Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,394 datasets
EfficientNetV2b0-weights is a dataset of pre-trained model weights for the EfficientNetV2-B0 architecture, hosted on Kaggle. The dataset likely contains the parameters necessary to initialize or fine-tune this specific convolutional neural network model. Details regarding the original training data, author, and update history are not provided in the available metadata.
A pretrained deep learning model file for the EfficientNetV2-B0 architecture, likely used for image classification tasks. The file is hosted on Kaggle, but its specific origin, training data, and creation date are not provided in the metadata. The '.h5' file extension indicates it contains model weights saved in the HDF5 format.
EfficientNetV2b0-weights is a dataset of pre-trained model weights for the EfficientNetV2-B0 architecture, hosted on Kaggle. The dataset likely contains the parameters necessary to initialize or fine-tune this specific convolutional neural network model. Details regarding the original training data, author, and update history are not provided in the available metadata.
EfficientNetV2b0-weights-final is a dataset of pre-trained neural network weights published on Kaggle. The dataset likely contains the final trained parameters for the EfficientNetV2-B0 architecture, a model designed for computer vision tasks. Specific details on the training data, author, and update history are not provided in the metadata.
Neil Ketchley's dataset supports research on diplomatic gift-giving to U.S. presidents from 2001 to 2018. It is used to analyze how regime type, such as autocracy versus democracy, influences the value and nature of gifts. The data underpins findings that autocratic regimes systematically spend more on diplomatic gifts.
Temporal_ResNet1D is a dataset hosted on Kaggle. The dataset's title suggests it contains temporal data formatted for use with one-dimensional Residual Network architectures. Its specific content, size, and origin are not detailed in the available metadata.
ServImage is a benchmark dataset for image generation and editing tasks in real-world commercial design services. According to the paper, it contains about 1,070 design tasks and 2,046 deliveries, expanded to roughly 33,000 candidate images. The dataset was created by FengxianUP and was last updated on Hugging Face in January 2026.
Colombia's registry of Politically Exposed Persons (PEPs) as mandated by Decree 830 of 2021, Article 7. The list is compiled by state entities and bodies in the Public Employment Information and Management System (SIGEP). It was last updated on 2025-12-19.
Imagenette is a smaller, more manageable subset of the ImageNet dataset, published on Kaggle. It likely contains labeled images across a reduced number of classes, designed to facilitate rapid experimentation in computer vision. The dataset's exact size, creation date, and author are not specified in the available metadata.
A dataset likely containing annotated images for detecting players in football (soccer) matches. It appears designed for training or benchmarking the YOLOv11 object detection model. The dataset is hosted on Kaggle, but its specific size, creation date, and authorship are unknown.
Kaggle hosts a dataset containing the pre-trained weights for the EfficientNetV2B0 neural network architecture. The dataset likely contains the model parameters necessary for image classification tasks. The author and specific creation details are unknown.
EfficientNetV2-B0 is a convolutional neural network architecture designed for image classification tasks. The dataset likely contains the pretrained weights for the 'b0' variant of this model, published on Kaggle. Specific details about the training data, license, and author are unknown.
2019 to 2021 data on bovine cattle inventory for the Department of Boyacá, Colombia. It contains annual counts of cattle categorized by sex and age group for each municipality. The figures were obtained by the Rural Agricultural Planning Unit (UPRA) of the Ministry of Agriculture in coordination with municipalities.
Kaggle hosts a dataset titled 'freeze cnn v1'. The title suggests it relates to a convolutional neural network model, possibly involving parameters or training data. The dataset is published on Kaggle, but details about its creator, size, and specific contents are unknown.
A dataset of images for object detection in construction environments, likely containing annotated construction items. It is formatted for use with the YOLOv8 model with oriented bounding boxes (OBB). The dataset is published on Kaggle, but specific details about its size, creation date, and author are not provided in the metadata.
An image dataset featuring cats and dogs, published on Kaggle. The dataset's size, annotation details, and creation date are unspecified. Its content is intended for machine learning tasks involving visual recognition of common domestic animals.
A collection of document images aggregated from multiple sources and published on Kaggle. The dataset likely contains various types of scanned or digital documents for analysis. Specific details on the number of images, source institutions, and creation date are not provided in the available metadata.
Best_ResNet18 is a dataset of pre-trained model weights for the ResNet18 architecture, hosted on Kaggle. The platform tags suggest a focus on image classification tasks. The dataset's author, size, and specific training data are not provided in the metadata.
Transparent PNG cutouts of jaguars were generated from the ImageNet dataset using the Segment Anything Model 3 (SAM3). The dataset consists of isolated jaguar subjects, likely intended for training or evaluating segmentation models. The original source is ImageNet, processed with a modern segmentation tool.
Keypoints is a dataset published on Kaggle. The title suggests it contains images with annotated keypoints, likely for tasks like human pose estimation or object landmark detection. Specific details on size, source, and annotation methodology are unavailable from the provided metadata.