Giter VIP home page Giter VIP logo

ademakdogan / nails_segmentation Goto Github PK

View Code? Open in Web Editor NEW
27.0 2.0 11.0 20.2 MB

This project was made for nails segmentation using deep learning models. __DeepLabV3Plus__ was used for segmentation problem. ResNet101 were used as encoder and imagenet weights were used as encoder weights.

Dockerfile 0.10% Makefile 0.19% Jupyter Notebook 0.02% Python 99.68%
deep-learning docker nails-detection object-detection segmentation-based-detection resnet-101

nails_segmentation's People

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

nails_segmentation's Issues

Copyright Questions

We are 3rd year college students. Can I use your nail segmentation to write a thesis and submit it to a conference? Sources will be revealed. If you don't allow us to use it, we'll remove the related content!

question about copyright

Hi, I'm a junior in university student. For a class project assignment, my teammates and I utilized your "nails_segmentation" project to create a nail color recommendation app. At a good opportunity, our professor offer us to help register software. But we can't find any License mention in your posted files, so I send you this message. Can we register it? We have been used it for non-commercial purposes. Thank you.

Problem with Timm

Hi, I wanted to try your project but I have an error when I run " python3 main.py -m train -d mps".

ModuleNotFoundError: No module named 'timm.models.layers.activations'

The issue is that I have timm on my computer so I don't really understand

I don't think It's learning well.

스크린샷 2023-07-16 오전 1 38 29

I've done all the content of "readme", and I've been waiting for 80 epochs. However, the same results as "readme" have not been produced, which is causing difficulties. If you look at the picture I posted, you can see through the heat map that I can't find my nails for sure. Is there a better way to learn? Or am I missing something? I didn't edit any of the code given.

I'm using a MacBook Air m1, and Python version is 3.8.16.

no kernel image is available for execution on the device

Thanks for releasing the code. I found that after switching the device to cuda:0, I got the following error. May I ask for any suggestions, please?

  File "/home/yanhao/anaconda3/envs/nailseg/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 148, in forward
    self.num_batches_tracked.add_(1)  # type: ignore[has-type]
RuntimeError: CUDA error: no kernel image is available for execution on the device

question about weight

Hello, I don't have enough computer performance, can I ask what are the weights of this model? Thank you very much!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.