Flood detector using effientnet as semantic segmentation model
-
Updated
Jul 2, 2023 - Python
Flood detector using effientnet as semantic segmentation model
This is a complete Project that revolves around churn modeling and it contains every aspect from data cleaning down to model deployment. The data of a bank was used in this implementation. An Artificial Neural Network was trained and used to predict the probability that a given customer would leave the bank(With 87% Test accuracy) and for deploy…
A PyTorch Implementation of Double-UNet
The goal is to segment instances of microvascular structures, including capillaries, arterioles, and venules, to in automating the segmentation of microvasculature structures as it will improve researchers' understanding of how the blood vessels are arranged in human tissues.
Notebook for autosegmentation of Head and Neck CT images using CNN
Semantic segmentation models for self-driving cars. Models developed for "Lyft Udacity Challenge for Self-driving Cars".
Case Study- Segmentation
A deep learning image segmentation library and API on top of PyTorch.
It's Spread Through Air Spaces(STAS) competition in lung by using image segmentation STAS contours
Repo to host the UPC AIDL spring 2022 post-graduate project
Segmentation models with pretrained backbones for RSI semantic segmentation (Keras and TensorFlow Keras).
Computer vision and machine learning project to count and detect the ripeness of strawberries in images
Segmenting customers based on their behavior and preferences
PyTorch implementation of DoubleUNet for medical image segmentation
Python script to remove background from a video, make use of google MediaPipe
This project is a Semantic Segmentation for Self Driving Cars made using Python. This project uses U-Net to segment the different regions of the image.
Breast Cell Nuclei Segmentation, project work done as a part of Internship at Machine Vision Lab, IIT Roorkee.
Projet de segmentation de clientèle - Classification non supervisée
Image segmentation
SAM is a deep learning model (transformer based). When we give an image as input to the Segment Anything Model, it first passes through an image encoder and produces a one-time embedding for the entire image. The downsampling happens using 2D convolutional layers. Then the model concatenates it with the image embedding to get the final vector.
Add a description, image, and links to the segmentation-models topic page so that developers can more easily learn about it.
To associate your repository with the segmentation-models topic, visit your repo's landing page and select "manage topics."