VajraV1

<div align="center"> <img src="./vajra/assets/Vayuvahana_logo.png" alt="Vayuvahana Technologies Private Limited Logo" width="450"> </div>

Vayuvahana Technologies Private Limited VajraV1 is a state-of-the-art (SOTA) real time object detection model inspired by the YOLO model architectures. VajraV1 is a family of fast, lightweight models that can be used for a variety of tasks like object detection and tracking, instance segmentation, oriented object detection, pose detection, and image classification.

<div align="center">Enterprise License</div>

To request for an Enterprise License please get in touch via Email

<div align="center">Performance on COCO Dataset</div>

<p align="center"> <img width="100%" src="./vajra/assets/vajra_v1_detection_performance_coco.png" alt="VajraV1 Detection Performance on COCO Dataset"> </p>

<div align="center">Segmentation Performance on COCO Dataset</div>

<p align="center"> <img width="100%" src="./vajra/assets/vajra_v1_segmentation_performance_coco.png" alt="VajraV1 Segmentation Performance on COCO Dataset"> </p>

<div align="center">Pose Estimation Performance on COCO Dataset</div>

<p align="center"> <img width="100%" src="./vajra/assets/vajra_v1_pose_performance.png" alt="VajraV1 Pose Estimation Performance on COCO Dataset"> </p>

<div align="center">Documentation</div>

<details open> <summary>Install</summary>

Git clone the VayuAI SDK including all requirements in a Python>=3.8 environment.

git clone https://github.com/NamanMakkar/VayuAI.git
cd VayuAI
pip install .

</details> <details open> <summary>Usage</summary>

CLI

Vajra can be used in the Command Line Interface with a vajra or vayuvahana or vayuai command:

vajra predict model=vajra-v1-nano-det img_size=640 source="path/to/source.jpg"

Python

Vajra can also be used directly in a Python environment, and accepts the same arguments as in the CLI example above:

from vajra import Vajra
model = Vajra("vajra-v1-nano-det")

train_results = model.train(
    data="coco8.yaml",
    epochs=100,
    img_size=640,
    device="cpu",
    weight_decay=0.,
)

metrics = model.val()
results = model("path/to/img.jpg")
results[0].show()

path = model.export(format="onnx")

Pretrained COCO weights can also be used for model inference

from vajra import Vajra
model = Vajra("vajra-v1-xlarge-det.pt")
results = model("path/to/img.jpg")
results[0].show()

path = model.export(format="engine", device=0, half=True)

</details>

Tasks Supported

✅ detect
✅ pose
✅ obb
✅ segment
✅ small_obj_detect
✅ classify
✅ multilabel_classify

Modes Supported

✅ Training
✅ Validation
✅ Prediction
✅ Multi-object Tracking
✅ Model Export -> (TensorRT, ONNX, OpenVINO, Torchscript, CoreML, TensorFlow.js, NCNN, Keras, PaddlePaddle)
✅ Benchmarking

Model Architectures

✅ VajraV1-det
✅ VajraV1-cls
✅ VajraV1-pose
✅ VajraV1-seg
✅ VajraV1-obb
✅ SAM
✅ SAM2
✅ FastSAM
✅ MobileSAM
✅ EfficientNetV1
✅ EfficientNetV2
✅ VajraEffNetV1
✅ VajraEffNetV2
✅ ConvNeXtV1
✅ ConvNeXtV2
✅ ResNet
✅ ResNeSt
❌ ResNeXt (Coming Soon!)
❌ ResNetV2 (Coming Soon!)
✅ EdgeNeXt
✅ ME-NeSt
✅ VajraME-NeSt
✅ MixConvNeXt
❌ ViT (Coming Soon!)
❌ Swin (Coming Soon!)
❌ SwinV2 (Coming Soon!)

Model Architecture Details

To be published

Acknowledgements

• https://github.com/ultralytics/ultralytics
• https://github.com/ultralytics/yolov5
• https://github.com/ouyanghaodong/DEYOv1.5
• https://github.com/WongKinYiu/yolov9
• https://github.com/meituan/YOLOv6
• https://github.com/huggingface/pytorch-image-models
• https://github.com/pytorch/vision

<div align="center">License</div>

Vayuvahana Technologies Private Limited offers two licensing options:

• AGPL-3.0 License: This is an OSI-approved open-source license for researchers for the purpose of promoting collaboration. See the LICENSE file for details.

• Enterprise License: This license is designed for commercial use and enables integration of VayuAI software and AI models into commercial goods and services, bypassing the open-source requirements of AGPL-3.0. If your product requires embedding the software for commercial purposes or require access to more capable enterprise AI models in the future, reach out via Email.