How to load pretrain models?

[xiazhongyv]

I have a lightning model {EncoderA, EncoderB, FusionModule, Decoder}
And I pretrained (DDP ckpt1){EncoderA, Decoder}, (DDP ckpt2){EncoderB, Decoder}
How can I train (DDP){EncoderA, EncoderB, FusionModule, Decoder}, load pretrained EncoderA from ckpt1, load pretrained EncoderB from ckpt2, and ignore hyperparameters of ckpt1 and ckpt2 ?

[xiazhongyv]

I tried using MyLighteningModule.model.EncoderA.load_state_dict(torch.load(ckpt1)) , but error occured like:

size mismatch for pts_middle_encoder.encoder_layers.encoder_layer3.1.conv1.weight: copying a param with shape ('pts_middle_encoder.encoder_layers.encoder_layer3.1.conv1.weight', torch.Size([64, 64, 3, 3, 3])) from checkpoint,the shape in current model is torch.Size([64, 3, 3, 3, 64]).
size mismatch for pts_middle_encoder.encoder_layers.encoder_layer3.1.conv2.weight: copying a param with shape ('pts_middle_encoder.encoder_layers.encoder_layer3.1.conv2.weight', torch.Size([64, 64, 3, 3, 3])) from checkpoint,the shape in current model is torch.Size([64, 3, 3, 3, 64]).
size mismatch for pts_middle_encoder.encoder_layers.encoder_layer3.2.0.weight: copying a param with shape ('pts_middle_encoder.encoder_layers.encoder_layer3.2.0.weight', torch.Size([64, 128, 3, 3, 3])) from checkpoint,the shape in current model is torch.Size([128, 3, 3, 3, 64]).
......