Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,127 datasets
YOLO_epoch_26 likely contains a model checkpoint from the 26th training epoch of a YOLO (You Only Look Once) object detection network. The dataset is hosted on Kaggle, a platform for sharing data science projects. Specifics regarding the training data, model architecture, and performance metrics are not provided in the available metadata.
ResNet34-imagenet.pth is a file containing pre-trained model weights for the ResNet34 architecture. It was published on the Kaggle platform. The dataset's specific content, such as the exact training data or version, requires verification after download.
Kaggle hosts this dataset named 'textocr-crnn-crops'. The title suggests it contains cropped image regions likely intended for Optical Character Recognition (OCR) training or evaluation, possibly using a CRNN (Convolutional Recurrent Neural Network) architecture. No further details on size, source, or creation date are available from the provided metadata.
A pre-trained ResNet50 model file for image classification tasks. The file contains weights likely trained on the ImageNet dataset. It was published on Kaggle, but the author and specific training details are unknown.
Annotations_yolo is a dataset hosted on Kaggle. The title suggests it contains annotation files formatted for the YOLO object detection framework. The dataset's author, organization, and specific content details are not provided.
Model weights for an MResNet architecture, likely for image classification tasks. The dataset is hosted on Kaggle, but its origin, creation date, and the specific training data used are unknown. The author and organization are not specified.
A dataset of images processed for computer vision tasks, likely involving a CNN (Convolutional Neural Network) architecture. The title suggests the images have been split and resized to 224x224 pixels, a common dimension for such models. It is hosted on Kaggle, but details on origin, size, and content are unspecified.
PPE-YOLOv8-Checkpoints is a dataset of model weights for a YOLOv8 object detection model, published on Kaggle. The dataset's specific content, such as the number of checkpoints or the training data used, is not detailed in the available metadata. Its primary purpose appears to be providing pre-trained weights for detecting Personal Protective Equipment (PPE) in images.
PPE-YOLOv8-Checkpoints is a dataset of model weights for a YOLOv8 object detection model, published on Kaggle. The dataset's specific content, such as the number of checkpoints or the training data used, is not detailed in the available metadata. Its primary purpose appears to be providing pre-trained weights for detecting Personal Protective Equipment (PPE) in images.
A dataset conversion of the original DeepBee dataset into YOLO label format. The data likely contains images of honey bee colonies, annotated for computer vision tasks. The author, organization, and specific scale of the dataset are unknown.
The Lunara Aesthetic Dataset is a curated collection of 2,000 high-quality image–prompt pairs. It was created by moonworks for controlled research on prompt grounding, style conditioning, and aesthetic alignment in text-to-image generation. The dataset was last updated on 2026-02 07 05:22:41.
STORM captures incidents like flooded streets and damaged trees reported by Norfolk residents and city staff since 2010. The dataset includes geospatial coordinates, event types, and civic league information for each report. Data is updated during and after inclement weather events and is provided by data.norfolk.gov.
Laboratory results from the Geochemical Baseline Survey of the Environment (G-BASE) program, initiated in 1968. The data includes processed chemical analyses of stream sediments, soil, and water samples collected for high-resolution mapping across mainland Britain.
A purified dataset for brood monitoring, likely containing images of honeybee brood frames. The dataset is formatted for the YOLO object detection model and appears to contain four distinct classes. It originates from the Kaggle platform, but details on the author, organization, and last update are unknown.
Zoning ordinance boundaries for the City of Austin, with data entry beginning in 2001 on a day-forward basis. The dataset contains polygons representing zoning ordinances, though older ordinances are less likely to be included. It is maintained by the City of Austin and was last updated in March 2026.
A dataset titled 'efficientnet-noerasing-final-output' published on Kaggle. The title suggests it contains outputs from an EfficientNet model variant trained without data augmentation involving erasing. The dataset's specific content, size, and creation details are not provided in the available metadata.
A dataset titled 'TBX11_YOLO' published on Kaggle. The title suggests it is likely intended for training or evaluating object detection models using the YOLO (You Only Look Once) framework. The specific subject, scale, and origin of the data are unknown from the provided metadata.
Evaluating CEV-CNN dataset is hosted on Kaggle. The title suggests it is designed for assessing Convolutional Neural Network models. No further metadata is available to confirm its size, origin, or specific content.
Keypoints Session1 is a computer vision dataset published on Kaggle. The dataset likely contains annotated keypoints, which are commonly used for pose estimation or object detection tasks. Its specific content, size, and creation details are not provided in the available metadata.
YOLO_Simulador_split is a dataset hosted on Kaggle. Its title suggests it contains synthetic or simulated imagery intended for training YOLO object detection models. The dataset's specific contents, scale, and creation details are not provided in the available metadata.