threestudio/utils/dpt.py [267:312]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )

    pretrained.act_postprocess3 = nn.Sequential(
        readout_oper[2],
        Transpose(1, 2),
        nn.Unflatten(2, torch.Size([size[0] // 16, size[1] // 16])),
        nn.Conv2d(
            in_channels=vit_features,
            out_channels=features[2],
            kernel_size=1,
            stride=1,
            padding=0,
        ),
    )

    pretrained.act_postprocess4 = nn.Sequential(
        readout_oper[3],
        Transpose(1, 2),
        nn.Unflatten(2, torch.Size([size[0] // 16, size[1] // 16])),
        nn.Conv2d(
            in_channels=vit_features,
            out_channels=features[3],
            kernel_size=1,
            stride=1,
            padding=0,
        ),
        nn.Conv2d(
            in_channels=features[3],
            out_channels=features[3],
            kernel_size=3,
            stride=2,
            padding=1,
        ),
    )

    pretrained.model.start_index = start_index
    pretrained.model.patch_size = [16, 16]

    # We inject this function into the VisionTransformer instances so that
    # we can use it with interpolated position embeddings without modifying the library source.
    pretrained.model.forward_flex = types.MethodType(forward_flex, pretrained.model)
    pretrained.model._resize_pos_embed = types.MethodType(
        _resize_pos_embed, pretrained.model
    )

    return pretrained
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



threestudio/utils/dpt.py [445:493]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )

    pretrained.act_postprocess3 = nn.Sequential(
        readout_oper[2],
        Transpose(1, 2),
        nn.Unflatten(2, torch.Size([size[0] // 16, size[1] // 16])),
        nn.Conv2d(
            in_channels=vit_features,
            out_channels=features[2],
            kernel_size=1,
            stride=1,
            padding=0,
        ),
    )

    pretrained.act_postprocess4 = nn.Sequential(
        readout_oper[3],
        Transpose(1, 2),
        nn.Unflatten(2, torch.Size([size[0] // 16, size[1] // 16])),
        nn.Conv2d(
            in_channels=vit_features,
            out_channels=features[3],
            kernel_size=1,
            stride=1,
            padding=0,
        ),
        nn.Conv2d(
            in_channels=features[3],
            out_channels=features[3],
            kernel_size=3,
            stride=2,
            padding=1,
        ),
    )

    pretrained.model.start_index = start_index
    pretrained.model.patch_size = [16, 16]

    # We inject this function into the VisionTransformer instances so that
    # we can use it with interpolated position embeddings without modifying the library source.
    pretrained.model.forward_flex = types.MethodType(forward_flex, pretrained.model)

    # We inject this function into the VisionTransformer instances so that
    # we can use it with interpolated position embeddings without modifying the library source.
    pretrained.model._resize_pos_embed = types.MethodType(
        _resize_pos_embed, pretrained.model
    )

    return pretrained
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -