You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have a dataset with image size 128x128. When I use patch size of 8x8 the code works for me but when I'm trying to run the local model with patches of size 16x16 instead of 8x8 I get this error:
Using a target size (torch.Size([1, 1, 128, 128])) that is different to the input size (torch.Size([1, 1, 64, 64])) is deprecated. Please ensure they have the same size.
I changed the value of "patch_size" in the file mmseg/models/segmentors/encoder_decoder_local8x8.py to be 16.
what else do I need to change?
The text was updated successfully, but these errors were encountered:
Please try to change the size in config files, e.g., configs/bsds/EDTER_BIMLA_320x320_80k_bsds_local8x8_bs_8.py or configs/base/models/edter_bimla_local8x8.py.
I have a dataset with image size 128x128. When I use patch size of 8x8 the code works for me but when I'm trying to run the local model with patches of size 16x16 instead of 8x8 I get this error:
Using a target size (torch.Size([1, 1, 128, 128])) that is different to the input size (torch.Size([1, 1, 64, 64])) is deprecated. Please ensure they have the same size.
I changed the value of "patch_size" in the file mmseg/models/segmentors/encoder_decoder_local8x8.py to be 16.
what else do I need to change?
The text was updated successfully, but these errors were encountered: