Hi, I meet a problem about training PGSFormer using batch size 4 per GPU, could you help me to debug this ?
Error info. :
"openpsg/models/relation_heads/psgformer_head.py" line 501, in loss_single
filtered_subject_scores = torch.cat(
RuntimeError: Sizes of tensors must match except in dimension 1. Got 9 and
8 (The offending index is 0)
I only change this line "data = dict(samples_per_gpu=4," in File "configs/psgformer/psgformer_r50_psg.py"
Hi, I meet a problem about training PGSFormer using batch size 4 per GPU, could you help me to debug this ?
Error info. :
I only change this line "data = dict(samples_per_gpu=4," in File "configs/psgformer/psgformer_r50_psg.py"