Convolution Playground

Experiment with image convolutions in your browser.

GitHub repository

Instructions

Upload the image this url then try the following kernels. What do you think each of them does?
  1. All positive numbers.
  2. All negative numbers.
  3. All zeros.
  4. All zeros, except a 1 in the top center.
Next, try to find a kernel for each of the following actions:
  1. Detects vertical edges.
  2. Detects horizantal edges.
  3. Generally detects contrast.
  4. Makes the image solid gray.
  5. Slightly brightens the image.
  6. Slightly darkens the image.
  7. Keeps as much as possible but removes the dots on the cat's body.
  8. Keeps as much of the cat as possible while making the background white.
  9. Emphasizes the stars and dots in the image.
Now, head over to https://adamharley.com/nn_vis/cnn/2d.html. Take a look at the first convolutional layer. What features do each of the convolutions represent? Try drawing a few different shapes to see what causes the pixels to light up for each kernel. Try to find a way to draw numbers in a style where the model fails to guess the correct number. How were you able to trick the model? Why do you think this is the case?
Upload an image file in .jpeg, .png, or .gif format.
Enter a URL of an image in .jpeg, .png, or .gif format.
Set resolution of input image.

Resolution

Current resolution.
Select a filter kernel to apply to image.


    Apply filter to image.


    Randomize weights of filter kernel.

    Input is not a number
    Repeat convolutional filter on image a specified number of times.
    Update convolutional filter whenever a setting is changed.
    Export filter kernel
    Import filter kernel

    Edit Kernel

    Input is not a number
    Repeat convolutional filter on image a specified number of times.
    Input image
    Download input image
    Output image
    Download output image

    Load Image From URL

    Enter an image URL below to load an image. Note that not all websites will allow this. Try Imgur.

    Export Filter Kernel

    Copy and paste the code below, or press the download button to save a text file with the filter kernel information.


    Download filter kernel data

    Import Filter Kernel

    Paste your filter kernel code here.