Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,431 datasets
A pre-trained Convolutional Neural Network model published on Kaggle. The title suggests it may be version 24.7 of a model, potentially for image-related tasks. Specific details on the model's architecture, training data, and performance are not provided in the available metadata.
A dataset published on Kaggle, likely containing features for computer vision tasks. The title suggests the data may involve CNN (Convolutional Neural Network) embeddings or image features. The author, organization, and specific content are unknown and require verification after download.
A dataset published on Kaggle, likely containing benchmark or training data for quantum convolutional neural networks (QCNNs). The title suggests a scale of approximately 5,000 entries, but specific row counts, column details, and creation details are unconfirmed. The dataset's author, organization, and last update date are unknown.
YOLO11m-v2-pcb likely contains images of printed circuit boards intended for training object detection models. The dataset is published on Kaggle, but its specific size, creation date, and authorship are unknown. Its name suggests it is a version two release of a dataset designed for use with the YOLO object detection framework.
Yolo11s-CBAM-SIoU-Focal-pcb-v2 is a dataset published on Kaggle. The title suggests it contains images for object detection, likely related to printed circuit board (PCB) inspection. The dataset's specific contents, scale, and origin require verification after download.
YoloGymKeypoints is a dataset published on Kaggle. The title suggests it contains images with annotated keypoints, likely for human pose estimation in gym or fitness contexts. The dataset's specific scale, creation details, and update history are not provided in the available metadata.
ResNet-50 is a pre-trained convolutional neural network model for image classification. It is hosted on the Kaggle platform and is tagged as a 'Pre Trained Model'. The dataset likely contains the model's architecture and weights, enabling transfer learning for computer vision tasks.
yolov8s-p2-only-pcb-training-runs is a dataset from Kaggle. The title suggests it contains logs or metrics from training runs for a YOLOv8 model configured for object detection on printed circuit boards (PCBs). The specific content, scale, and origin details are not provided in the available metadata.
A synthetic dataset for optical character recognition tasks. The dataset is published on Kaggle and is tagged as 'Synthetic'. The specific content, scale, and creation details require verification after download.
A dataset for training and evaluating Convolutional Neural Network models, sourced from Kaggle. The specific content, size, and creation details are not provided in the metadata. Users must download the dataset to verify its exact composition and suitability for their tasks.
CNN skin cancer dataset is a collection of medical images for computer vision tasks. The dataset is hosted on Kaggle and is tagged for Computer Vision applications. Specific details regarding the number of images, collection methodology, and licensing are not provided in the available metadata.
Follicle-YOLO is a dataset hosted on Kaggle, likely containing images annotated for object detection tasks. The dataset's specific content, such as the number of images or annotation types, requires verification after download. Its title suggests a focus on detecting follicles, which may be relevant to medical or biological imaging analysis.
A dataset likely containing images for training or evaluating a Faster R-CNN object detection model. The title suggests the primary subject is fish, but the specific number of images, annotation details, and source are unknown. It is hosted on Kaggle, a platform for data science and machine learning projects.
A YOLO11s segmentation model, likely containing weights and configuration files for performing instance segmentation on images. The dataset is hosted on Kaggle and is categorized under Computer Vision. Specific details on the model's training data, performance, and architecture are not provided in the available metadata.
A dataset likely intended for training or evaluating the YOLOv8 object detection model architecture. It was published on the Kaggle platform, but the specific creator, size, and content details are not provided. The dataset's exact purpose and composition require verification after download.
A dataset likely containing annotated images for training object detection models, specifically for components on printed circuit boards (PCBs). It is hosted on Kaggle, but the author, organization, and specific details like the number of images are unknown. The title suggests the dataset is configured for use with the YOLOv11s architecture, incorporating enhancements like ECA attention, SIoU loss, and Focal loss.
A pre-trained Convolutional Neural Network (CNN) model, version 24.5, published on Kaggle. The model's specific architecture and training data are not detailed in the available metadata. Its intended application is likely for computer vision tasks, as suggested by the platform tags.
A dataset published on Kaggle, likely containing image embeddings generated by a Convolutional Neural Network (CNN). The specific data volume, creation date, and author are not provided in the available metadata. The title suggests a focus on computer vision feature extraction, possibly related to gait energy images (GEI).
Kaggle hosts a collection of pre-trained models named 'cnn-informer-all-model'. The dataset's specific contents, such as the number of models, their architecture details, or training data, are not described. Its purpose is likely related to applying or analyzing computer vision models within a news domain.
A dataset titled 'yolo-best1' hosted on Kaggle, likely related to object detection tasks given its name and platform tags. The dataset's specific content, size, and creation details are not provided in the available metadata. Its origin, scale, and temporal coverage are unknown.