You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
260 lines
12 KiB
260 lines
12 KiB
# Ultralytics YOLO 🚀, GPL-3.0 license
|
|
|
|
import os
|
|
from multiprocessing.pool import ThreadPool
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import torch
|
|
import torch.nn.functional as F
|
|
|
|
from ultralytics.yolo.utils import DEFAULT_CFG, NUM_THREADS, ops
|
|
from ultralytics.yolo.utils.checks import check_requirements
|
|
from ultralytics.yolo.utils.metrics import ConfusionMatrix, SegmentMetrics, box_iou, mask_iou
|
|
from ultralytics.yolo.utils.plotting import output_to_target, plot_images
|
|
from ultralytics.yolo.v8.detect import DetectionValidator
|
|
|
|
|
|
class SegmentationValidator(DetectionValidator):
|
|
|
|
def __init__(self, dataloader=None, save_dir=None, pbar=None, logger=None, args=None):
|
|
super().__init__(dataloader, save_dir, pbar, logger, args)
|
|
self.args.task = 'segment'
|
|
self.metrics = SegmentMetrics(save_dir=self.save_dir)
|
|
|
|
def preprocess(self, batch):
|
|
batch = super().preprocess(batch)
|
|
batch["masks"] = batch["masks"].to(self.device).float()
|
|
return batch
|
|
|
|
def init_metrics(self, model):
|
|
head = model.model[-1] if self.training else model.model.model[-1]
|
|
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.nc = head.nc
|
|
self.nm = head.nm if hasattr(head, "nm") else 32
|
|
self.names = model.names
|
|
self.metrics.names = self.names
|
|
self.metrics.plot = self.args.plots
|
|
self.confusion_matrix = ConfusionMatrix(nc=self.nc)
|
|
self.plot_masks = []
|
|
self.seen = 0
|
|
self.jdict = []
|
|
self.stats = []
|
|
if self.args.save_json:
|
|
check_requirements('pycocotools>=2.0.6')
|
|
self.process = ops.process_mask_upsample # more accurate
|
|
else:
|
|
self.process = ops.process_mask # faster
|
|
|
|
def get_desc(self):
|
|
return ('%22s' + '%11s' * 10) % ('Class', 'Images', 'Instances', 'Box(P', "R", "mAP50", "mAP50-95)", "Mask(P",
|
|
"R", "mAP50", "mAP50-95)")
|
|
|
|
def postprocess(self, preds):
|
|
p = ops.non_max_suppression(preds[0],
|
|
self.args.conf,
|
|
self.args.iou,
|
|
labels=self.lb,
|
|
multi_label=True,
|
|
agnostic=self.args.single_cls,
|
|
max_det=self.args.max_det,
|
|
nm=self.nm)
|
|
return p, preds[1][-1]
|
|
|
|
def update_metrics(self, preds, batch):
|
|
# Metrics
|
|
for si, (pred, proto) in enumerate(zip(preds[0], preds[1])):
|
|
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_masks = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device) # init
|
|
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_masks, 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
|
|
|
|
# Masks
|
|
midx = [si] if self.args.overlap_mask else idx
|
|
gt_masks = batch["masks"][midx]
|
|
pred_masks = self.process(proto, pred[:, 6:], pred[:, :4], shape=batch["img"][si].shape[1:])
|
|
|
|
# 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
|
|
correct_masks = self._process_batch(predn,
|
|
labelsn,
|
|
pred_masks,
|
|
gt_masks,
|
|
overlap=self.args.overlap_mask,
|
|
masks=True)
|
|
if self.args.plots:
|
|
self.confusion_matrix.process_batch(predn, labelsn)
|
|
|
|
# Append correct_masks, correct_boxes, pconf, pcls, tcls
|
|
self.stats.append((correct_masks, correct_bboxes, pred[:, 4], pred[:, 5], cls.squeeze(-1)))
|
|
|
|
pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
|
|
if self.args.plots and self.batch_i < 3:
|
|
self.plot_masks.append(pred_masks[:15].cpu()) # filter top 15 to plot
|
|
|
|
# Save
|
|
if self.args.save_json:
|
|
pred_masks = ops.scale_image(batch["img"][si].shape[1:],
|
|
pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
|
|
shape,
|
|
ratio_pad=batch["ratio_pad"][si])
|
|
self.pred_to_json(predn, batch["im_file"][si], pred_masks)
|
|
# if self.args.save_txt:
|
|
# save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
|
|
|
|
def _process_batch(self, detections, labels, pred_masks=None, gt_masks=None, overlap=False, masks=False):
|
|
"""
|
|
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
|
|
"""
|
|
if masks:
|
|
if overlap:
|
|
nl = len(labels)
|
|
index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1
|
|
gt_masks = gt_masks.repeat(nl, 1, 1) # shape(1,640,640) -> (n,640,640)
|
|
gt_masks = torch.where(gt_masks == index, 1.0, 0.0)
|
|
if gt_masks.shape[1:] != pred_masks.shape[1:]:
|
|
gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode="bilinear", align_corners=False)[0]
|
|
gt_masks = gt_masks.gt_(0.5)
|
|
iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1))
|
|
else: # boxes
|
|
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 plot_val_samples(self, batch, ni):
|
|
plot_images(batch["img"],
|
|
batch["batch_idx"],
|
|
batch["cls"].squeeze(-1),
|
|
batch["bboxes"],
|
|
batch["masks"],
|
|
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[0], max_det=15),
|
|
torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
|
|
paths=batch["im_file"],
|
|
fname=self.save_dir / f'val_batch{ni}_pred.jpg',
|
|
names=self.names) # pred
|
|
self.plot_masks.clear()
|
|
|
|
def pred_to_json(self, predn, filename, pred_masks):
|
|
# Save one JSON result
|
|
# Example result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
|
|
from pycocotools.mask import encode # noqa
|
|
|
|
def single_encode(x):
|
|
rle = encode(np.asarray(x[:, :, None], order="F", dtype="uint8"))[0]
|
|
rle["counts"] = rle["counts"].decode("utf-8")
|
|
return rle
|
|
|
|
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
|
|
pred_masks = np.transpose(pred_masks, (2, 0, 1))
|
|
with ThreadPool(NUM_THREADS) as pool:
|
|
rles = pool.map(single_encode, pred_masks)
|
|
for i, (p, b) in enumerate(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),
|
|
'segmentation': rles[i]})
|
|
|
|
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
|
|
self.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)
|
|
for i, eval in enumerate([COCOeval(anno, pred, 'bbox'), COCOeval(anno, pred, 'segm')]):
|
|
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()
|
|
idx = i * 4 + 2
|
|
stats[self.metrics.keys[idx + 1]], stats[
|
|
self.metrics.keys[idx]] = eval.stats[:2] # update mAP50-95 and mAP50
|
|
except Exception as e:
|
|
self.logger.warning(f'pycocotools unable to run: {e}')
|
|
return stats
|
|
|
|
|
|
def val(cfg=DEFAULT_CFG, use_python=False):
|
|
model = cfg.model or "yolov8n-seg.pt"
|
|
data = cfg.data or "coco128-seg.yaml"
|
|
|
|
args = dict(model=model, data=data)
|
|
if use_python:
|
|
from ultralytics import YOLO
|
|
YOLO(model).val(**args)
|
|
else:
|
|
validator = SegmentationValidator(args=args)
|
|
validator(model=args['model'])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
val()
|