Issue on mac M1 - Githubissues

TimKong21 / Polyp-Segmentation

Polyp segmentation tool utilizing U-Net for accurate medical image analysis, designed to enhance early detection and diagnosis of colorectal cancer. Features a user-friendly Streamlit web app for easy image processing and analysis, leveraging the Kvasir-SEG dataset for improved healthcare outcomes.

https://polyp-segmentation-tool.streamlit.app/

3 stars 2 forks source link

Issue on mac M1 #1

Closed kartikhegadi closed 4 months ago

kartikhegadi commented 5 months ago

While installing dependencies. ERROR

any other methord?

TimKong21 commented 5 months ago

Hi Kartik,

To address the installation issues on Mac M1, you should use Python >= 3.7 and < 3.11. Specifically for Mac M1, setting up a virtual environment with Python 3.8 is recommended. After setting up Python 3.8, you can try reinstalling the dependencies.

If issues persist, consider removing the explicit version numbers in the requirements.txt to let pip choose compatible versions for your system.

As a note, I'm developing this project on Windows with Python 3.10.11, which works well for me, but I do not use a Mac for testing.

For the Mac M1 architecture, ensure to install the ARM-compatible TensorFlow (tensorflow-macos).

Hope this helps.

kartikhegadi commented 5 months ago

Yes It helped me!!

Hi TimKong21,

Thank you for your detailed guidance! I followed your instructions and successfully set up Python 3.8 on my Mac M1. After reinstalling the dependencies and ensuring compatibility with ARM architecture, everything seems to be working smoothly now. Additionally, I've forked the project and made necessary changes to ensure compatibility for all Mac users. Your assistance has been invaluable in resolving the installation issues.

review --> The uploaded image is displayed as the first. The segmented mask appears as the second. However, the third display, representing the detected image, is not showing correctly. if any comments on this you can give suggestions @TimKong21

Best regards, Kartik

TimKong21 commented 4 months ago

Hi Kartik,

Thank you for taking the time to adapt the project for Mac users.

Regarding your review, the current implementation of the Polyp Segmentation Tool is designed to display only two main elements for each uploaded image: the original image and the predicted segmentation mask. There isn't a third display for a "detected image" in the version you've worked with. If you're referring to an overlay of the segmentation mask on the original image, that feature hasn't been implemented yet.

kartikhegadi commented 4 months ago

Okay , all the best @TimKong21