groundingdino/models/GroundingDINO/backbone/position_encoding.py

# ------------------------------------------------------------------------
# Grounding DINO
# url: https://github.com/IDEA-Research/GroundingDINO
# Copyright (c) 2023 IDEA. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# DINO
# Copyright (c) 2022 IDEA. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Conditional DETR
# Copyright (c) 2021 Microsoft. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Copied from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
# ------------------------------------------------------------------------

"""
Various positional encodings for the transformer.
"""
import math

import torch
from torch import nn

from groundingdino.util.misc import NestedTensor


class PositionEmbeddingSine(nn.Module):
    """
    This is a more standard version of the position embedding, very similar to the one
    used by the Attention is all you need paper, generalized to work on images.
    """

    def __init__(self, num_pos_feats=64, temperature=10000, normalize=False, scale=None):
        super().__init__()
        self.num_pos_feats = num_pos_feats
        self.temperature = temperature
        self.normalize = normalize
        if scale is not None and normalize is False:
            raise ValueError("normalize should be True if scale is passed")
        if scale is None:
            scale = 2 * math.pi
        self.scale = scale

    def forward(self, tensor_list: NestedTensor):
        x = tensor_list.tensors
        mask = tensor_list.mask
        assert mask is not None
        not_mask = ~mask
        y_embed = not_mask.cumsum(1, dtype=torch.float32)
        x_embed = not_mask.cumsum(2, dtype=torch.float32)
        if self.normalize:
            eps = 1e-6
            # if os.environ.get("SHILONG_AMP", None) == '1':
            #     eps = 1e-4
            # else:
            #     eps = 1e-6
            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale

        dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)

        pos_x = x_embed[:, :, :, None] / dim_t
        pos_y = y_embed[:, :, :, None] / dim_t
        pos_x = torch.stack(
            (pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos_y = torch.stack(
            (pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
        return pos


class PositionEmbeddingSineHW(nn.Module):
    """
    This is a more standard version of the position embedding, very similar to the one
    used by the Attention is all you need paper, generalized to work on images.
    """

    def __init__(
        self, num_pos_feats=64, temperatureH=10000, temperatureW=10000, normalize=False, scale=None
    ):
        super().__init__()
        self.num_pos_feats = num_pos_feats
        self.temperatureH = temperatureH
        self.temperatureW = temperatureW
        self.normalize = normalize
        if scale is not None and normalize is False:
            raise ValueError("normalize should be True if scale is passed")
        if scale is None:
            scale = 2 * math.pi
        self.scale = scale

    def forward(self, tensor_list: NestedTensor):
        x = tensor_list.tensors
        mask = tensor_list.mask
        assert mask is not None
        not_mask = ~mask
        y_embed = not_mask.cumsum(1, dtype=torch.float32)
        x_embed = not_mask.cumsum(2, dtype=torch.float32)

        # import ipdb; ipdb.set_trace()

        if self.normalize:
            eps = 1e-6
            y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
            x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale

        dim_tx = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_tx = self.temperatureW ** (2 * (torch.div(dim_tx, 2, rounding_mode='floor')) / self.num_pos_feats)
        pos_x = x_embed[:, :, :, None] / dim_tx

        dim_ty = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
        dim_ty = self.temperatureH ** (2 * (torch.div(dim_ty, 2, rounding_mode='floor')) / self.num_pos_feats)
        pos_y = y_embed[:, :, :, None] / dim_ty

        pos_x = torch.stack(
            (pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos_y = torch.stack(
            (pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4
        ).flatten(3)
        pos = torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)

        # import ipdb; ipdb.set_trace()

        return pos


class PositionEmbeddingLearned(nn.Module):
    """
    Absolute pos embedding, learned.
    """

    def __init__(self, num_pos_feats=256):
        super().__init__()
        self.row_embed = nn.Embedding(50, num_pos_feats)
        self.col_embed = nn.Embedding(50, num_pos_feats)
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.uniform_(self.row_embed.weight)
        nn.init.uniform_(self.col_embed.weight)

    def forward(self, tensor_list: NestedTensor):
        x = tensor_list.tensors
        h, w = x.shape[-2:]
        i = torch.arange(w, device=x.device)
        j = torch.arange(h, device=x.device)
        x_emb = self.col_embed(i)
        y_emb = self.row_embed(j)
        pos = (
            torch.cat(
                [
                    x_emb.unsqueeze(0).repeat(h, 1, 1),
                    y_emb.unsqueeze(1).repeat(1, w, 1),
                ],
                dim=-1,
            )
            .permute(2, 0, 1)
            .unsqueeze(0)
            .repeat(x.shape[0], 1, 1, 1)
        )
        return pos


def build_position_encoding(args):
    N_steps = args.hidden_dim // 2
    if args.position_embedding in ("v2", "sine"):
        # TODO find a better way of exposing other arguments
        position_embedding = PositionEmbeddingSineHW(
            N_steps,
            temperatureH=args.pe_temperatureH,
            temperatureW=args.pe_temperatureW,
            normalize=True,
        )
    elif args.position_embedding in ("v3", "learned"):
        position_embedding = PositionEmbeddingLearned(N_steps)
    else:
        raise ValueError(f"not supported {args.position_embedding}")

    return position_embedding