def add_fpn()

in detectron/modeling/FPN.py [0:0]


def add_fpn(model, fpn_level_info):
    """Add FPN connections based on the model described in the FPN paper."""
    # FPN levels are built starting from the highest/coarest level of the
    # backbone (usually "conv5"). First we build down, recursively constructing
    # lower/finer resolution FPN levels. Then we build up, constructing levels
    # that are even higher/coarser than the starting level.
    fpn_dim = cfg.FPN.DIM
    min_level, max_level = get_min_max_levels()
    # Count the number of backbone stages that we will generate FPN levels for
    # starting from the coarest backbone stage (usually the "conv5"-like level)
    # E.g., if the backbone level info defines stages 4 stages: "conv5",
    # "conv4", ... "conv2" and min_level=2, then we end up with 4 - (2 - 2) = 4
    # backbone stages to add FPN to.
    num_backbone_stages = (
        len(fpn_level_info.blobs) - (min_level - LOWEST_BACKBONE_LVL)
    )

    lateral_input_blobs = fpn_level_info.blobs[:num_backbone_stages]
    output_blobs = [
        'fpn_inner_{}'.format(s)
        for s in fpn_level_info.blobs[:num_backbone_stages]
    ]
    fpn_dim_lateral = fpn_level_info.dims
    xavier_fill = ('XavierFill', {})

    # For the coarsest backbone level: 1x1 conv only seeds recursion
    if cfg.FPN.USE_GN:
        # use GroupNorm
        c = model.ConvGN(
            lateral_input_blobs[0],
            output_blobs[0],  # note: this is a prefix
            dim_in=fpn_dim_lateral[0],
            dim_out=fpn_dim,
            group_gn=get_group_gn(fpn_dim),
            kernel=1,
            pad=0,
            stride=1,
            weight_init=xavier_fill,
            bias_init=const_fill(0.0)
        )
        output_blobs[0] = c  # rename it
    else:
        model.Conv(
            lateral_input_blobs[0],
            output_blobs[0],
            dim_in=fpn_dim_lateral[0],
            dim_out=fpn_dim,
            kernel=1,
            pad=0,
            stride=1,
            weight_init=xavier_fill,
            bias_init=const_fill(0.0)
        )

    #
    # Step 1: recursively build down starting from the coarsest backbone level
    #

    # For other levels add top-down and lateral connections
    for i in range(num_backbone_stages - 1):
        add_topdown_lateral_module(
            model,
            output_blobs[i],             # top-down blob
            lateral_input_blobs[i + 1],  # lateral blob
            output_blobs[i + 1],         # next output blob
            fpn_dim,                     # output dimension
            fpn_dim_lateral[i + 1]       # lateral input dimension
        )

    # Post-hoc scale-specific 3x3 convs
    blobs_fpn = []
    spatial_scales = []
    for i in range(num_backbone_stages):
        if cfg.FPN.USE_GN:
            # use GroupNorm
            fpn_blob = model.ConvGN(
                output_blobs[i],
                'fpn_{}'.format(fpn_level_info.blobs[i]),
                dim_in=fpn_dim,
                dim_out=fpn_dim,
                group_gn=get_group_gn(fpn_dim),
                kernel=3,
                pad=1,
                stride=1,
                weight_init=xavier_fill,
                bias_init=const_fill(0.0)
            )
        else:
            fpn_blob = model.Conv(
                output_blobs[i],
                'fpn_{}'.format(fpn_level_info.blobs[i]),
                dim_in=fpn_dim,
                dim_out=fpn_dim,
                kernel=3,
                pad=1,
                stride=1,
                weight_init=xavier_fill,
                bias_init=const_fill(0.0)
            )
        blobs_fpn += [fpn_blob]
        spatial_scales += [fpn_level_info.spatial_scales[i]]

    #
    # Step 2: build up starting from the coarsest backbone level
    #

    # Check if we need the P6 feature map
    if not cfg.FPN.EXTRA_CONV_LEVELS and max_level == HIGHEST_BACKBONE_LVL + 1:
        # Original FPN P6 level implementation from our CVPR'17 FPN paper
        P6_blob_in = blobs_fpn[0]
        P6_name = P6_blob_in + '_subsampled_2x'
        # Use max pooling to simulate stride 2 subsampling
        P6_blob = model.MaxPool(P6_blob_in, P6_name, kernel=1, pad=0, stride=2)
        blobs_fpn.insert(0, P6_blob)
        spatial_scales.insert(0, spatial_scales[0] * 0.5)

    # Coarser FPN levels introduced for RetinaNet
    if cfg.FPN.EXTRA_CONV_LEVELS and max_level > HIGHEST_BACKBONE_LVL:
        fpn_blob = fpn_level_info.blobs[0]
        dim_in = fpn_level_info.dims[0]
        for i in range(HIGHEST_BACKBONE_LVL + 1, max_level + 1):
            fpn_blob_in = fpn_blob
            if i > HIGHEST_BACKBONE_LVL + 1:
                fpn_blob_in = model.Relu(fpn_blob, fpn_blob + '_relu')
            fpn_blob = model.Conv(
                fpn_blob_in,
                'fpn_' + str(i),
                dim_in=dim_in,
                dim_out=fpn_dim,
                kernel=3,
                pad=1,
                stride=2,
                weight_init=xavier_fill,
                bias_init=const_fill(0.0)
            )
            dim_in = fpn_dim
            blobs_fpn.insert(0, fpn_blob)
            spatial_scales.insert(0, spatial_scales[0] * 0.5)

    return blobs_fpn, fpn_dim, spatial_scales