First, thank you very much for your code and for sharing it.
I'm trying to apply it to a new dataset, and I have few questions about doing Auto-labeling for a new set of coarse data.
In your paper, you said the Auto-labeling was obtained by "[performing] a single iteration of full training of our teacher model with the default coarse and fine labeled provided image". However, for its application on the cityscape dataset, auto-labeled images have to be download from a drive. Could you please share the script (of a method) used to obtain such images please?
Thanks once again for your code, it is of great use.
Hi,
First, thank you very much for your code and for sharing it. I'm trying to apply it to a new dataset, and I have few questions about doing Auto-labeling for a new set of coarse data.
In your paper, you said the Auto-labeling was obtained by "[performing] a single iteration of full training of our teacher model with the default coarse and fine labeled provided image". However, for its application on the cityscape dataset, auto-labeled images have to be download from a drive. Could you please share the script (of a method) used to obtain such images please?
Thanks once again for your code, it is of great use.
Matthieu