Most Viewed Models of the Month
Models Keywords (407)
Computer Vision
6 models found.
Grid View
List View
-
Even as engineers, 'cracking' on the top of the structure frame was also a big problem. That is because 'cracks' may have a... moreEven as engineers, 'cracking' on the top of the structure frame was also a big problem. That is because 'cracks' may have a major effect on structural safety, serviceability, and reliability.
The project aim is to detect cracks in concrete building structures using deep learning.
Construction companies can use the project to detect cracks and help determine the health of a concrete structure.
The datasets contain images of various concrete surfaces with and without cracks. Each class has 19,950 images, i.e. total of 39,900 images with 227 x 227 pixels with RGB channels.
The "Accuracy_score" metric has been used to measure that model's performance. less
-
In this project, classification model of emergency vehicle vs non emergency vehicle has been build.After implementing custom... moreIn this project, classification model of emergency vehicle vs non emergency vehicle has been build.After implementing custom model architecture and hyperparameter tuning, obtained accuracy is 84.5%.
-
September 9, 2021 - MODEL_posted_by
Tarun Reddy,
786 views, 3 likes
PROBLEM STATEMENT:Our main goal is to determine a person's gender by training a model on their eyes. This model may make... morePROBLEM STATEMENT:Our main goal is to determine a person's gender by training a model on their eyes. This model may make gender prediction very easier. Even if we don't have complete access to a person's face, we might predict their gender.DATASET DESCRIPTON:The data was collected to train a model to distinguish between images containing Female eyes and images of Male eyes.The folder femaleeyes contains 5202 images and the folder maleeyes contains 6323 images for training and testing the model.MODEL ACCURACY: 93%DATASET SOURCE: https://ruskino.ru/ less
-
August 31, 2021 - MODEL_posted_by
Tarun Reddy,
766 views, 5 likes
Problem Statement:Forest fire detection should be quick and precise, as they can create massive damage and destruction.As... moreProblem Statement:Forest fire detection should be quick and precise, as they can create massive damage and destruction.As the technology is developing, we can use Machine Learning techniques to detect the forest fires as early as possible and can control it.
Dataset Description:
The data was gathered in order to train a model that can identify between pictures that contain fire (images of fire) and regular images (images which aren't fire), hence the task is simply a binary classification problem. The data is divided into two folders: one is for outdoor fire photographs, which comprises 755 images, some of which have smoke, and another for non-fire images, which has 244 nature images.Model Accuracy: 91% less
-
Problem StatementThis model was built in order to explore an application of MediaPipe known as MediaPipe Pose... moreProblem StatementThis model was built in order to explore an application of MediaPipe known as MediaPipe Pose Detection. Human pose estimation from video plays a critical role in various applications such as quantifying physical exercises, sign language recognition, and full-body gesture control. For example, it can form the basis for yoga, dance, and fitness applications. It can also enable the overlay of digital content and information on top of the physical world in augmented reality.How does this model work?The solution utilizes a two-step detector-tracker ML pipeline, proven to be effective in our MediaPipe Hands and MediaPipe Face Mesh solutions. Using a detector, the pipeline first locates the person/pose region-of-interest (ROI) within the frame. The tracker subsequently predicts the pose landmarks within the ROI using the ROI-cropped frame as input.Output DescriptionThis model can detect 3 yoga poses as of now. The Mountain Pose, Tree Pose and The Downward-Facing Dog Pose. How to use the model?1) Choose the Yoga Pose that you want to predict.2) Click predict.3) Voila! You can see your output now!. less
-
May 7, 2021 - MODEL_posted_by
Raji Reddy A,
925 views, 2 likes
YOLO is a state-of-the-art object detection system. It is used to detect objects in an image and also draw a bounding box... moreYOLO is a state-of-the-art object detection system. It is used to detect objects in an image and also draw a bounding box around the object. In other object detection systems like Fast RCNN & Faster RCNN, separate networks are used to detect the objects and predict the bounding boxes whereas in YOLO, a single convolutional network predicts the bounding boxes and the class probabilities for these boxes, hence the name You Only Look Once.The original yolo research paper is available here https://pjreddie.com/media/files/papers/yolo.pdf Here we see how to train an object detection model on a custom dataset and use the trained model to predict objects in a real time video stream. less
Loading ...