使用pycocotools对yolov8进行验证，获取APs、APm、APl
使用pycocotools对yolov8进行验证，获取APs、APm、APl
参考：https://blog.csdn.net/qq_43430381/article/details/129024912
用原始val.py生成的prediction.json中，image_id是图象名称，而lableme生成的val_instances.json中，image_id是纯数字，所以需要一致。
原始的val.py文件中
def pred_to_json(self, predn, filename):
stem = Path(filename).stem
image_id = int(stem) if stem.isnumeric() else stem
box = ops.xyxy2xywh(predn[:, :4]) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(predn.tolist(), box.tolist()):
self.jdict.append({
'image_id': image_id,
'category_id': self.class_map[int(p[5])],
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)})
def eval_json(self, stats):
if self.args.save_json and self.is_coco and len(self.jdict):
anno_json = self.data['path'] / 'annotations/instances_val2017.json' # annotations
pred_json = self.save_dir / 'predictions.json' # predictions
LOGGER.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
check_requirements('pycocotools>=2.0.6')
from pycocotools.coco import COCO # noqa
from pycocotools.cocoeval import COCOeval # noqa
for x in anno_json, pred_json:
assert x.is_file(), f'{x} file not found'
anno = COCO(str(anno_json)) # init annotations api
pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path)
eval = COCOeval(anno, pred, 'bbox')
if self.is_coco:
eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval
eval.evaluate()
eval.accumulate()
eval.summarize()
stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2] # update mAP50-95 and mAP50
except Exception as e:
LOGGER.warning(f'pycocotools unable to run: {e}')
return stats
对上面的两个函数进行修改，如下：
def pred_to_json(self, predn,filename):
stem = Path(filename).stem
name = int(stem) if stem.isnumeric() else stem
image_id= int(stem) if stem.isnumeric() else stem
with open('/F/nyj/dataset/wuliao-5k/val/val_json-one/wuliao-5k-val-annotations.json',"r",encoding="utf-8") as f:
load_dict = json.load(f)
for image in load_dict["images"]:
if image['file_name'][:-4] == name:
image_id = image["id"]
box = ops.xyxy2xywh(predn[:, :4]) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(predn.tolist(), box.tolist()):
self.jdict.append({
'image_id': image_id,
'category_id': self.class_map[int(p[5])]+1,
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)})
def eval_json(self, stats):
if self.args.save_json and self.is_coco and len(self.jdict):
anno_json = '/F/nyj/dataset/wuliao-5k/val/val_json-one/wuliao-5k-val-annotations.json' #self.data['path'] / 'annotations/instances_val2017.json' # annotations
pred_json = self.save_dir / 'predictions.json' # predictions
LOGGER.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
check_requirements('pycocotools>=2.0.6')
#if self.coco_evaluate:
from pycocotools.coco import COCO # noqa
from pycocotools.cocoeval import COCOeval # noqa
for x in anno_json, pred_json:
assert x.is_file(), f'{x} file not found'
anno = COCO(str(anno_json)) # init annotations api
pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path)
eval = COCOeval(anno, pred, 'bbox')
ids=[]
if self.is_coco:
for x in dataloader.dataset.im_files:
with open(anno_json,"r",encoding="utf-8") as f:
load_dict = json.load(f)
for x in dataloader.dataset.im_files:
for img in load_dict["images"]:
if img["file_name"]== x.split("/")[-1]:
ids.append(img["id"])
f.close()
#eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.im_files] # image IDs to evaluate
eval.params.imgIds = ids
#if self.is_coco:
#eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval
eval.evaluate()
eval.accumulate()
eval.summarize()
stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2] # update mAP50-95 and mAP50
print(eval.evaluate())
print(eval.accumulate())
print(eval.summarize())
print(stats)
except Exception as e:
LOGGER.warning(f'pycocotools unable to run: {e}')
return stats
需要注意的是，上面的 'category_id': self.class_map[int(p[5])]+1中，末尾需要+1，不然生成的category_id会从0开始，而labelme生成的val_instances.json中，category_id是从1开始
此外，还需要将defalut.yaml文件中，save_json设置为True
这样运行python val.py后，就会生成prediction.json文件，然后再用下面的脚本就能计算coco的指标了
参考https://blog.csdn.net/weixin_44751294/article/details/126580294中的3. 使用coco API评估结果
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
if __name__ == '__main__':
anno_json = '/F/nyj/dataset/wuliao-5k/val/val_json-one/wuliao-5k-val-annotations.json'
pred_json = './detect-wuliao-val/v8m-p2-no-pt-no-mosaic-best/predictions.json'
anno = COCO(anno_json) # init annotations api
pred = anno.loadRes(pred_json) # init predictions api
eval = COCOeval(anno, pred, 'bbox')
eval.evaluate()
eval.accumulate()
eval.summarize()
map, map50 = eval.stats[:2] # update results ([email protected]:0.95, [email protected])
print(eval.stats)
也参考了其他的，但没效果
https://blog.csdn.net/Yang_4881002/article/details/124125811
https://blog.csdn.net/weixin_44751294/article/details/126580294
整体的val.py文件
# Ultralytics YOLO , GPL-3.0 license
import os
from pathlib import Path
import json
import numpy as np
import torch
from ultralytics.yolo.data import build_dataloader
from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
from ultralytics.yolo.engine.validator import BaseValidator
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, colorstr, ops
from ultralytics.yolo.utils.checks import check_requirements
from ultralytics.yolo.utils.metrics import ConfusionMatrix, DetMetrics, box_iou
from ultralytics.yolo.utils.plotting import output_to_target, plot_images
from ultralytics.yolo.utils.torch_utils import de_parallel
class DetectionValidator(BaseValidator):
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None):
super().__init__(dataloader, save_dir, pbar, args)
self.args.task = 'detect'
self.is_coco = False
self.class_map = None
self.metrics = DetMetrics(save_dir=self.save_dir)
self.iouv = torch.linspace(0.5, 0.95, 10) # iou vector for [email protected]:0.95
self.niou = self.iouv.numel()
def preprocess(self, batch):
batch['img'] = batch['img'].to(self.device, non_blocking=True)
batch['img'] = (batch['img'].half() if self.args.half else batch['img'].float()) / 255
for k in ['batch_idx', 'cls', 'bboxes']:
batch[k] = batch[k].to(self.device)
nb = len(batch['img'])
self.lb = [torch.cat([batch['cls'], batch['bboxes']], dim=-1)[batch['batch_idx'] == i]
for i in range(nb)] if self.args.save_hybrid else [] # for autolabelling
return batch
def init_metrics(self, model):
val = self.data.get(self.args.split, '') # validation path
self.is_coco = isinstance(val, str) and val.endswith(f'coco{os.sep}val2017.txt') # is COCO dataset
self.class_map = ops.coco80_to_coco91_class() if self.is_coco else list(range(1000))
self.args.save_json |= self.is_coco and not self.training # run on final val if training COCO
self.names = model.names
self.nc = len(model.names)
self.metrics.names = self.names
self.metrics.plot = self.args.plots
self.confusion_matrix = ConfusionMatrix(nc=self.nc)
self.seen = 0
self.jdict = []
self.stats = []
def get_desc(self):
return ('%22s' + '%11s' * 6) % ('Class', 'Images', 'Instances', 'Box(P', 'R', 'mAP50', 'mAP50-95)')
def postprocess(self, preds):
preds = ops.non_max_suppression(preds,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=True,
agnostic=self.args.single_cls,
max_det=self.args.max_det)
return preds
def update_metrics(self, preds, batch):
# Metrics
for si, pred in enumerate(preds):
idx = batch['batch_idx'] == si
cls = batch['cls'][idx]
bbox = batch['bboxes'][idx]
nl, npr = cls.shape[0], pred.shape[0] # number of labels, predictions
shape = batch['ori_shape'][si]
correct_bboxes = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device) # init
self.seen += 1
if npr == 0:
if nl:
self.stats.append((correct_bboxes, *torch.zeros((2, 0), device=self.device), cls.squeeze(-1)))
if self.args.plots:
self.confusion_matrix.process_batch(detections=None, labels=cls.squeeze(-1))
continue
# Predictions
if self.args.single_cls:
pred[:, 5] = 0
predn = pred.clone()
ops.scale_boxes(batch['img'][si].shape[1:], predn[:, :4], shape,
ratio_pad=batch['ratio_pad'][si]) # native-space pred
# Evaluate
if nl:
height, width = batch['img'].shape[2:]
tbox = ops.xywh2xyxy(bbox) * torch.tensor(
(width, height, width, height), device=self.device) # target boxes
ops.scale_boxes(batch['img'][si].shape[1:], tbox, shape,
ratio_pad=batch['ratio_pad'][si]) # native-space labels
labelsn = torch.cat((cls, tbox), 1) # native-space labels
correct_bboxes = self._process_batch(predn, labelsn)
# TODO: maybe remove these `self.` arguments as they already are member variable
if self.args.plots:
self.confusion_matrix.process_batch(predn, labelsn)
self.stats.append((correct_bboxes, pred[:, 4], pred[:, 5], cls.squeeze(-1))) # (conf, pcls, tcls)
# Save
if self.args.save_json:
self.pred_to_json(predn, batch['im_file'][si])
if self.args.save_txt:
file = self.save_dir / 'labels' / f'{Path(batch["im_file"][si]).stem}.txt'
self.save_one_txt(predn, self.args.save_conf, shape, file)
def finalize_metrics(self, *args, **kwargs):
self.metrics.speed = self.speed
self.metrics.confusion_matrix = self.confusion_matrix
def get_stats(self):
stats = [torch.cat(x, 0).cpu().numpy() for x in zip(*self.stats)] # to numpy
if len(stats) and stats[0].any():
self.metrics.process(*stats)
self.nt_per_class = np.bincount(stats[-1].astype(int), minlength=self.nc) # number of targets per class
return self.metrics.results_dict
def print_results(self):
pf = '%22s' + '%11i' * 2 + '%11.3g' * len(self.metrics.keys) # print format
LOGGER.info(pf % ('all', self.seen, self.nt_per_class.sum(), *self.metrics.mean_results()))
if self.nt_per_class.sum() == 0:
LOGGER.warning(
f'WARNING ⚠️ no labels found in {self.args.task} set, can not compute metrics without labels')
# Print results per class
if self.args.verbose and not self.training and self.nc > 1 and len(self.stats):
for i, c in enumerate(self.metrics.ap_class_index):
LOGGER.info(pf % (self.names[c], self.seen, self.nt_per_class[c], *self.metrics.class_result(i)))
if self.args.plots:
self.confusion_matrix.plot(save_dir=self.save_dir, names=list(self.names.values()))
def _process_batch(self, detections, labels):
"""
Return correct prediction matrix
Arguments:
detections (array[N, 6]), x1, y1, x2, y2, conf, class
labels (array[M, 5]), class, x1, y1, x2, y2
Returns:
correct (array[N, 10]), for 10 IoU levels
"""
iou = box_iou(labels[:, 1:], detections[:, :4])
correct = np.zeros((detections.shape[0], self.iouv.shape[0])).astype(bool)
correct_class = labels[:, 0:1] == detections[:, 5]
for i in range(len(self.iouv)):
x = torch.where((iou >= self.iouv[i]) & correct_class) # IoU > threshold and classes match
if x[0].shape[0]:
matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]),
1).cpu().numpy() # [label, detect, iou]
if x[0].shape[0] > 1:
matches = matches[matches[:, 2].argsort()[::-1]]
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
# matches = matches[matches[:, 2].argsort()[::-1]]
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
correct[matches[:, 1].astype(int), i] = True
return torch.tensor(correct, dtype=torch.bool, device=detections.device)
def get_dataloader(self, dataset_path, batch_size):
# TODO: manage splits differently
# calculate stride - check if model is initialized
gs = max(int(de_parallel(self.model).stride if self.model else 0), 32)
return create_dataloader(path=dataset_path,
imgsz=self.args.imgsz,
batch_size=batch_size,
stride=gs,
hyp=vars(self.args),
cache=False,
pad=0.5,
rect=self.args.rect,
workers=self.args.workers,
prefix=colorstr(f'{self.args.mode}: '),
shuffle=False,
seed=self.args.seed)[0] if self.args.v5loader else \
build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, names=self.data['names'],
mode='val')[0]
def plot_val_samples(self, batch, ni):
plot_images(batch['img'],
batch['batch_idx'],
batch['cls'].squeeze(-1),
batch['bboxes'],
paths=batch['im_file'],
fname=self.save_dir / f'val_batch{ni}_labels.jpg',
names=self.names)
def plot_predictions(self, batch, preds, ni):
plot_images(batch['img'],
*output_to_target(preds, max_det=15),
paths=batch['im_file'],
fname=self.save_dir / f'val_batch{ni}_pred.jpg',
names=self.names) # pred
def save_one_txt(self, predn, save_conf, shape, file):
gn = torch.tensor(shape)[[1, 0, 1, 0]] # normalization gain whwh
for *xyxy, conf, cls in predn.tolist():
xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(file, 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
def pred_to_json(self, predn,filename):
stem = Path(filename).stem
name = int(stem) if stem.isnumeric() else stem
#name = int(path.stem) if path.stem.isnumeric() else path.stem
with open('/F/nyj/dataset/wuliao-5k/val/val_json-one/wuliao-5k-val-annotations.json',"r",encoding="utf-8") as f:
load_dict = json.load(f)
for image in load_dict["images"]:
if image['file_name'][:-4] == name:
image_id = image["id"]
box = ops.xyxy2xywh(predn[:, :4]) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(predn.tolist(), box.tolist()):
self.jdict.append({
'image_id': image_id,
'category_id': self.class_map[int(p[5])]+1,
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)})
def eval_json(self, stats):
if self.args.save_json and self.is_coco and len(self.jdict):
anno_json = '/F/nyj/dataset/wuliao-5k/val/val_json-one/wuliao-5k-val-annotations.json' #self.data['path'] / 'annotations/instances_val2017.json' # annotations
pred_json = self.save_dir / 'predictions.json' # predictions
LOGGER.info(f'\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...')
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
check_requirements('pycocotools>=2.0.6')
#if self.coco_evaluate:
from pycocotools.coco import COCO # noqa
from pycocotools.cocoeval import COCOeval # noqa
for x in anno_json, pred_json:
assert x.is_file(), f'{x} file not found'
anno = COCO(str(anno_json)) # init annotations api
pred = anno.loadRes(str(pred_json)) # init predictions api (must pass string, not Path)
eval = COCOeval(anno, pred, 'bbox')
ids=[]
if self.is_coco:
for x in dataloader.dataset.im_files:
with open(anno_json,"r",encoding="utf-8") as f:
load_dict = json.load(f)
for x in dataloader.dataset.im_files:
for img in load_dict["images"]:
if img["file_name"]== x.split("/")[-1]:
ids.append(img["id"])
f.close()
#eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.im_files] # image IDs to evaluate
eval.params.imgIds = ids
#if self.is_coco:
#eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval
eval.evaluate()
eval.accumulate()
eval.summarize()
stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = eval.stats[:2] # update mAP50-95 and mAP50
print(eval.evaluate())
print(eval.accumulate())
print(eval.summarize())
print(stats)
except Exception as e:
LOGGER.warning(f'pycocotools unable to run: {e}')
return stats
def val(cfg=DEFAULT_CFG, use_python=False):
model = cfg.model or 'yolov8n.pt'
data = cfg.data or 'coco128.yaml'
args = dict(model=model, data=data)
if use_python:
from ultralytics import YOLO
YOLO(model).val(**args)
else:
validator = DetectionValidator(args=args)
validator(model=args['model'])
if __name__ == '__main__':
val()
但在验证hole数据集时，又不需要改动，直接用原始的val.py即可