Loading...
Loading...
Image classification, object detection, segmentation, face recognition, OCR, image generation, video understanding
16,811 datasets
A dataset named 'prepared_model_vgg16_lstm_attention_30k' published on Kaggle. The title suggests it likely contains data related to a pre-trained deep learning model combining VGG16, LSTM, and attention mechanisms. Specific details about its contents, size, and origin are unavailable.
prepared_model_resnet50_lstm_attention_30k is a dataset published on Kaggle. Its title suggests it likely contains weights or parameters for a hybrid neural network architecture combining a ResNet50 convolutional backbone with an LSTM and attention mechanism. The dataset's specific content, size, and provenance are unknown.
ResNet101-cifar100-200epoch-trained is a pre-trained neural network model available on Kaggle. The model likely contains weights and architecture parameters for a ResNet101 model trained on the CIFAR-100 image dataset for 200 epochs. Its specific performance metrics and training details are unknown from the provided metadata.
Preprocessed_data_VGG16_attn likely contains image data formatted for use with the VGG16 convolutional neural network architecture, focusing on attention mechanisms. The dataset is hosted on Kaggle, but its specific contents, size, and creation details are unknown. Columns, sample data, and author information are unavailable.
Prepared_data_resnet50_attn is a dataset hosted on Kaggle. Its title suggests it likely contains processed features or attention maps derived from a ResNet50 model applied to images. The dataset's specific content, size, and origin are unknown.
Pages 120-159 from the first volume of the manga series Gantz. The dataset likely contains sequential image panels from a specific segment of the comic. It is hosted on Kaggle under the tag 'Pre Trained Model', suggesting it may be intended for model training.
An image dataset likely containing photographs of athletes for classification tasks. The dataset is hosted on Kaggle and includes platform tags for football, tennis, and baseball, suggesting a focus on these sports. Details on size, author, and update frequency are not provided in the metadata.
Mars surface imagery likely annotated for crater detection. The dataset is hosted on Kaggle, but its specific size, creation date, and author are unknown. Columns and sample data are unavailable, limiting pre-download assessment.
A Generative Adversarial Network encoder-decoder model trained on three unspecified datasets. The model is hosted on Kaggle and is categorized as a pre-trained model. The specific datasets used, model architecture, and performance metrics are not detailed in the provided metadata.
A pre-trained ResNet18 model weights file, likely trained for 60 epochs on the CIFAR-100 dataset. The dataset is hosted on Kaggle. The specific contents and performance metrics require verification after download.
A collection of images of steel samples captured using a scanning electron microscope. The dataset is hosted on Kaggle, but details on the number of images, sample origins, and collection date are not provided. The author, organization, and specific time range are unknown.
EfficientNet-B0 model weights trained on the ImageNet dataset. The dataset likely contains the parameter files necessary to initialize or fine-tune this specific convolutional neural network architecture. Published on Kaggle, its exact size, version, and licensing details are not provided in the metadata.
Kaggle hosts the SonicLens Multi-Modal Scene Understanding Challenge dataset. The dataset likely contains multi-modal data, such as images paired with audio or text, intended for a competition. Its specific content, scale, and creation details require verification after download.
BirdCLEF V27 E1 - EfficientNetB7 235sp is a pre-trained model for bird species classification, likely derived from the BirdCLEF competition on Kaggle. The model appears to be an EfficientNetB7 architecture trained to identify 235 distinct bird species. Its specific performance metrics, training data, and intended application require verification after download.
A dataset published on Kaggle, likely containing images annotated for object detection tasks using the YOLO model framework. The specific content, scale, and creation details are not provided in the available metadata. Users must download the dataset to verify its exact composition and suitability for their projects.
Bounding Boxes for ACSK LSTM model in VQA is a dataset hosted on Kaggle. The dataset's title suggests it contains bounding box annotations, likely for images used in Visual Question Answering tasks. Specific details on the number of images, annotation format, and creation date are not provided in the available metadata.
Input_OCR is a dataset for optical character recognition tasks, published on Kaggle. The dataset's specific content, size, and origin are not detailed in the provided metadata. Further details about the number of images, text samples, or annotation specifics require verification after download.
OCR Checkpoint QuyetDinh is a dataset published on Kaggle. The title suggests it relates to optical character recognition, likely containing model weights or training data for document text extraction. Metadata is minimal; the actual content and structure require verification after download.
A dataset for detecting Indian vehicle number plates using YOLO object detection models. The data was sourced from Kaggle, but the author, organization, and specific collection details are not provided. The last update date and dataset size are unknown.
A pre-trained Convolutional Neural Network (CNN) model designed for processing Gait Energy Images (GEI), likely for biometric identification. The model, version 24.3, is hosted on Kaggle and is associated with computer vision tasks. Specific details on the training data size, creator, and update date are not provided.