How can we resume training from the last checkpoint saved?
2nd Question, I've images of 4 different channels (Red, green, NIR, Red edge) in 4 different folders, each folder contain a single channel images. To apply semantic segmentation Do i have to merge images into 3 channels or I can use multiple input image input of your repository?
How can we resume training from the last checkpoint saved? 2nd Question, I've images of 4 different channels (Red, green, NIR, Red edge) in 4 different folders, each folder contain a single channel images. To apply semantic segmentation Do i have to merge images into 3 channels or I can use multiple input image input of your repository?