@tteepe
I faced an issue when trying to run predict on CASIA-B, there were many unexpected layers not recognized when loading state_dict.
The result of my investigation points out that there was a backend mismatch, more details below:
In casia_b.yaml: backend_name: resgcn-n21-r8.
However, the pre-trained model used backbone resgcn-n31-r8 as stated in hparams.yaml and the training log file of this model as well.
There is no such n31 structure defined in the __init__.py of ResGCNv1, thus changing the backend_name solves nothing.
@tteepe I faced an issue when trying to run predict on CASIA-B, there were many unexpected layers not recognized when loading
state_dict
. The result of my investigation points out that there was a backend mismatch, more details below:casia_b.yaml
:backend_name: resgcn-n21-r8
.resgcn-n31-r8
as stated inhparams.yaml
and the training log file of this model as well.n31
structure defined in the__init__.py
of ResGCNv1, thus changing thebackend_name
solves nothing.