shi-labs

/

oneformer_ade20k_swin_tiny

like 13

Follow

SHI Labs 47

I want to fine tune the model, so:
config=OneFormerConfig.from_pretrained("shi-labs/oneformer_ade20k_swin_tiny",is_training=True)
model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_swin_tiny",config=config)

But the text_mapper seems not in the model checkpoint:
Some weights of OneFormerForUniversalSegmentation were not initialized from the model checkpoint at shi-labs/oneformer_ade20k_swin_tiny and are newly initialized: ['model.text_mapper.text_encoder.transformer.layers.2.mlp.fc1.bias', ......,'model.text_mapper.text_encoder.transformer.layers.5.self_attn.out_proj.bias']

So that means I must retrain the text_mapper if fine-tuning?