Drag mouse (from the top to the right) to mark a new region for inference.
Use the A,S,D,W keys to translate and J,K,L,I to enlarge bounding box (hold the Shift key
to move x10 faster). This region from the source image (see its position,
width and height in console) is scaled into 224x224 image and is shown to the right.
Open a new browser window (or tab) and Copy / Paste(Ctrl+V) images from
image.google.com,
unsplash.com, ...
You can Copy images from your PC e.g. by Photos or Paint.
Press the "trick" button to split image randomly (by 7x7 pieces).
Comments
CNNs are trained to distinguish 1000 image classes by local features.
Moreover, average pooling on the 7x7 grid is used before classification.
Therefore we can trick them by mixing randomly 7x7 pieces of images.
Obviously it works better for "zebra" stripes :)
TFjs notesupdated 9 Jan 2020
