Yolov5 Classification Test

## Overview

 Yolov5 Classification Test is a dataset for classification tasks - it contains Tomatos annotations for 2,908 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

YOLOv5 Classification Flowers

## Overview

YOLOv5 Classification Flowers is a dataset for classification tasks - it contains Flowers annotations for 2,743 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

A high-quality YOLOv5-ready game dataset containing images and frames from diverse gaming environments for object detection, tracking, and classification tasks used in computer vision and AI model training.

 Brief of Dataset Random images collected from Google and coco website Data have 5 class Car /plane/train/Person/Traffic-light

71 images 346 annotations

Context

The dataset is planned to use in the project for predicting Hong Kong plants images. https://github.com/r48n34/leafers

Child Adult Classification

## Overview

Child Adult Classification is a dataset for object detection tasks - it contains Adult Child annotations for 9,498 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

YoloV5 8_Class

## Overview

YoloV5 8_Class is a dataset for object detection tasks - it contains Classification annotations for 8,008 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Class:

• Acne
• Oiliness
• Wrinkles
• Spots

The dataset includes 302 images. Face are annotated in YOLO v5 PyTorch format.

The following pre-processing was applied to each image: * Auto-orientation of pixel data (with EXIF-orientation stripping) * Resize to 640x640 (Stretch)

This dataset contains labeled images for garbage classification using object detection, formatted for use with YOLOv5 and similar models. It includes six classes of waste:

• BIODEGRADABLE
• CARDBOARD
• GLASS
• METAL
• PAPER
• PLASTIC

The dataset is organized into train, valid, and test directories, each containing images/ and labels/ folders. An accompanying data.yaml file is included to simplify training with YOLO-based models.

This dataset is useful for training real-time waste-sorting AI models or smart recycling bin systems.

🩻 Scoliosis YOLOv5 — Annotated Spine X-ray Dataset

This dataset is a curated and preprocessed collection of spinal X-ray images for deep learning–based scoliosis and vertebra detection using YOLOv5, YOLOv8, or other object detection frameworks.

It contains high-quality annotated X-rays featuring multiple bounding boxes per image — each representing different spinal regions and conditions.

🧩 Dataset Configuration

train: scoliosis yolov5/train/images
val: scoliosis yolov5/valid/images
test: scoliosis yolov5/test/images

nc: 3
names: ['Vertebra', 'scoliosis spine', 'normal spine']

⚙️ Data Details

• Train Set: /train/images
• Validation Set: /valid/images
• Test Set: /test/images
• Total Classes: 3
• Annotations: YOLOv5 format (.txt with class, x_center, y_center, width, height)
• Image Format: .jpg / .png

Classes Description:

1. Vertebra — Individual vertebral structures localized across the spine.
2. Scoliosis Spine — Spinal X-rays with visible curvature or deformation.
3. Normal Spine — Straight, healthy spinal alignment with no abnormality.

🧠 Augmentations Applied

To improve model generalization and balance the dataset, the following augmentations were used:

• Random rotation
• Brightness and contrast adjustment
• Horizontal flipping
• Random zoom and cropping
• Gaussian noise injection

🎯 Use Cases

This dataset is ideal for:

• Scoliosis detection and classification
• Vertebra localization and segmentation
• Object detection model benchmarking (YOLOv5/YOLOv8)
• Transfer learning on medical image datasets
• Explainable AI research in healthcare

📊 Source

The dataset was processed and annotated using Roboflow, then refined and organized into YOLOv5 format for seamless training. Each image includes verified bounding boxes for vertebral and scoliosis regions.

Roboflow Project Link: 🔗 View on Roboflow (add your Roboflow link here)

🧾 License

CC BY 4.0 — Free to use, modify, and redistribute with proper attribution.

This dataset has 9 class names. These are ambulance, bicycle, bus, car, motorbike, pickup, truck, van and license plate. You can use this dataset for vehicle detection, classification and license plate recognition.

Oxford-IIIT Pet Dataset with ground truth labels for breeds (from https://public.roboflow.com/object-detection/oxford-pets).

Classification Of Potato

## Overview

Classification Of Potato is a dataset for object detection tasks - it contains Good Potato Or Pad Potato annotations for 2,382 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The model added modules such as SEBlock and Dropout, added data enhancement, and adjusted hyperparameters and thresholds.

Among them, SEBlock is defined in the common.py file and added to the convolutional layers of the model, such as C3, Conv, Bottleneck, etc. The Dropout module is also added to each key layer of the model.

The impact of the SEBlock module is as follows: 1. Feature Re-calibration: SEBlock enhances network efficiency by re-calibrating the responses of feature channels in convolutional layers. It learns the importance of different feature channels and adjusts their responses accordingly, enabling the model to focus more on useful features.

1. Performance Enhancement: Numerous studies have shown that SEBlocks can improve model performance in various tasks, including image classification and object detection. By enhancing the model's perception of features, it can increase recognition accuracy.

2. Strong Adaptability: The structure of the SEBlock is relatively simple, and it does not significantly increase the computational load, yet it effectively enhances the model's ability to learn complex features. This allows SEBlocks to be widely applied across various deep learning models without imposing a heavy computational burden.

3. Improving Learning from Small Samples: For tasks like object detection, especially with limited sample sizes, SEBlocks can help the model extract effective information from each sample more efficiently, thus improving the effectiveness of learning from small samples.

https://i.imgur.com/s4PgS4X.gif" alt="CreateML Output">

Info

The dataset contains 7 classes of underwater creatures with provided bboxes locations for every animal. The dataset is already split into the train, validation, and test sets.

Data

It includes 638 images. - Creatures are annotated in YOLO v5 PyTorch format

Pre-Processing

The following pre-processing was applied to each image: - Auto-orientation of pixel data (with EXIF-orientation stripping) - Resize to 1024x1024 (Fit within)

Class Breakdown

The following classes are labeled: ['fish', 'jellyfish', 'penguin', 'puffin', 'shark', 'starfish', 'stingray']. Most images contain multiple bounding boxes.

https://i.imgur.com/lFzeXsT.png" alt="Class Balance">

Group 13 Helmet Detection And Classification

## Overview

Group 13 Helmet Detection And Classification is a dataset for object detection tasks - it contains Rider annotations for 933 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The object detection category included the default YOLOv5m architecture and its five variations (v0, v1, v2, v3 and v4; see Methods), while the second category included six state-of-the-art image classification architectures. We studied the effect of adding random background images as negative control. The best models were estimated by retraining until epoch Ep when over-fitting was observed. Performance metrics included precision (P), Recall (R), F1 score (F1), mAP@0.5 (M1) and mAP@.5,.95, for both classes combined (a), as well as individually for the low (l) and high (h) classes.

This dataset was created using vehicle pictures gathered in Chattogram, Bangladesh. It includes 28 unique categories of vehicles regularly observed in the city. Data was collected in a variety of contexts to replicate the city's actual traffic circumstances. To improve generalization, vehicles were photographed in a variety of lighting conditions, angles, and backgrounds. It can be used to train, validate, and test machine learning algorithms. This material is very valuable for computer vision research purposes. Vehicle detection, classification, recognition, and traffic monitoring are all potential domains. It may also fund future projects centered on intelligent transportation systems. The dataset attempts to develop automated traffic management technologies. The dataset's comprehensiveness is ensured by its inclusion of several categories.

Further investigation is needed to improve the identification and classification of fish in underwater images using artificial intelligence, specifically deep learning. Questions that need to be explored include the importance of using diverse backgrounds, the effect of (not) labeling small fish on precision, the number of images needed for successful classification, and whether they should be randomly selected. To address these questions, a new labeled dataset was created with over 18,400 recorded Mediterranean fish from 20 species from over 1,600 underwater images with different backgrounds. Two state-of-the-art object detectors/classifiers, YOLOv5m and Faster RCNN, were compared for the detection of the ‘fish’ category in different datasets. YOLOv5m performed better and was thus selected for classifying an increasing number of species in six combinations of labeled datasets varying in background types, balanced or unbalanced number of fishes per background, number of labeled fish, and quality of labeling. Results showed that i) it is cost-efficient to work with a reduced labeled set (a few hundred labeled objects per category) if images are carefully selected, ii) the usefulness of the trained model for classifying unseen datasets improves with the use of different backgrounds in the training dataset, and iii) avoiding training with low-quality labels (e.g., small relative size or incomplete silhouettes) yields better classification metrics. These results and dataset will help select and label images in the most effective way to improve the use of deep learning in studying underwater organisms.

NEW CLASSIFICATION YOLOV5_nano

## Overview

NEW CLASSIFICATION YOLOV5_nano is a dataset for object detection tasks - it contains PLASTIC PAPER GLASS WASTE N JjWl annotations for 1,913 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).