Panoptic-SegFormer issues

Impossible to debug, single_gpu code paths are broken

1

It seems that the multi gpu training and eval works great, however, while trying to debug you're opt for using a single gpu. In that case the code breaks in...

aviadmx

Why instance annotations are required along panoptic ones?

5

The model solves the panoptic segmentation task, why does the validation dataset uses the instance segmentation annotations? ``` data = dict( samples_per_gpu=2, workers_per_gpu=2, train=dict( type=dataset_type, ann_file= './datasets/annotations/panoptic_train2017_detection_format.json', img_prefix=data_root + 'train2017/',...

aviadmx

Loading checkpoint

3

When loading the Swin-L checkpoint by adding a `load_from` line to the config `configs/panformer/panformer_swinl_24e_coco_panoptic.pyz` as following: ``` load_from='./pretrained/panoptic_segformer_swinl_2x.pth' ``` The loading fails with an error about keys mismatch: ``` unexpected...

aviadmx

ImportError Libtorch_cpu.so: undefined symbol

1

Thank you for this awesome work Unfortunately I can't run the training because I get the following error ``` ./tools/dist_train.sh ./configs/panformer/panformer_r50_24e_coco_panoptic.py 1 + CONFIG=./configs/panformer/panformer_r50_24e_coco_panoptic.py + GPUS=1 + PORT=29503 ++ dirname...

EnnioEvo

dataset problem

1

Hello, I'm trying to train this model by using my own dataset. But how could I build my own coco-like panoptic segmentation dataset with my own dataset to use this...

hys02245

Instruction for single GPU run

2

Hi thanks for sharing your works. Iwas trying to run it on single gpu. Would you pls add some instructions or scripts to run it in single gpu? That would...

nazib