When I use mask2former_learn_prompt_bs16_10k.yaml to get proposal classification, i got an error "RuntimeError: The size of tensor a (211) must match the size of tensor b (197) at non-singleton dimension 1". I checked the size is (224, 244), but the position embedding is (197, n_dim). Is the predefined size wrong?
Logically, there will be no problem of predefined size errors. You can provide the specific code location where the error is reported to facilitate locating the problem.
When I use mask2former_learn_prompt_bs16_10k.yaml to get proposal classification, i got an error "RuntimeError: The size of tensor a (211) must match the size of tensor b (197) at non-singleton dimension 1". I checked the size is (224, 244), but the position embedding is (197, n_dim). Is the predefined size wrong?