Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,487 datasets
Kaggle hosts a pre-trained Convolutional Neural Network (CNN) model identified as 'dhbk_hb_model cnn gei 075 v24.5'. The model's specific architecture, training data, and performance metrics are not detailed in the available metadata. Its author, organization, and last update date are currently unknown.
The dataset title 'dhbk_hb_emb cnn gei 075 v24.5' suggests it contains feature embeddings generated by a Convolutional Neural Network (CNN). It is hosted on Kaggle, a platform for data science and machine learning projects. The specific source, size, and creation date are not provided in the available metadata.
A dataset titled 'YOLO_CrowdHuman' hosted on Kaggle. The title suggests it contains images for training and evaluating object detection models, specifically in crowded human scenes. No further metadata on size, source, or specific annotations is provided.
A pre-trained Convolutional Neural Network (CNN) model, version 24.6, published on Kaggle. The title suggests it may be a model for image analysis, potentially related to a specific architecture or task. The author, organization, and specific training data are unknown.
A collection of images related to autism, hosted on Kaggle. The dataset likely contains visual data for analysis, but specific details on volume, origin, and creation date are not provided in the metadata. Further inspection after download is required to confirm the exact content and scope.
A dataset of image embeddings likely generated by a Convolutional Neural Network (CNN), as suggested by the title. It is hosted on Kaggle, but details on the source images, model architecture, and dataset size are not provided. The version number 'v24.6' indicates it is part of a series of updates or experiments.
Kaggle dataset titled 'human fire smoke using yolov11' suggests a collection of images for object detection. The dataset likely contains annotated images of humans, fire, and smoke, intended for training a YOLOv11 model. Metadata is minimal; the specific source, size, and annotation details are unknown.
MiniImageNet-0shot-cls-dinov2 is a dataset for computer vision tasks, likely derived from the MiniImageNet benchmark. It appears to be formatted for zero-shot classification experiments using the DINOv2 vision transformer model. The dataset is hosted on Kaggle, but its specific size, creation date, and author are not provided in the available metadata.
CGCNN Formation Energy Training Data is a dataset published on Kaggle for material property prediction. The raw description indicates it contains 60,000 CIF files. The specific author, organization, and other metadata are unknown.
A dataset of histopathology images, likely from the NCT-CRC-HE-100K collection. The dataset is hosted on Kaggle and appears to be pre-processed for use with a ResNet18 model. The specific number of images, source institution, and creation date are not provided in the metadata.
RESNET18_Greyscale_NCT-CRC-HE-100K is a dataset of histopathology images, likely derived from the NCT-CRC-HE-100K collection. The title suggests the images are pre-processed into greyscale and may be formatted for use with the ResNet18 convolutional neural network architecture. It is hosted on the Kaggle platform, but detailed metadata such as author, license, and exact size are not provided.
DNCNN-3_Repo is a dataset and resource collection published on Kaggle. The title suggests it is related to the DNCNN (Denoising Convolutional Neural Network) architecture, likely version 3. The dataset likely contains images and model resources for training or benchmarking denoising algorithms.
YOLO26-1st-Runs is a dataset published on Kaggle. The title suggests it contains outputs or logs from the first training runs of a YOLO (You Only Look Once) object detection model, likely version 26. Metadata is minimal; actual content requires verification after download.
LAMBDA_ResNet50_seperated is a dataset published on Kaggle. The title suggests it contains image data, likely separated or processed for use with a ResNet50 architecture. The dataset's specific content, size, and origin require verification after download.
A checkpoint file likely containing trained model weights for an Optical Character Recognition system designed for the Vietnamese language. The dataset is hosted on Kaggle, but its specific contents, creation date, and author are not detailed in the available metadata. Users must download the file to inspect the model architecture, training data, and performance specifics.
A dataset or model named 'my_custom_yolov8n' published on Kaggle. The title suggests a connection to the YOLOv8 architecture, a popular framework for real-time object detection. Specific details on content, size, and authorship are not provided in the available metadata.
A dataset likely for training or benchmarking object detection models, inferred from the title's reference to the YOLO (You Only Look Once) architecture. It was published on the Kaggle platform. The specific contents, scale, and creation details are not provided in the metadata.
Sony's See In The Dark (SID) dataset provides paired images for low-light computer vision research. The dataset is published on Kaggle, but its specific scale, collection method, and update history are not detailed in the provided metadata. Its content likely consists of matching low-light and corresponding normal-light image pairs.
OCR2_O is a dataset hosted on Kaggle, likely containing images and corresponding text for optical character recognition tasks. The dataset's specific content, scale, and origin are not detailed in the provided metadata. Users must download the dataset to verify its exact composition and suitability for their projects.
Michigan Consumer Survey data, likely containing responses from residents of the U.S. state of Michigan. The dataset is hosted on Kaggle and includes a codebook for interpreting the survey variables. Specific details on the number of respondents, survey period, and collection methodology are not provided in the metadata.