File size: 9,398 Bytes
d24572a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
# ------------------------------------------------------------------------
# Grounding DINO. Midified by Shilong Liu.
# 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]
# ------------------------------------------------------------------------
# Copyright (c) Aishwarya Kamath & Nicolas Carion. Licensed under the Apache License 2.0. All Rights Reserved
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
"""
COCO evaluator that works in distributed mode.

Mostly copy-paste from https://github.com/pytorch/vision/blob/edfd5a7/references/detection/coco_eval.py
The difference is that there is less copy-pasting from pycocotools
in the end of the file, as python3 can suppress prints with contextlib
"""
import contextlib
import copy
import os

import numpy as np
import pycocotools.mask as mask_util
import torch
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval

from groundingdino.util.misc import all_gather


class CocoGroundingEvaluator(object):
    def __init__(self, coco_gt, iou_types, useCats=True):
        assert isinstance(iou_types, (list, tuple))
        coco_gt = copy.deepcopy(coco_gt)
        self.coco_gt = coco_gt

        self.iou_types = iou_types
        self.coco_eval = {}
        for iou_type in iou_types:
            self.coco_eval[iou_type] = COCOeval(coco_gt, iouType=iou_type)
            self.coco_eval[iou_type].useCats = useCats

        self.img_ids = []
        self.eval_imgs = {k: [] for k in iou_types}
        self.useCats = useCats

    def update(self, predictions):
        img_ids = list(np.unique(list(predictions.keys())))
        self.img_ids.extend(img_ids)

        for iou_type in self.iou_types:
            results = self.prepare(predictions, iou_type)

            # suppress pycocotools prints
            with open(os.devnull, "w") as devnull:
                with contextlib.redirect_stdout(devnull):
                    coco_dt = COCO.loadRes(self.coco_gt, results) if results else COCO()

            coco_eval = self.coco_eval[iou_type]

            coco_eval.cocoDt = coco_dt
            coco_eval.params.imgIds = list(img_ids)
            coco_eval.params.useCats = self.useCats
            img_ids, eval_imgs = evaluate(coco_eval)

            self.eval_imgs[iou_type].append(eval_imgs)

    def synchronize_between_processes(self):
        for iou_type in self.iou_types:
            self.eval_imgs[iou_type] = np.concatenate(self.eval_imgs[iou_type], 2)
            create_common_coco_eval(self.coco_eval[iou_type], self.img_ids, self.eval_imgs[iou_type])

    def accumulate(self):
        for coco_eval in self.coco_eval.values():
            coco_eval.accumulate()

    def summarize(self):
        for iou_type, coco_eval in self.coco_eval.items():
            print("IoU metric: {}".format(iou_type))
            coco_eval.summarize()

    def prepare(self, predictions, iou_type):
        if iou_type == "bbox":
            return self.prepare_for_coco_detection(predictions)
        elif iou_type == "segm":
            return self.prepare_for_coco_segmentation(predictions)
        elif iou_type == "keypoints":
            return self.prepare_for_coco_keypoint(predictions)
        else:
            raise ValueError("Unknown iou type {}".format(iou_type))

    def prepare_for_coco_detection(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            boxes = prediction["boxes"]
            boxes = convert_to_xywh(boxes).tolist()
            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": labels[k],
                        "bbox": box,
                        "score": scores[k],
                    }
                    for k, box in enumerate(boxes)
                ]
            )
        return coco_results

    def prepare_for_coco_segmentation(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            scores = prediction["scores"]
            labels = prediction["labels"]
            masks = prediction["masks"]

            masks = masks > 0.5

            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()

            rles = [
                mask_util.encode(np.array(mask[0, :, :, np.newaxis], dtype=np.uint8, order="F"))[0] 
                for mask in masks
            ]
            for rle in rles:
                rle["counts"] = rle["counts"].decode("utf-8")

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": labels[k],
                        "segmentation": rle,
                        "score": scores[k],
                    }
                    for k, rle in enumerate(rles)
                ]
            )
        return coco_results

    def prepare_for_coco_keypoint(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            boxes = prediction["boxes"]
            boxes = convert_to_xywh(boxes).tolist()
            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()
            keypoints = prediction["keypoints"]
            keypoints = keypoints.flatten(start_dim=1).tolist()

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": labels[k],
                        "keypoints": keypoint,
                        "score": scores[k],
                    }
                    for k, keypoint in enumerate(keypoints)
                ]
            )
        return coco_results


def convert_to_xywh(boxes):
    xmin, ymin, xmax, ymax = boxes.unbind(1)
    return torch.stack((xmin, ymin, xmax - xmin, ymax - ymin), dim=1)


def merge(img_ids, eval_imgs):
    all_img_ids = all_gather(img_ids)
    all_eval_imgs = all_gather(eval_imgs)

    merged_img_ids = []
    for p in all_img_ids:
        merged_img_ids.extend(p)

    merged_eval_imgs = []
    for p in all_eval_imgs:
        merged_eval_imgs.append(p)

    merged_img_ids = np.array(merged_img_ids)
    merged_eval_imgs = np.concatenate(merged_eval_imgs, 2)

    # keep only unique (and in sorted order) images
    merged_img_ids, idx = np.unique(merged_img_ids, return_index=True)
    merged_eval_imgs = merged_eval_imgs[..., idx]

    return merged_img_ids, merged_eval_imgs


def create_common_coco_eval(coco_eval, img_ids, eval_imgs):
    img_ids, eval_imgs = merge(img_ids, eval_imgs)
    img_ids = list(img_ids)
    eval_imgs = list(eval_imgs.flatten())

    coco_eval.evalImgs = eval_imgs
    coco_eval.params.imgIds = img_ids
    coco_eval._paramsEval = copy.deepcopy(coco_eval.params)


#################################################################
# From pycocotools, just removed the prints and fixed
# a Python3 bug about unicode not defined
#################################################################


def evaluate(self):
    """
    Run per image evaluation on given images and store results (a list of dict) in self.evalImgs
    :return: None
    """
    # tic = time.time()
    # print('Running per image evaluation...')
    p = self.params
    # add backward compatibility if useSegm is specified in params
    if p.useSegm is not None:
        p.iouType = "segm" if p.useSegm == 1 else "bbox"
        print("useSegm (deprecated) is not None. Running {} evaluation".format(p.iouType))
    # print('Evaluate annotation type *{}*'.format(p.iouType))
    p.imgIds = list(np.unique(p.imgIds))
    if p.useCats:
        p.catIds = list(np.unique(p.catIds))
    p.maxDets = sorted(p.maxDets)
    self.params = p

    self._prepare()
    # loop through images, area range, max detection number
    catIds = p.catIds if p.useCats else [-1]

    if p.iouType == "segm" or p.iouType == "bbox":
        computeIoU = self.computeIoU
    elif p.iouType == "keypoints":
        computeIoU = self.computeOks
    self.ious = {
        (imgId, catId): computeIoU(imgId, catId) 
        for imgId in p.imgIds 
        for catId in catIds}

    evaluateImg = self.evaluateImg
    maxDet = p.maxDets[-1]
    evalImgs = [
        evaluateImg(imgId, catId, areaRng, maxDet) 
        for catId in catIds 
        for areaRng in p.areaRng 
        for imgId in p.imgIds
    ]
    # this is NOT in the pycocotools code, but could be done outside
    evalImgs = np.asarray(evalImgs).reshape(len(catIds), len(p.areaRng), len(p.imgIds))
    self._paramsEval = copy.deepcopy(self.params)
    # toc = time.time()
    # print('DONE (t={:0.2f}s).'.format(toc-tic))
    return p.imgIds, evalImgs


#################################################################
# end of straight copy from pycocotools, just removing the prints
#################################################################