Closed Abeni18 closed 3 years ago
Or is it like, once the model is trained on the tiled image, during inference we use the original size image without tiling?
@Abeni18 Your last guess was right, here in the config you may see resolutions. Sorry for the long response.
Got it thanks
Thank you for the work. My question is for the tile-combine option, I assume there is a step where the tiled images predicted JSON file labels need to be combined into one JSON file label corresponding to the original image size. Where is that script located? I am not able to find it.
The soonest response is highly appreciated. Thank you!