"The inference script we provide gets its input from a 6-band TIFF file. You can modify the script to feed the model a matrix of MxNx6 dimensions in any form. For example, you can read the input bands from separate files, concatenate them in the channel axis, and feed it to the model."
Could an additional section be added on how to implement this? Or the inference file be updated to have this as an option?
"The inference script we provide gets its input from a 6-band TIFF file. You can modify the script to feed the model a matrix of MxNx6 dimensions in any form. For example, you can read the input bands from separate files, concatenate them in the channel axis, and feed it to the model."
Could an additional section be added on how to implement this? Or the inference file be updated to have this as an option?