hustvl / BoxTeacher

[CVPR 2023] Exploring High-Quality Pseudo Masks for Weakly Supervised Instance Segmentation
https://arxiv.org/abs/2210.05174
MIT License
74 stars 3 forks source link

RuntimeError: input tensor must fit into 32-bit index mathPlease read & provide the following #11

Open VikasRajashekar opened 6 months ago

VikasRajashekar commented 6 months ago

I get the following error:

` File "/netscratch/rajashekar/SAIL/BoxTeacher_new/BoxTeacher-main/projects/BoxTeacher/boxteacher/condinst.py", line 579, in forward instances_per_im = self.postprocess( File "/netscratch/rajashekar/SAIL/BoxTeacher_new/BoxTeacher-main/projects/BoxTeacher/boxteacher/condinst.py", line 795, in postprocess pred_global_masks = aligned_bilinear( File "/netscratch/rajashekar/SAIL/BoxTeacher_new/BoxTeacher-main/AdelaiDet/adet/utils/comm.py", line 40, in aligned_bilinear tensor = F.pad( File "/opt/conda/lib/python3.8/site-packages/torch/nn/functional.py", line 4194, in _pad return torch._C._nn.replication_pad2d(input, pad) RuntimeError: input tensor must fit into 32-bit index math

`

Attaching the config file generated as txt. config.txt

Please let me know how do i resolve this?