Is it possible to upload image and use it in ML model?

Using Streamlit
1

I have my model ready but I want to use this to run on new image data. And I want to get the image by using upload option using streamlit. Is it possible to do that?

2

Hi, the following example might help for your use case. It’s a modification from: Upload Files to Streamlit App

import os
import streamlit as st


def file_selector(folder_path='.'):
    filenames = os.listdir(folder_path)
    selected_filename = st.selectbox('Select a file', filenames)
    return os.path.join(folder_path, selected_filename)


if __name__ == '__main__':
    # Select a file
    if st.checkbox('Select a file in current directory'):
        folder_path = '.'
        if st.checkbox('Change directory'):
            folder_path = st.text_input('Enter folder path', '.')
        filename = file_selector(folder_path=folder_path)
        st.write('You selected `%s`' % filename)

    # TODO: Add code to open and process your image file
1 Like
3

There’s actually a file uploader, streamlit.file_uploader which returns a bytesio for binary uploads.

4 Likes