Spaces:
Runtime error
Runtime error
File size: 5,559 Bytes
3e99b05 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
# coding=utf-8
# Copyright 2022 The IDEA Authors. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ------------------------------------------------------------------------------------------------
# HungarianMatcher
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# ------------------------------------------------------------------------------------------------
# Modified from:
# https://github.com/Atten4Vis/ConditionalDETR/blob/GroupDETR/models/matcher.py
# ------------------------------------------------------------------------------------------------
import numpy as np
import torch
import torch.nn as nn
from scipy.optimize import linear_sum_assignment
from detrex.layers.box_ops import box_cxcywh_to_xyxy, generalized_box_iou
class GroupHungarianMatcher(nn.Module):
"""HugarianMatcher supports Group-DETR
Args:
cost_class (float): The relative weight of the classification error
in the matching cost. Default: 1.
cost_bbox (float): The relative weight of the L1 error of the bounding box
coordinates in the matching cost. Default: 1.
cost_giou (float): This is the relative weight of the giou loss of
the bounding box in the matching cost. Default: 1.
"""
def __init__(self, cost_class: float = 1, cost_bbox: float = 1, cost_giou: float = 1):
super().__init__()
self.cost_class = cost_class
self.cost_bbox = cost_bbox
self.cost_giou = cost_giou
assert cost_class != 0 or cost_bbox != 0 or cost_giou != 0, "all costs cant be 0"
@torch.no_grad()
def forward(self, outputs, targets, group_nums=1):
"""Performs the matching
Params:
outputs: This is a dict that contains at least these entries:
"pred_logits": Tensor of dim [batch_size, num_queries, num_classes] with the classification logits
"pred_boxes": Tensor of dim [batch_size, num_queries, 4] with the predicted box coordinates
targets: This is a list of targets (len(targets) = batch_size), where each target is a dict containing:
"labels": Tensor of dim [num_target_boxes] (where num_target_boxes is the number of ground-truth
objects in the target) containing the class labels
"boxes": Tensor of dim [num_target_boxes, 4] containing the target box coordinates
group_nums: Number of groups used for matching.
Returns:
A list of size batch_size, containing tuples of (index_i, index_j) where:
- index_i is the indices of the selected predictions (in order)
- index_j is the indices of the corresponding selected targets (in order)
For each batch element, it holds:
len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
"""
bs, num_queries = outputs["pred_logits"].shape[:2]
# We flatten to compute the cost matrices in a batch
out_prob = (
outputs["pred_logits"].flatten(0, 1).sigmoid()
) # [batch_size * num_queries, num_classes]
out_bbox = outputs["pred_boxes"].flatten(0, 1) # [batch_size * num_queries, 4]
# Also concat the target labels and boxes
tgt_ids = torch.cat([v["labels"] for v in targets])
tgt_bbox = torch.cat([v["boxes"] for v in targets])
# Compute the classification cost.
alpha = 0.25
gamma = 2.0
neg_cost_class = (1 - alpha) * (out_prob**gamma) * (-(1 - out_prob + 1e-8).log())
pos_cost_class = alpha * ((1 - out_prob) ** gamma) * (-(out_prob + 1e-8).log())
cost_class = pos_cost_class[:, tgt_ids] - neg_cost_class[:, tgt_ids]
# Compute the L1 cost between boxes
cost_bbox = torch.cdist(out_bbox, tgt_bbox, p=1)
# Compute the giou cost betwen boxes
cost_giou = -generalized_box_iou(box_cxcywh_to_xyxy(out_bbox), box_cxcywh_to_xyxy(tgt_bbox))
# Final cost matrix
C = self.cost_bbox * cost_bbox + self.cost_class * cost_class + self.cost_giou * cost_giou
C = C.view(bs, num_queries, -1).cpu()
sizes = [len(v["boxes"]) for v in targets]
indices = []
g_num_queries = num_queries // group_nums
C_list = C.split(g_num_queries, dim=1)
for g_i in range(group_nums):
C_g = C_list[g_i]
indices_g = [linear_sum_assignment(c[i]) for i, c in enumerate(C_g.split(sizes, -1))]
if g_i == 0:
indices = indices_g
else:
indices = [
(
np.concatenate([indice1[0], indice2[0] + g_num_queries * g_i]),
np.concatenate([indice1[1], indice2[1]]),
)
for indice1, indice2 in zip(indices, indices_g)
]
return [
(torch.as_tensor(i, dtype=torch.int64), torch.as_tensor(j, dtype=torch.int64))
for i, j in indices
]
|