RuntimeError: expected scalar type Half but found Float

[sanmulab]

Hello author! I seem to have a new problem now: I want to use half-precision fp16 for training, so I add the line fp16 = dict(loss_scale=512.) to the config file, but I get an error: . Does your codebase currently not support half-precision training?

error:
File "/home/ubuntu/cs_logdet/rankSortLoss-main/mmdet/models/necks/fpn_carafe.py", line 256, in forward
upsample_feat = self.upsample_modulesi - 1
File "/home/ubuntu/.conda/envs/testlogdet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/ubuntu/.conda/envs/testlogdet/lib/python3.7/site-packages/mmcv/ops/carafe.py", line 285, in forward
x = self.feature_reassemble(x, mask)
File "/home/ubuntu/.conda/envs/testlogdet/lib/python3.7/site-packages/mmcv/ops/carafe.py", line 277, in feature_reassemble
x = carafe(x, mask, self.up_kernel, self.up_group, self.scale_factor)
File "/home/ubuntu/.conda/envs/testlogdet/lib/python3.7/site-packages/mmcv/ops/carafe.py", line 139, in forward
scale_factor=scale_factor)
RuntimeError: expected scalar type Half but found Float

[kemaloksuz]

Hi,

Unfortunately, we have tried the code with half precision. Having checked your error message, the error may not be related to RS Loss but carafe operation in the mmdetection, however, I am not fully sure. Have you tried to run an architecture without carafe?

[sanmulab]

This is the case, when I add fpn_carafe, I will have this error, and I can train normally without fpn_carafe. I will go to the official to raise this issue. Thanks for answering.