Custom Object Detection

This is a custom single object detection model used to detect a specific object in a given image.

Object Detection (Example 1)

Objection detection is one of the key use cases for CV. The job requires to detect the objects and coordinates in a given image. In this image, we. are showing the examples for single object detection. The same can be expanded to multiple objects.

Object Segmentation

Object Detection (Example 2)

Object Segmentation

Model Description:

Model Architecture for SingleObject Detection:

Input:Accepts an image of shape (224, 224, 3).
Convolutional Blocks:
1. 5 sequential blocks of Conv2D layers withReLUactivation and MaxPooling2D for feature extraction.
2. Filters progress as 32 → 64 → 128 → 256 → 512.
Global Pooling:
1. GlobalAveragePooling2D reduces spatialdimensions to a single vector.
Dense Layers:
1. Two fully connected layers with 512 and256 units for feature refinement.
Output Layer:
1. Dense(4, activation='sigmoid') outputs 4normalized values representing bounding box coordinates: [x_min,y_min,x_max,y_max].

Run In Your Model

Explore more models

Custom Object Detection

This is a custom single object detection model used to detect a specific object in a given image.

Object Detection

Llama-3.2-3B-Instruct

The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

text-LLMs

T5-small

T5 Small is a lightweight, 60M-parameter text-to-text transformer, ideal for resource-constrained NLP tasks, offering efficiency and versatility for quick prototyping and deployment.

text-LLMs

BERT

BERT (Bidirectional Encoder Representations from Transformers) is a transformer-based deep learning model developed by Google in 2018

text-LLMs

U-net

The U-Net is a convolutional neural network designed for image segmentation, featuring a U-shaped architecture. It consists of an encoder (contracting path) to capture context and a decoder (expanding path) for precise localization. Skip connections bridge the encoder and decoder, ensuring spatial information is preserved.

computer-vision

Resnet-32

ResNet-34 is a convolutional neural network (CNN) architecture that is part of the ResNet (Residual Network) family, introduced in the groundbreaking 2015 paper "Deep Residual Learning for Image Recognition" .

image-classification

Llama-3.2-1B-Instruct

The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

text-LLMs

AryaXAI provides the most accurate explainability and alignment stack to deliver accurate, true-to-model explainability, monitoring, risk management, and alignment techniques essential for highly mission-critical or regulated AI solutions.

Products

Explainable AI ML Monitoring ML Audit Policy Control Pricing

Resources

Articles Videos White papers Research paper Podcasts Events Tutorials Wikis

Company

About us Research Contact us Career