Open Dowe-dong opened 1 year ago
v
I want test your algriom on cornell datatset but I don't know how to convert the data format, Thank u for you excellent job.
Sorry for the delay. This repo is no longer maintained.
To convert the dataset, you need to first use the background images provided by the cornell grasp dataset to segment the foreground objects. This might be a little tricky because you need to find a proper threshold and refine the results with manual labels.
Then you can directly follow the dataset format of our VMRN dataset to convert the data.
I want test your algriom on cornell datatset but I don't know how to convert the data format, Thank u for you excellent job.