search

ashkamath / mdetr

Apache License 2.0
969 stars 125 forks source link

How to train DETR on provided LVIS 1%/10%/100% dtaset #57

Open Flaick opened 2 years ago

Flaick commented 2 years ago

Hi, Thank you for the great work. Though I am wondering how to train the DETR using the dataset you provided. When I check the caption for each bounding box, I find that the 'salmon(fish)' and 'salmon(food)' are merged into 'salmon' using the clean_name() function, resulting in 1199 classes smaller than 1203 classes in the original LVIS dataset.

I am wondering if there is a way to train the conventional DETR using the provided .json file.

Thanks in advance!