EfficientDet 512

## Overview

EfficientDet 512 is a dataset for object detection tasks - it contains Plants annotations for 435 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).

EfficientDet 1024

## Overview

EfficientDet 1024 is a dataset for object detection tasks - it contains Object Detection annotations for 560 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).

EfficientDet Train

## Overview

EfficientDet Train is a dataset for object detection tasks - it contains Ripe Tomato annotations for 2,381 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 [Public Domain license](https://creativecommons.org/licenses/Public Domain).

EfficientDet (PyTorch) This is a work in progress PyTorch implementation of EfficientDet.

It is based on the

official Tensorflow implementation by Mingxing Tan and the Google Brain team paper by Mingxing Tan, Ruoming Pang, Quoc V. Le EfficientDet: Scalable and Efficient Object Detection I am aware there are other PyTorch implementations. Their approach didn't fit well with my aim to replicate the Tensorflow models closely enough to allow weight ports while still maintaining a PyTorch feel and a high degree of flexibility for future additions. So, this is built from scratch and leverages my previous EfficientNet work.

Updates / Tasks 2020-4-15 Taking a pause on training, some high priority things came up. There are signs of life on the training branch, was working the basic augs before priority switch, loss fn appeared to be doing something sane with distributed training working, no proper eval yet, init not correct yet. I will get to it, with SOTA training config and good performance as the end goal (as with my EfficientNet work).

2020-04-11 Cleanup post-processing. Less code and a five-fold throughput increase on the smaller models. D0 running > 130 img/s on a single 2080Ti, D1 > 130 img/s on dual 2080Ti up to D7 @ 8.5 img/s.

2020-04-10 Replace generate_detections with PyTorch impl using torchvision batched_nms. Significant performance increase with minor (+/-.001 mAP) score differences. Quite a bit faster than original TF impl on a GPU now.

2020-04-09 Initial code with working validation posted. Yes, it's a little slow, but I think faster than the official impl on a GPU if you leave AMP enabled. Post processing needs some love.

Core Tasks Feature extraction from my EfficientNet implementations (https://github.com/rwightman/gen-efficientnet-pytorch or https://github.com/rwightman/pytorch-image-models) Low level blocks / helpers (SeparableConv, create_pool2d (same padding), etc) PyTorch implementation of BiFPN, BoxNet, ClassNet modules and related submodules Port Tensorflow checkpoints to PyTorch -- initial D1 checkpoint converted, state_dict loaded, on to validation.... Basic MS COCO validation script Temporary (hacky) COCO dataset and transform Port reference TF anchor and object detection code Verify model output sanity Integrate MSCOCO eval metric calcs Some cleanup, testing Submit to test-dev server, all good Add torch hub support and pretrained URL based weight download Change module dependencies from 'timm' to minimal 'geffnet' for backbone, bring some of the layers here leaving as timm for now, as the training code will use many timm functions that I leverage to reproduce SOTA EfficientNet training in PyTorch Remove redundant bias layers that exist in the official impl and weights Add visualization support Performance improvements, numpy TF detection code -> optimized PyTorch Verify/fix Torchscript and ONNX export compatibility Possible Future Tasks Training (object detection) reimplementation w/ Rand/AutoAugment, etc Training (semantic segmentation) experiments Integration with Detectron2 / MMDetection codebases Addition and cleanup of EfficientNet based U-Net and DeepLab segmentation models that I've used in past projects Addition and cleanup of OpenImages dataset/training support from a past project Exploration of instance segmentation possibilities... If you are an organization is interested in sponsoring and any of this work, or prioritization of the possible future directions interests you, feel free to contact me (issue, LinkedIn, Twitter, hello at rwightman dot com). I will setup a github sponser if there is any interest.

Models Variant Download mAP (val2017) mAP (test-dev2017) mAP (Tensorflow official test-dev2017) D0 tf_efficientdet_d0.pth 32.8 TBD 33.8 D1 tf_efficientdet_d1.pth 38.5 TBD 39.6 D2 tf_efficientdet_d2.pth 42.0 42.5 43 D3 tf_efficientdet_d3.pth 45.3 TBD 45.8 D4 tf_efficientdet_d4.pth 48.3 TBD 49.4 D5 tf_efficientdet_d5.pth 49.6 TBD 50.7 D6 tf_efficientdet_d6.pth 50.6 TBD 51.7 D7 tf_efficientdet_d7.pth 50.9 51.2 52.2 Usage Environment Setup Tested in a Python 3.7 or 3.8 conda environment in Linux with:

PyTorch 1.4 PyTorch Image Models (timm) 0.1.20, pip install timm or local install from (https://github.com/rwightman/pytorch-image-models) Apex AMP master (as of 2020-04) NOTE - There is a conflict/bug with Numpy 1.18+ and pycocotools, force install numpy <= 1.17.5 or the coco eval will fail, the validation script will still save the output JSON and that can be run through eval again later.

Dataset Setup MSCOCO 2017 validation data:

wget http://images.cocodataset.org/zips/val2017.zip wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip unzip val2017.zip unzip annotations_trainval2017.zip MSCOCO 2017 test-dev data:

wget http://images.cocodataset.org/zips/test2017.zip unzip -q test2017.zip wget http://images.cocodat...

EfficientDet module [2023-03-30]. Fork of the main branch

GitHub repo here.

Learn how to train and infer with EfficientDet: - Benetech EfficientDet Train - Benetech EfficientDet Inference

EfficientDet Valid

## Overview

EfficientDet Valid is a dataset for object detection tasks - it contains Ripe Tomato annotations for 241 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 [Public Domain license](https://creativecommons.org/licenses/Public Domain).

This Dataset contains following packages for the offline installations of Object Detection models using EfficientDet

• effdet 0.2.3 Latest (7th Dec 2020)
• omegaconf-2.0.6
• timm-0.3.4
• ensemble_boxes-1.0.4
• pycocotools-2.0.2

Additionally it has the VinBigData Chest Abnormalities competition annotations which have been combined using Weighted Boxes Fusion.

References:

Thanks to @rwightman for the awesome EfficientDet implementation. Do check it out https://github.com/rwightman/efficientdet-pytorch

By accessing this dataset, you agree to abide by the license terms of the VinBigData Chest Abnormalities competition and the respective licenses of all the packages in this dataset.

Efficientdet Name Changes

## Overview

Efficientdet Name Changes is a dataset for object detection tasks - it contains Efficientdet Name Change annotations for 1,025 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).

🚗 Enhanced BDD100K Clean Dataset

📄 Overview

This dataset is a refined and enhanced version of the BDD100K dataset, focused on improving the quality and consistency of data for object detection tasks — especially in traffic-related scenes.

It has been carefully cleaned, filtered, and augmented to ensure better model generalization, with an emphasis on improving the representation of smaller traffic objects and removing noisy or invalid samples.

🧹 Improvements Made

• 🔹 High-quality image additions: Added higher-resolution images to strengthen underrepresented classes.
• 🔹 Focused classes: Emphasis on:
  • train
  • bike
  • motor
  • rider
  • traffic sign
  • traffic light
  • tuktuk
  • banners
• 🔹 Cleaned data:
  • Dropped all bounding boxes smaller than 10% of the average object size per class.
  • Removed duplicate images.
  • Excluded samples with missing images or missing labels.
  • Standardized label formatting and annotation consistency.

📦 Dataset Structure

├── train/ │ ├── images/ │ └── labels/ ├── val/ │ ├── images/ │ └── labels/ └── test/ ├── images/ └── labels/

Each annotation file corresponds to an image and contains bounding boxes and class labels following standard object detection formats (e.g., YOLO, COCO, or Pascal VOC depending on your export setup).

🧠 Applications

• Object detection (YOLOv8, YOLO11, Faster R-CNN, EfficientDet, etc.)
• Traffic and road-scene understanding
• Model robustness and domain adaptation research

⚙️ Recommended Usage

1. Train/Test Split: Use your preferred split (default 80/10/10).
2. Preprocessing: Normalize image sizes and verify label compatibility.
3. Frameworks: Compatible with most deep learning frameworks (TensorFlow, PyTorch, etc.).

📊 Classes Included

notes : the data is already augmmented

augmentation applied : Rotation Hue Contrast Noise

📜 License

This dataset is released under the CC BY 4.0 License — you are free to use it with attribution.

✍️ Author Notes

This enhanced version of BDD100K aims to offer a cleaner, more balanced, and higher-quality dataset to improve performance for real-world traffic detection models.

For any issues or suggestions, feel free to open a discussion on Kaggle.

EfficientDet 640

## Overview

EfficientDet 640 is a dataset for object detection tasks - it contains Weeds annotations for 443 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).

Synthetic Data for Khmer Word Detection

This dataset contains 10,000 synthetic images and corresponding bounding box labels for training object detection models to detect Khmer words.

The dataset is generated using a custom tool designed to create diverse and realistic training data for computer vision tasks, especially where real annotated data is scarce.

✨ Highlights

• 100,000 images (.png) with random backgrounds and styles.
• Bounding boxes provided in YOLO (.txt) and Pascal VOC (.xml) formats.
• 50+ real background images + unlimited random background colors.
• 250+ different Khmer fonts.
• Randomized effects: brightness, contrast, blur, color jitter, and more.
• Wide variety of text sizes, positions, and layouts.

📂 Folder Structure

/
├── synthetic_images/   # Synthetic images (.png)
├── synthetic_labels/   # YOLO format labels (.txt)
├── synthetic_xml_labels/ # Pascal VOC format labels (.xml)

Each image has corresponding .txt and .xml files with the same filename.

📏 Annotation Formats

• YOLO Format (.txt):
  Each line represents a word, with format: class_id center_x center_y width height All values are normalized between 0 and 1.
  Example: 0 0.235 0.051 0.144 0.081

• Pascal VOC Format (.xml):
  Standard XML structure containing image metadata and bounding box coordinates (absolute pixel values).
  Example: ```xml

🖼️ Image Samples

Each image contains random Khmer words placed naturally over backgrounds, with different font styles, sizes, and visual effects.
The dataset was carefully generated to simulate real-world challenges like:

• Different lighting conditions
• Different text sizes
• Motion blur and color variations

🧠 Use Cases

• Train YOLOv5, YOLOv8, EfficientDet, and other object detection models.
• Fine-tune OCR (Optical Character Recognition) systems for Khmer language.
• Research on low-resource language computer vision tasks.
• Data augmentation for scene text detection.

⚙️ How It Was Generated

1. A random real-world background or random color is chosen.
2. Random Khmer words are selected from a large cleaned text file.
3. Words are rendered with random font, size, color, spacing, and position.
4. Image effects like motion blur and color jitter are randomly applied.
5. Bounding boxes are automatically generated for each word.

🧹 Data Cleaning

• Words were sourced from a cleaned Khmer corpus to avoid duplicates and garbage data.
• Fonts were tested to make sure they render Khmer characters properly.

📢 Important Notes

• This dataset is synthetic. While it simulates real-world conditions, it may not fully replace real-world labeled data for final model evaluation.
• All labels assume one class only (i.e., "word" = class_id 0).

❤️ Credits

• Khmer text data collected from open-source projects such as khmer-text-data.
• Khmer fonts collected from free and open repositories like Khmer Fonts Project.

📈 Future Updates

We plan to release:

• Datasets with rotated bounding boxes for detecting skewed text.
• More realistic mixing of real-world backgrounds and synthetic text.
• Advanced distortions (e.g., handwriting-like simulation).

Stay tuned!

📜 License

This project is licensed under MIT license.

Please credit the original authors when using this data and provide a link to this dataset.

✉️ Contact

If you have any questions or want to collaborate, feel free to reach out:

• 📧 Email: veasnaec@gmail.com
• 🌐 GitHub: Chanveasna ENG

Railsem19 EfficientDet Test

## Overview

Railsem19 EfficientDet Test is a dataset for object detection tasks - it contains Things annotations for 6,649 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 [Public Domain license](https://creativecommons.org/licenses/Public Domain).

Disaster Response Object Detection Dataset is a curated dataset containing images across 6 classes relevant to disaster and emergency response: person, fire, smoke, small vehicle, large vehicle, and two-wheeler. Each image is annotated with bounding boxes in YOLO format, making the dataset directly usable for object detection tasks. It can also be extended to image classification tasks, enabling dual use in disaster response AI research.

The dataset consists of real-world and open-source disaster-related images, compiled and preprocessed with balanced annotations. Each annotation file follows the standard YOLO format (class x_center y_center width height), ensuring compatibility with modern detection frameworks. This makes it suitable for training and benchmarking deep learning models such as YOLOv5, YOLOv8, YOLOv11, Faster R-CNN, and EfficientDet for detection, as well as ResNet, EfficientNet, and MobileNet for classification.

Potential applications include drone-based disaster monitoring, fire and smoke detection, automated search and rescue, traffic and evacuation management, and broader humanitarian response systems. Evaluation can be performed using standard metrics such as mAP, precision, recall, and F1-score.

If you use this dataset, please cite: Rupankar Majumdar, "Disaster Response Object Detection Dataset," Kaggle, 2025.

COVID 19 FMD EfficientDet

## Overview

COVID 19 FMD EfficientDet is a dataset for object detection tasks - it contains Mask IncorrectMask annotations for 1,961 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 quality and safety of tea food production is of paramount importance. In traditional processing techniques, there is a risk of small foreign objects being mixed into Pu-erh sun-dried green tea, which directly affects the quality and safety of the food. To rapidly detect and accurately identify these small foreign objects in Pu-erh sun-dried green tea, this study proposes an improved YOLOv8 network model for foreign object detection. The method employs an MPDIoU optimized loss function to enhance target detection performance, thereby increasing the model’s precision in targeting. It incorporates the EfficientDet high-efficiency target detection network architecture module, which utilizes compound scale-centered anchor boxes and an adaptive feature pyramid to achieve efficient detection of targets of various sizes. The BiFormer bidirectional attention mechanism is introduced, allowing the model to consider both forward and backward dependencies in sequence data, significantly enhancing the model’s understanding of the context of targets in images. The model is further integrated with sliced auxiliary super-inference technology and YOLOv8, which subdivides the image and conducts in-depth analysis of local features, significantly improving the model’s recognition accuracy and robustness for small targets and multi-scale objects. Experimental results demonstrate that, compared to the original YOLOv8 model, the improved model has seen increases of 4.50% in Precision, 5.30% in Recall, 3.63% in mAP, and 4.9% in F1 score. When compared with the YOLOv7, YOLOv5, Faster-RCNN, and SSD network models, its accuracy has improved by 3.92%, 7.26%, 14.03%, and 11.30%, respectively. This research provides new technological means for the intelligent transformation of automated color sorters, foreign object detection equipment, and intelligent sorting systems in the high-quality production of Yunnan Pu-erh sun-dried green tea. It also provides strong technical support for the automation and intelligent development of the tea industry.

Person Dataset 2

## Overview

Person Dataset 2 is a dataset for object detection tasks - it contains Person annotations for 2,496 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 [Public Domain license](https://creativecommons.org/licenses/Public Domain).

AgroPest-12 is a curated dataset containing images of 12 classes of crop insects and pests. Each image is annotated with bounding boxes in YOLO format, making the dataset directly usable for object detection tasks. It can also be applied to image classification, enabling dual use in agricultural AI research.

The dataset consists of high-quality pest images captured in natural agricultural environments, along with annotation files in .txt format (class x_center y_center width height). This makes it suitable for training and benchmarking deep learning models such as YOLOv5, YOLOv8, YOLOv11, Faster R-CNN, and EfficientDet for detection, as well as ResNet, EfficientNet, and MobileNet for classification.

Potential applications include drone-based pest monitoring, automated crop protection systems, early pest outbreak prediction, and broader smart farming use cases. Evaluation can be done using standard metrics such as mAP, precision, recall, F1-score, and accuracy for classification tasks.

If you use this dataset, please cite: Rupankar Majumdar, "AgroPest-12: A 12-Class Image Dataset of Crop Insects and Pests," Kaggle, 2025.

Lab7_EfficientDet

## Overview

Lab7_EfficientDet is a dataset for object detection tasks - it contains Keys annotations for 781 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).

🩻 Scoliosis Spine Detection Dataset (YOLOv5 Ready)

This dataset is a curated and preprocessed version of a Scoliosis Spine X-ray dataset, designed specifically for deep learning–based object detection and classification tasks using frameworks like YOLOv5, YOLOv8, and TensorFlow Object Detection API.

It contains annotated spinal X-ray images categorized into three classes, representing different spinal conditions.

🧩 Dataset Configuration

train: scoliosis2.v16i.tensorflow/images/train
val: scoliosis2.v16i.tensorflow/images/valid
test: scoliosis2.v16i.tensorflow/images/test

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

⚙️ Data Details

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

Classes Description:

1. Vertebra — Labeled vertebral regions used for bone localization.
2. Scoliosis Spine — X-rays showing curvature or deformity in the spinal structure.
3. Normal Spine — Healthy, straight spinal alignment without scoliosis signs.

🧠 Augmentations Applied

To enhance diversity and model robustness, the dataset was augmented using:

• Rotation
• Brightness and contrast adjustment
• Horizontal flip
• Random zoom and cropping
• Gaussian noise

🎯 Use Cases

This dataset is ideal for:

• Scoliosis detection and classification research
• Vertebra localization and spine anomaly detection
• Medical object detection experiments (YOLOv5, YOLOv8, EfficientDet)
• Transfer learning on medical X-ray datasets
• Explainable AI and model comparison studies

📊 Source

The dataset was preprocessed and labeled using Roboflow, then manually refined and balanced for research use. Originally derived from a spinal X-ray dataset and adapted for deep learning object detection.

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

🧾 License

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

Would you like me to make a short summary version (under 1000 characters) for the “Short Description” field on Kaggle too? It’s required for the dataset card.

This dataset is a balanced and augmented version of the original Scoliosis Detection Dataset designed for deep learning and computer vision tasks, particularly spinal curvature classification using YOLOv5.

It contains dermatoscopic-style spine X-ray images categorized into four classes based on the severity of scoliosis:

1-derece → Mild scoliosis

2-derece → Moderate scoliosis

3-derece → Severe scoliosis

saglikli → Healthy (no scoliosis)

⚙️ Data Details

Train set: ../train/images

Validation set: ../valid/images

Test set: ../test/images

Total Classes: 4

Balanced Samples: Each class contains approximately 1259 images and labels

Augmentations Applied:

Rotation

Brightness and contrast adjustment

Horizontal flip

Random zoom and cropping

Gaussian noise

These augmentations were used to improve model robustness and reduce class imbalance.

🎯 Use Cases

This dataset is ideal for:

Scoliosis detection and classification research

Object detection experiments (YOLOv5, YOLOv8, EfficientDet)

Transfer learning on medical image datasets

Model comparison and explainability studies

📊 Source

Originally sourced and preprocessed using Roboflow, then restructured and balanced manually for research and experimentation.

Roboflow Project Link: 🔗 View on Roboflow

🧠 License

CC BY 4.0 — Free to use and share with attribution.