Mooshie/swinv2_base_window8_256.dbv4-full
Full fine-tune vs timm/swinv2_base_window8_256.ms_in1k. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Attention 216/216, MLP 96/96, Norms 104/104, other 3/3, Embeddings 4/4
Full fine-tune vs timm/swinv2_base_window8_256.ms_in1k. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Attention 216/216, MLP 96/96, Norms 104/104, other 3/3, Embeddings 4/4