comet-ai / comet.box Goto Github PK
View Code? Open in Web Editor NEWCollection of Object Detection and Segmentation Pipelines🛸🚀
License: Apache License 2.0
Collection of Object Detection and Segmentation Pipelines🛸🚀
License: Apache License 2.0
I will like to add a feature will which keep the contributor section In read me update the list of contributors automatically !!
Detect Tiger from the wild Environment
Models can be used:
Dataset: https://storage.googleapis.com/openimages/web/index.html [Download From Hereafter filtering]
Refer to this YT channel for YoloV5 custom Training
https://www.youtube.com/channel/UCrydcKaojc44XnuXrfhlV8Q
Python programs to capture a user's face and generate dataset. Then detect and recognize the user's face by using opencv.
Hello!
Under the NLP Models, I noticed that GPT1 and GPT2 are unticked. Do you have a specific use in mind for these models? I would like to work with them as part of GSSOC 2021. Thanks!
Detect human pose using opencv
ALGO: The YOLOv3 (You Only Look Once) is a state-of-the-art, real-time object detection algorithm. The published model recognizes 80 different objects in images and videos.
In this project, I will create a Face Detection Script using YOLOv3 Algorithm.
Dependencies
Tensorflow
opencv-python
opencv-contrib-python
Numpy
Keras
Matplotlib
Pillow
I'd Like to work on this issue as part of GSSOC-21.
Hello!! I have an NLP-based Project Idea.
Problem statement: Emotion Recogniser using NLP
I've been working on this already would be happy to add this project here.
Here is a glimpse
I'd Like to work on this issue as part of GSSoC'21.
Thanks.
this bot basically welcomes and greets someone who open their first issue or make their first pr in a repo.
you can download the bot from here
https://github.com/apps/welcome
and another extra file needs to be added to set the custom messages
please assign it to me under gssoc'21
remove grammatical mistakes
**Is your feature request related to a problem?
Add pull request template for contributers reference and message to follow contributors guidelines.
Tasks Include :
Create a Vgg-19 Model for classifying imagenet images
Create a simple web app with Flask and Html/CSS/Js
Upload an image to predict the class of the image.
Dataset-Here
The dataset will be loaded in the code itself, We do not require any manual downloading as it's huge around 15GB.
It has over 200 classes with 100k+ images.
Once The application is done all you need to do is access the web app ( No training as I will be saving the model)
I'd like to work on this as part of the GSSOC-21.
Thanks
I would like to add a project for punctuation corrector using NLP. Here, the punctuations given will be corrected from a set of data take as input.
Detect the different brands like Starbucks, McDonald's, and others.The model will be trained on a custom Annotated Dataset Scraped from google. Use collab notebook for the task.
I would like to add a project for mask detection. To be more precise, I would use datasets which contains multiple images and would detect whether the person is wearing mask or not. Then, determine the total number of person wearing and not wearing mask.
I am a participant of GSSOC'21
Hi, I'm a Gssoc'21 Participant I would love to contribute to your project
I want to contribute the face_detection part to your repository in which I would like to add the face, eye, and nose detection part with the help of open-cv and python.
@Rishikeshrajrxl Kindly Please assign this part to me.
Task#1
This project lacks issue and pr templates so would like to add those please assign it to me under gssoc'21 @DARK-art108
hey I would like to add the following on contributing.md
Description
Given a sequence of words, next k words will be predicted using
After which I'll compare the performance of these models.
I am a GSSOC-21 participant, kindly assign this issue to me.
add all contributors bot to display the contributors of this project on README
I would like to add a project for Ludo game in python.
I would like to add a python script.
Here, it will autodetect whether to click a click in day or night mode.
Input will be a grid of pixels and output will be day or night
I would like to add a project for background removal from a image.
Example: a image of person with garden in the background, after implementation of this feature we will have only the person parts of the garden would be removed.
Statement.
Here a dataset has collected from kaggle. Here is the link - https://www.kaggle.com/tawsifurrahman/covid19-radiography-database . Here we get different images of X-Ray. We can say from X-Ray is it Covid-19 or Viral Pneumonia or Normal fever.
Solution
Here we build a model for classification using Pytorch. Afterwards we will calculate validation accuracy for test dataset and also plot graph of it.
Additional
We can compare the training time between a normal deep learning model and transfer learning model also.
I would like to add a project for brain tumor analysis. Here, I would use datasets containing images of the brain, from which I would detect whether a person is having brain tumor or not. And, then also classify the type of tumor.
Hey.Please assign this issue to me.I want to make a detailed documentation on this task using deep learning algorithms
Would like to work on this issue using either in google colab or kaggle notebooks for better use for everyone.
Please assign me this project as part of GSSOC'21
There is no code of conduct file so would like to add one please assign it to me @DARK-art108
please assign it to me under gssoc'21
Is your feature request related to a problem? Please describe.
Add github action to auto labels issues with gssoc21 label when contributor asks to work on the issue under gssoc label.
I would like to add a project for template matching. One template will be taken and will be checked wheather it is in the input image.
Task#1
Hi admin, Sayan here. I'm GSSoC'21 participant. I want to contribute in your project as it is more insightful.
I want to add a new feature "Iris Detection".
I've implemented it already.
Please assign me to this issue so I can contribute.
Task#1
Hi, I am a GSSOC participant, can you assign me this feature to implement the code.
I would like to add a project for spam detection.
Here, I would take sample data from datasets and then detect whether it is a spam data or not.
I would like to add a project for blurring face. Here, I would detect face and then blur it.
Hey, so i am a little new to the project and was not exactly sure if the addition that i wished to make went hand in hand with the overall goal of this project but a few days earlier i was working on a project which required me to detect human emotions. The model was built using the Kaggle notebooks and the data set that i used was FER2013 competition data. So it would be great if you could let me know if i can work on making that a part of this project.
If you would like any more information from my end, please let me know. I am a GSSoC participant.
Create a Car Brand Classification Project
Tasks:
It will be added as part of Folder
I'd Like to work on this issue as part of GSSOC-21.
I'd Like to add Generating Face Project.
I would be using This Data set to generate faces of celebrities using DCGAN.( will be following the total pipeline)
Describe the solution you'd like
In this project, I'll define and train a DCGAN on a dataset of faces. the goal is to get a generator network to generate new images of faces that look as realistic as possible!
1.I'll use, CelebFaces Attributes Dataset (CelebA) to train the adversarial networks.
2.The project will be broken down into a series of tasks from loading in data to defining and training adversarial networks.
3.At the end of the notebook, We'll be able to visualize the results of the trained Generator to see how it performs.
4.I'll add Model pkl File and Images as well.
I'd like to work on this issue as part of GSSOC-21.
Thanks
Hello, I noticed the ELMo checkbox was unticked in the README. I've been working with ELMo and would like to contribute (as part of gssoc21).
What is required for a successful submission, an example notebook where it is used?
Is your feature request related to a problem? Please describe.
I've noticed several notebooks on github have an "Open in Colab" badge that let's viewers quickly setup and experiment with the code. I think this would be a super useful feature.
Describe the solution you'd like
{{badge}}
to every existing notebook. This means that all new PRs will need to have a {{badge}}
markdown cell.Additional context
Part of GSSoC'21
Detect Helmet from real-time traffic videos.
Task#1
There are a lot of grammatical errors in the Readme file that needs correction.
I would like to add a project in Java.
It will be a game where player will rescue a princess from a grid, avoiding the obstacles.
Describe the bug
Model name is wrong under Classification Model's
To Reproduce
Steps to reproduce the behavior:
Expected behavior
Model name should be resnet18
On an additional note, I'd like to add a Live Webcam Feature to detect masks using EfficientNetB3.
tf.keras.applications.EfficientNetB3(
include_top=True, weights='imagenet', input_tensor=None,
input_shape=None, pooling=None, classes=1000,
classifier_activation='softmax', **kwargs
)
I'd like to work on this issue as part of GSSOC-21 and this will be implemented into This Folder.
Hello, I am a GSSOC'21 participant and I want add the GAN and CGAN architectures trained on MNIST data in the folder https://github.com/CoinShift-Imaging/CoinShift-Imaging-Box/tree/main/GANS.
I will add the notebooks and a readme explaining the same.
Could you please assign it to me?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.