(pretrained=False, load_pos_embed=True, **kwargs)
| 535 | |
| 536 | |
| 537 | def vit_aligned_base_patch16(pretrained=False, load_pos_embed=True, **kwargs): |
| 538 | default = dict( |
| 539 | # vitpose defauat drop_path_rate=0.3 |
| 540 | drop_path_rate=0.1, use_abs_pos_emb=True, # as in table 11 |
| 541 | #### |
| 542 | patch_size=16, embed_dim=768, depth=12, num_heads=12, mlp_ratio=4, qkv_bias=True, |
| 543 | norm_layer=partial(nn.LayerNorm, eps=1e-6) |
| 544 | ) |
| 545 | recursive_update(default, kwargs) |
| 546 | model = ViT(**default) |
| 547 | # del model.head |
| 548 | |
| 549 | if pretrained: |
| 550 | script_dir = os.path.dirname(__file__) |
| 551 | rel_path = "pretrain_weights/mae_pretrain_vit_base.pth" |
| 552 | |
| 553 | checkpoint = torch.load(os.path.join(script_dir, rel_path))['model'] |
| 554 | |
| 555 | # load while interpolates position embedding |
| 556 | load_checkpoint(model, checkpoint, load_pos_embed, strict=False, logger=dummy_logger) |
| 557 | |
| 558 | return model |
| 559 | |
| 560 | |
| 561 | class dummy_logger: |
nothing calls this directly
no test coverage detected