Closed Azong-HQU closed 1 year ago
作者您好!我按照如下操作进行转换数据格式(没改任何代码),但处理完后没有生成这个文件'datasets/coco/stuffthingmaps_panoptic_detectron2/train2017_base_label_count.json',导致在执行train_prompt阶段无法顺利进行,在“mask2former/data/datasets/register_coco_full.py”文件中的第233行 提示缺失上述json文件!请问作者能否提供我一些改进方法,帮助我解决这个问题?万分感谢!!!
python datasets/prepare_coco_alldata.py datasets/coco python datasets/prepare_coco_stuff_164k_sem_seg.py datasets/coco python tools/mask_cls_collect.py datasets/coco/stuffthingmaps_detectron2/train2017_base datasets/coco/stuffthingmaps_detectron2/train2017_base_label_count.json python tools/mask_cls_collect.py datasets/coco/stuffthingmaps_detectron2/val2017 datasets/coco/stuffthingmaps_detectron2/val2017_label_count.json
You can change the bash command from "datasets/coco/stuffthingmaps_detectron2/train2017_base_label_count.json" to "datasets/coco/stuffthingmaps_panoptic_detectron2/train2017_base_label_count.json".
作者您好!我按照如下操作进行转换数据格式(没改任何代码),但处理完后没有生成这个文件'datasets/coco/stuffthingmaps_panoptic_detectron2/train2017_base_label_count.json',导致在执行train_prompt阶段无法顺利进行,在“mask2former/data/datasets/register_coco_full.py”文件中的第233行 提示缺失上述json文件!请问作者能否提供我一些改进方法,帮助我解决这个问题?万分感谢!!!