MedSegDiff sample erroe

hello, I trained the model in my dataset, when I sample ,I meet the error.Could you help me？ RuntimeError: Error(s) in loading state_dict for UNetModel_v1preview: size mismatch for input_blocks.0.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 6, 3, 3]). size mismatch for hwm.conv1_e2_B.weight: copying a param with shape torch.Size([64, 3, 5, 5]) from checkpoint, the shape in current model is torch.Size([64, 6, 5, 5]).

Nov 03 '23 04:11 tianxiaoer

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

Title: sample error

Nov 03 '23 04:11 Issues-translate-bot

Same problem

Nov 06 '23 02:11 ahmadrezarm

Same problem

Do you set the param 'learn sigma' to be True, if you do not do that, you will meet that problem, or you can imitate the upper code.

Nov 11 '23 12:11 MurphyYe

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

Same problem

Do you set the param 'learn sigma' to be True, if you do not do that, you will meet that problem, or you can imitate the upper code.

Nov 11 '23 12:11 Issues-translate-bot