Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,520 datasets
Kaggle hosts this dataset of car logo images formatted for the YOLO2 object detection framework. The dataset likely contains images with bounding box annotations for training and evaluating logo detection models. The author, organization, and specific scale of the collection are unknown.
A pre-trained Convolutional Neural Network model published on Kaggle. The model, named 'dhbk_hb_model cnn gei 240 v24.4', is likely intended for image-based tasks. Its specific architecture, training data, and performance metrics require verification after download.
Kaggle hosts a dataset titled 'dhbk_hb_emb cnn gei 240 v24.4'. The title suggests it contains image embeddings generated by a Convolutional Neural Network (CNN), likely version 24.4 of a series. The dataset's author, organization, and specific content details are not provided in the metadata.
Wider-Face-Yolo-Degraded is a dataset from Kaggle likely containing images for face detection tasks. The title suggests it may involve degraded or altered versions of images from the WIDER FACE benchmark, potentially for testing model robustness. Its specific content, scale, and origin require verification after download.
Pose keypoints data likely contains numerical coordinates for human body joints. The dataset is hosted on Kaggle, but its specific size, origin, and creation date are unknown. Columns suggest it may include x, y coordinates and confidence scores for keypoints.
best-yolo26 is a dataset published on Kaggle. Its title suggests it is likely related to the YOLO (You Only Look Once) object detection algorithm. The dataset's specific content, size, and origin are unknown from the provided metadata.
Kaggle hosts a dataset titled 'YOLO merge CLF'. The dataset likely contains images annotated for object detection tasks, possibly related to merging or classification (CLF) processes. Its specific content, size, and origin are not detailed in the available metadata.
OCR Fine-tuning dataset is a collection likely intended for training and refining optical character recognition models. It was published on Kaggle, but its specific contents, size, and creation details are unknown. The dataset's purpose suggests it contains images and corresponding text annotations.
Kaggle dataset titled 'prepared_data_resnet50_attention'. The dataset likely contains image data processed for use with a ResNet50 model incorporating attention mechanisms. Metadata is minimal; actual content requires verification after download.
Kaggle dataset titled 'prepared_data_vgg16_attention'. The dataset likely contains image data preprocessed for use with the VGG16 convolutional neural network architecture and attention mechanisms. Metadata is minimal; actual content requires verification after download.
A dataset of model weights for a YOLO-based computer vision architecture, published on Kaggle. The specific architecture appears to combine YOLOv11n and P2deep components with a weight concatenation method. The exact number of weights, training data, and performance metrics are unknown from the provided metadata.
Mpox train for yolo suggests a collection of images intended for training YOLO object detection models. The dataset is hosted on Kaggle, but its specific scale, origin, and creation date are not provided. Columns and sample data are unknown, limiting detailed assessment prior to download.
dhbk_hb_model cnn gei 225 v24.2 is a pre-trained model published on Kaggle. The title suggests it is a Convolutional Neural Network (CNN) model, likely for image-based tasks. Specific details on architecture, training data, and performance are unavailable from the provided metadata.
dhbk_hb_emb cnn gei 225 v24.2 is a dataset of image embeddings likely generated by a Convolutional Neural Network (CNN). The dataset is hosted on Kaggle, but details on its size, source, and creation date are not provided in the metadata. The title suggests it contains feature vectors (embeddings) extracted from images using a CNN architecture.
mydata1_vgg is a dataset hosted on Kaggle. The title suggests a connection to the VGG architecture, a prominent model in computer vision. Its specific content, scale, and origin are not detailed in the provided metadata.
ImageNet is a large-scale image database for visual object recognition research. The class index likely maps numeric identifiers to descriptive labels for the dataset's categories. This dataset is hosted on Kaggle.
Image classification data for evaluating convolutional neural network performance. The dataset is hosted on Kaggle, but its size, creation date, and authorship are unspecified. Content details require verification after download.
flower-classification-cnn is a dataset hosted on Kaggle. The title suggests it contains images of flowers intended for training and evaluating convolutional neural network models. The dataset's specific size, source, and creation date are not provided in the available metadata.
A set of pre-trained neural network weights for the EfficientNetB4 architecture. The file likely contains the model parameters trained on a large image dataset, excluding the final classification layers. It is hosted on Kaggle.
A dataset likely containing images annotated for weapon detection, intended for training the YOLOv12 object detection model. It is hosted on Kaggle, but no further metadata is available. The dataset's specific content, size, and origin require verification after download.