018-0471-x</a>). In order to reproduce the data cleaning and conversion: download the data from <a href="https://www.kaggle.com/c/second-annual-data-science-bowl/data">Kaggle</a> and follow the data curation and conversion steps outlined in: <a href="https://github.com/chfc-cmi/cmr-seg-tl">cmr-seg-tl</a> and the associated publication (Link to be added).</p> <p>As this is a derived dataset please abide by the data use rules of the original dataset at kaggle and provide proper citation to the original data:</p> <blockquote> <p>The data for the Data Science Bowl is available for research and academic pursuits. Please cite as ‘Data Science Bowl Cardiac Challenge Data’.</p> </blockquote> <p>Please also cite the Bai et al. article for the algorithm and our publication for the data curation.</p>
CellDeathPred: a deep learning framework for ferroptosis and apoptosis prediction based on cell painting
<p><strong>Data Description:</strong></p> <ul> <li>Two cell death modalities are considered in this study: apoptosis and ferroptosis. The treatments and their cell death types used in these experiments are shown in Figure 1 in the paper. In total we have seven apoptosis and seven ferroptosis inducers. They target specific cell organelles and components. Besides, active treatments there are negative controls DMSO and untreated wells.</li> <li>Every image has a resolution of 1360 x 1024. These four channels were imaged in the experiments. For every well multiple images (fields) are taken typically ten fields.</li> <li>Three plates with four different settings were imaged. 20x non-confocal (very fast [1.5h]), 20x confocal (fast [2.5h]), 40x non-confocal (slow [5h]), 40x confocal (very slow [8h]). All for one time point 28h (incubation time).</li> </ul>
Towards a Unified Benchmark and Framework for Deep Learning-Based Prediction of Nuclear Magnetic Resonance Chemical Shifts
Open the record for dataset details and reuse information.
Track-to-Learn: A general framework for tractography with deep reinforcement learning
<p>Datasets used in the experiments presented in Track-to-Learn: A general framework for tractography using deep reinforcement learning</p> <p>See https://github.com/scil-vital/TrackToLearn to use the datasets and recreate the experiments.</p>
An ensemble deep learning framework to refine large deletions in linked-reads
<p>An ensemble deep learning framework to refine large deletions in linked-reads</p>
The role of low-complexity repeats in RNA–RNA interactions and a deep learning framework for duplex prediction
GEO Series GSE290073. Mus musculus. 8 samples. Type: Expression profiling by high throughput sequencing.
Usability and Clinical Effectiveness of an Interpretable Deep Learning Framework for Post-Hepatectomy Liver Failure Prediction
ClinicalTrials.gov study NCT06031818. IPD Sharing: UNDECIDED. Countries: 1. Publications: 0.
Construction of a Deep Learning-Based Precise Diagnostic Framework for Bladder Tumors Using Ultrasound: A Multicenter, Ambispective Cohort Study
ClinicalTrials.gov study NCT07111364. IPD Sharing: UNDECIDED. Countries: 1. Publications: 0.
m6ATM: a deep learning framework for demystifying m6A epitranscriptome via Nanopore long read RNA-seq data
GEO Series GSE265754. synthetic construct. 3 samples. Type: Expression profiling by high throughput sequencing.
m6ATM: a deep learning framework for demystifying m6A epitranscriptome via Nanopore long read RNA-seq data [HepG2 ]
GEO Series GSE265867. Homo sapiens. 1 samples. Type: Expression profiling by high throughput sequencing.
A deep learning framework for the reconstruction of gene expression profiles derived from formalin-fixed paraffin-embedded samples
GEO Series GSE299799. Homo sapiens. 12 samples. Type: Expression profiling by high throughput sequencing.
A deep learning framework for the reconstruction of gene expression profiles derived from formalin-fixed paraffin-embedded samples
GEO Series GSE298630. Homo sapiens. 5 samples. Type: Expression profiling by high throughput sequencing.
Dataset for the Paper: "Understanding Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study"
<p>This is the dataset for the paper: "Understanding Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study". It contains the 3004 Self-Claimed Assumptions (SCAs) extracted from nine deep learning frameworks (i.e., TensorFlow, Theano, PyTorch, Caffe, MXNet, Keras, CNTK, DL4J, and PaddlePaddle), which includes 2232 unique SCAs that have different content and 772 duplicated SCAs that have the same content as one of the 2232 SCAs.</p>
Dataset for the Paper: "Understanding Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study"
<p>This is the dataset for the paper: "Understanding Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study". It contains the 3084 Self-Claimed Assumptions (SCAs) extracted from nine deep learning frameworks (i.e., TensorFlow, Theano, PyTorch, Caffe, MXNet, Keras, CNTK, DL4J, and PaddlePaddle), which includes 2278 unique SCAs that have different content and 806 duplicated SCAs that have the same content as one of the 2278 SCAs.</p>
A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers
<p>Trained models and basecalled reads.</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.