Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,396 datasets
Aksara Jawa 350 Sandhangan is a dataset published on Kaggle. The title suggests it contains images of Javanese script characters, specifically the 350 'sandhangan' diacritic marks. The dataset's author, organization, and specific content details are not provided in the metadata.
Colombian public health data tracks acute respiratory infections across outpatient, emergency, hospitalization, ICU admission, and mortality categories. The dataset contains over 30 columns disaggregating patient counts by specific age brackets, from under 1 year to over 60 years old. It is published by the Colombian government's open data portal, with a last recorded update in December 2025.
A fine-tuned model for brain tumor segmentation, likely based on the VGG architecture and Transformer components. The dataset appears to contain model weights or checkpoints trained on the BRATS (Brain Tumor Segmentation) benchmark. It was published on Kaggle, but the author, organization, and specific training details are not provided.
Volatile Organic Compounds (VOCs) are a significant class of air pollutants. This dataset, hosted on Kaggle, likely contains measurements or properties of various VOCs. The specific source, collection method, and data volume are not detailed in the provided metadata.
A checkpoint file for a model trained on the ImageNetV1 dataset, published on Kaggle. The specific architecture, training details, and performance metrics are not provided in the metadata. Users must download and inspect the file to verify its contents and intended use.
A model checkpoint for a computer vision model trained on the ImageNetV1 dataset. The title suggests it is the third checkpoint for a model using a Squeeze-and-Excitation (SE) L4 architecture. It is hosted on Kaggle, but detailed metadata about the model's performance, training specifics, or file contents is not provided.
guitar-gan-weights-v3 is a dataset of pre-trained model weights published on Kaggle. The title suggests it is associated with a Generative Adversarial Network (GAN) for generating or manipulating guitar-related imagery. The dataset's author, organization, and specific content details are not provided in the available metadata.
dhbk_hb_model cnn gei 195 v24.6 is a dataset published on Kaggle. The title suggests it contains weights for a Convolutional Neural Network (CNN) model, likely for image classification or related computer vision tasks. The dataset's author, organization, and specific content details are unknown.
A collection of image embeddings likely generated by a Convolutional Neural Network (CNN), as suggested by the title. The dataset is hosted on Kaggle, but details on its creator, size, and specific source images are unavailable. Its last update status is unknown.
dhbk_hb_model cnn gei 075 v24.16 is a dataset published on Kaggle. The title suggests it contains a convolutional neural network (CNN) model, likely for image-related tasks. The dataset's specific content, size, and origin are not detailed in the provided metadata.
A dataset titled 'Accident severity detection.v5i.yolov8' is hosted on Kaggle. The title suggests it contains images annotated for object detection, likely using the YOLOv8 model format. Metadata is minimal; actual content, scale, and origin require verification after download.
ORGAN_SEGMENTATION_DS is a dataset for computer vision tasks related to medical imaging. It was published on Kaggle, but the author, organization, and data collection details are not provided. The specific organ types, image modalities, and dataset scale are unknown from the available metadata.
Aksara Jawa Sandhangan dataset likely contains images of Javanese script diacritical marks for character recognition tasks. The dataset is hosted on Kaggle, but its author, size, and creation date are unknown. Its content and structure require verification after download.
A dataset of image embeddings likely generated by a Convolutional Neural Network (CNN), as suggested by the title. The dataset is published on Kaggle. Specific details on the number of embeddings, source images, and creation date are unavailable.
Aksara Jawa Sandhangan Dataset is a collection of images for Javanese script diacritical marks, known as sandhangan. The dataset is hosted on Kaggle, but details on its size, creator, and update history are not provided. Its content likely supports the development of tools for reading and preserving traditional Javanese writing systems.
A dataset titled 'new-DataSet-ResNet50-79' was published on Kaggle. The title suggests it is related to the ResNet-50 deep learning architecture, likely for image classification tasks. No further metadata on size, source, or content is available.
A dataset likely containing medical images for the purpose of skin cancer detection using convolutional neural networks. It was published on the Kaggle platform. The specific number of images, collection method, and temporal coverage are unknown from the provided metadata.
A dataset for training and evaluating MASK R-CNN models on brain tumour detection tasks. It is hosted on Kaggle, but the specific number of images, annotation details, and creation date are unknown. The dataset's author, organization, and license information are also not provided in the available metadata.
HASSANBRAINTUMOR is a dataset of brain tumor images intended for computer vision model training. The dataset is hosted on Kaggle, but its size, origin, and specific annotations are not detailed in the provided metadata. Its title suggests a focus on convolutional neural networks and the Mask R-CNN architecture for segmentation tasks.
A Mask R-CNN model likely trained for segmenting brain tumors in medical images. The dataset is hosted on Kaggle, but details about its size, source, and creation date are unavailable. The model's architecture suggests it is designed for pixel-level segmentation tasks in oncology imaging.