Source code for mmdet.evaluation.metrics.faster_coco_metric
# Copyright (c) OpenMMLab. All rights reserved.
# type: ignore
"""Metric object to use in mmdetection framework to calculate mAP etc."""
import itertools
import os.path as osp
import tempfile
from collections import OrderedDict
from typing import Any, Dict, List, Sequence
import numpy as np
import torch
from faster_coco_eval import COCO, COCOeval_faster
from mmengine.fileio import load
from mmengine.logging import MMLogger
from terminaltables import AsciiTable
from mmdet.evaluation.metrics import CocoMetric
from mmdet.registry import METRICS
from mmdet.structures.mask import encode_mask_results
def convert_gt_samples(gt_instances: dict) -> List[Dict[str, Any]]:
converted = []
if 'masks' in gt_instances:
zipped = zip(gt_instances['bboxes'], gt_instances['labels'],
gt_instances['masks'])
else:
zipped = zip(gt_instances['bboxes'], gt_instances['labels'])
# FIXME masks
for instance in zipped:
bbox, label = instance[:2] # noqa: PLR2004
mask = None
if len(instance) > 2: # noqa: PLR2004
mask = instance[-1]
inst = {'bbox': list(bbox.cpu().numpy()), 'bbox_label': int(label)}
if mask is not None:
inst['mask'] = encode_mask_results([mask])[0]
converted.append(inst)
return converted
[docs]@METRICS.register_module()
class FasterCocoMetric(CocoMetric):
# copied from CocoMetric, only 'instances' is renamed to 'gt_instances'
[docs] def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None:
"""Process one batch of data samples and predictions. The processed
results should be stored in ``self.results``, which will be used to
compute the metrics when all batches have been processed.
Args:
data_batch (dict): A batch of data from the dataloader.
data_samples (Sequence[dict]): A batch of data samples that
contain annotations and predictions.
"""
for data_sample in data_samples:
result = dict()
pred = data_sample['pred_instances']
result['img_id'] = data_sample['img_id']
result['bboxes'] = pred['bboxes'].cpu().numpy()
result['scores'] = pred['scores'].cpu().numpy()
result['labels'] = pred['labels'].cpu().numpy()
# encode mask to RLE
if 'masks' in pred:
result['masks'] = (
encode_mask_results(
pred['masks'].detach().cpu().numpy()) if isinstance(
pred['masks'], torch.Tensor) else pred['masks'])
# some detectors use different scores for bbox and mask
if 'mask_scores' in pred:
result['mask_scores'] = pred['mask_scores'].cpu().numpy()
# parse gt
gt = dict()
gt['width'] = data_sample['ori_shape'][1]
gt['height'] = data_sample['ori_shape'][0]
gt['img_id'] = data_sample['img_id']
if self._coco_api is None:
assert 'gt_instances' in data_sample, (
'ground truth is required for evaluation when '
'`ann_file` is not provided')
gt['anns'] = convert_gt_samples(data_sample['gt_instances'])
# add converted result to the results list
self.results.append((gt, result))
# copied from CocoMetric, only 'CocoEval' is replaced by 'CocoEval_faster'
[docs] def compute_metrics(
self, results: list) -> Dict[str, float]: # noqa: PLR0912, PLR0915
"""Compute the metrics from processed results.
Args:
results (list): The processed results of each batch.
Returns:
Dict[str, float]: The computed metrics. The keys are the names of
the metrics, and the values are corresponding results.
"""
logger: MMLogger = MMLogger.get_current_instance()
# split gt and prediction list
gts, preds = zip(*results)
tmp_dir = None
if self.outfile_prefix is None:
tmp_dir = tempfile.TemporaryDirectory()
outfile_prefix = osp.join(tmp_dir.name, 'results')
else:
outfile_prefix = self.outfile_prefix
if self._coco_api is None:
# use converted gt json file to initialize coco api
logger.info('Converting ground truth to coco format...')
coco_json_path = self.gt_to_coco_json(
gt_dicts=gts, outfile_prefix=outfile_prefix)
self._coco_api = COCO(coco_json_path)
# handle lazy init
if self.cat_ids is None:
self.cat_ids = self._coco_api.getCatIds(
catNms=self.dataset_meta['classes'])
if self.img_ids is None:
self.img_ids = self._coco_api.getImgIds()
# convert predictions to coco format and dump to json file
result_files = self.results2json(preds, outfile_prefix)
eval_results = OrderedDict()
if self.format_only:
logger.info('results are saved in '
f'{osp.dirname(outfile_prefix)}')
return eval_results
for metric in self.metrics:
logger.info(f'Evaluating {metric}...')
# TODO: May refactor fast_eval_recall to an independent metric?
# fast eval recall
if metric == 'proposal_fast':
ar = self.fast_eval_recall(
preds, self.proposal_nums, self.iou_thrs, logger=logger)
log_msg = []
for i, num in enumerate(self.proposal_nums):
eval_results[f'AR@{num}'] = ar[i]
log_msg.append(f'\nAR@{num}\t{ar[i]:.4f}')
log_msg = ''.join(log_msg)
logger.info(log_msg)
continue
# evaluate proposal, bbox and segm
iou_type = 'bbox' if metric == 'proposal' else metric
if metric not in result_files:
raise KeyError(f'{metric} is not in results')
try:
predictions = load(result_files[metric])
if iou_type == 'segm':
# Refer to https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocotools/coco.py#L331 # noqa
# When evaluating mask AP, if the results contain bbox,
# cocoapi will use the box area instead of the mask area
# for calculating the instance area. Though the overall AP
# is not affected, this leads to different
# small/medium/large mask AP results.
for x in predictions:
x.pop('bbox')
coco_dt = self._coco_api.loadRes(predictions)
except IndexError:
logger.error(
'The testing results of the whole dataset is empty.')
break
coco_eval = COCOeval_faster(self._coco_api, coco_dt, iou_type)
coco_eval.params.catIds = self.cat_ids
coco_eval.params.imgIds = self.img_ids
coco_eval.params.maxDets = list(self.proposal_nums)
coco_eval.params.iouThrs = self.iou_thrs
# mapping of cocoEval.stats
coco_metric_names = {
'mAP': 0,
'mAP_50': 1,
'mAP_75': 2,
'mAP_s': 3,
'mAP_m': 4,
'mAP_l': 5,
'AR@100': 6,
'AR@300': 7,
'AR@1000': 8,
'AR_s@1000': 9,
'AR_m@1000': 10,
'AR_l@1000': 11,
}
metric_items = self.metric_items
if metric_items is not None:
for metric_item in metric_items:
if metric_item not in coco_metric_names:
raise KeyError(
f'metric item "{metric_item}" is not supported')
if metric == 'proposal':
coco_eval.params.useCats = 0
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
if metric_items is None:
metric_items = [
'AR@100', 'AR@300', 'AR@1000', 'AR_s@1000',
'AR_m@1000', 'AR_l@1000'
]
for item in metric_items:
val = float(
f'{coco_eval.stats[coco_metric_names[item]]:.3f}')
eval_results[item] = val
else:
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
if self.classwise: # Compute per-category AP
# Compute per-category AP
# from https://github.com/facebookresearch/detectron2/
precisions = coco_eval.eval['precision']
# precision: (iou, recall, cls, area range, max dets)
assert len(self.cat_ids) == precisions.shape[2]
results_per_category = []
for idx, cat_id in enumerate(self.cat_ids):
t = []
# area range index 0: all area ranges
# max dets index -1: typically 100 per image
nm = self._coco_api.loadCats(cat_id)[0]
precision = precisions[:, :, idx, 0, -1]
precision = precision[precision > -1]
if precision.size:
ap = np.mean(precision)
else:
ap = float('nan')
t.append(f'{nm["name"]}')
t.append(f'{round(ap, 3)}')
eval_results[f'{nm["name"]}_precision'] = round(ap, 3)
# indexes of IoU @50 and @75
for iou in [0, 5]:
precision = precisions[iou, :, idx, 0, -1]
precision = precision[precision > -1]
if precision.size:
ap = np.mean(precision)
else:
ap = float('nan')
t.append(f'{round(ap, 3)}')
# indexes of area of small, median and large
for area in [1, 2, 3]:
precision = precisions[:, :, idx, area, -1]
precision = precision[precision > -1]
if precision.size:
ap = np.mean(precision)
else:
ap = float('nan')
t.append(f'{round(ap, 3)}')
results_per_category.append(tuple(t))
num_columns = len(results_per_category[0])
results_flatten = list(
itertools.chain(*results_per_category))
headers = [
'category', 'mAP', 'mAP_50', 'mAP_75', 'mAP_s',
'mAP_m', 'mAP_l'
]
results_2d = itertools.zip_longest(*[
results_flatten[i::num_columns]
for i in range(num_columns)
])
table_data = [headers]
table_data += [result for result in results_2d]
table = AsciiTable(table_data)
logger.info('\n' + table.table)
if metric_items is None:
metric_items = [
'mAP', 'mAP_50', 'mAP_75', 'mAP_s', 'mAP_m', 'mAP_l'
]
for metric_item in metric_items:
key = f'{metric}_{metric_item}'
val = coco_eval.stats[coco_metric_names[metric_item]]
eval_results[key] = float(f'{round(val, 3)}')
ap = coco_eval.stats[:6]
logger.info(f'{metric}_mAP_copypaste: {ap[0]:.3f} '
f'{ap[1]:.3f} {ap[2]:.3f} {ap[3]:.3f} '
f'{ap[4]:.3f} {ap[5]:.3f}')
if tmp_dir is not None:
tmp_dir.cleanup()
return eval_results