class DetectionValidator(BaseValidator):
"""
A class extending the BaseValidator class for validation based on a detection model.
Example:
```python
from ultralytics.models.yolo.detect import DetectionValidator
args = dict(model='yolov8n.pt', data='coco8.yaml')
validator = DetectionValidator(args=args)
validator()
```
"""
def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
"""Initialize detection model with necessary variables and settings."""
super().__init__(dataloader, save_dir, pbar, args, _callbacks)
self.nt_per_class = None
self.is_coco = False
self.is_lvis = False
self.class_map = None
self.args.task = "detect"
self.metrics = DetMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
self.iouv = torch.linspace(0.5, 0.95, 10) # IoU vector for mAP@0.5:0.95
self.niou = self.iouv.numel()
self.lb = [] # for autolabelling
def preprocess(self, batch):
"""Preprocesses batch of images for YOLO training."""
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)
if self.args.save_hybrid:
height, width = batch["img"].shape[2:]
nb = len(batch["img"])
bboxes = batch["bboxes"] * torch.tensor((width, height, width, height), device=self.device)
self.lb = (
[
torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
for i in range(nb)
]
if self.args.save_hybrid
else []
) # for autolabelling
return batch
def init_metrics(self, model):
"""Initialize evaluation metrics for YOLO."""
val = self.data.get(self.args.split, "") # validation path
self.is_coco = isinstance(val, str) and "coco" in val and val.endswith(f"{os.sep}val2017.txt") # is COCO
self.is_lvis = isinstance(val, str) and "lvis" in val and not self.is_coco # is LVIS
self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(len(model.names)))
self.args.save_json |= (self.is_coco or self.is_lvis) 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, conf=self.args.conf)
self.seen = 0
self.jdict = []
self.stats = dict(tp=[], conf=[], pred_cls=[], target_cls=[])
def get_desc(self):
"""Return a formatted string summarizing class metrics of YOLO model."""
return ("%22s" + "%11s" * 6) % ("Class", "Images", "Instances", "Box(P", "R", "mAP50", "mAP50-95)")
def postprocess(self, preds):
"""Apply Non-maximum suppression to prediction outputs."""
return 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,
)
def _prepare_batch(self, si, batch):
"""Prepares a batch of images and annotations for validation."""
idx = batch["batch_idx"] == si
cls = batch["cls"][idx].squeeze(-1)
bbox = batch["bboxes"][idx]
ori_shape = batch["ori_shape"][si]
imgsz = batch["img"].shape[2:]
ratio_pad = batch["ratio_pad"][si]
if len(cls):
bbox = ops.xywh2xyxy(bbox) * torch.tensor(imgsz, device=self.device)[[1, 0, 1, 0]] # target boxes
ops.scale_boxes(imgsz, bbox, ori_shape, ratio_pad=ratio_pad) # native-space labels
return {"cls": cls, "bbox": bbox, "ori_shape": ori_shape, "imgsz": imgsz, "ratio_pad": ratio_pad}
def _prepare_pred(self, pred, pbatch):
"""Prepares a batch of images and annotations for validation."""
predn = pred.clone()
ops.scale_boxes(
pbatch["imgsz"], predn[:, :4], pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"]
) # native-space pred
return predn
def update_metrics(self, preds, batch):
"""Metrics."""
for si, pred in enumerate(preds):
self.seen += 1
npr = len(pred)
stat = dict(
conf=torch.zeros(0, device=self.device),
pred_cls=torch.zeros(0, device=self.device),
tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
)
pbatch = self._prepare_batch(si, batch)
cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
nl = len(cls)
stat["target_cls"] = cls
if npr == 0:
if nl:
for k in self.stats.keys():
self.stats[k].append(stat[k])
if self.args.plots:
self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
continue
# Predictions
if self.args.single_cls:
pred[:, 5] = 0
predn = self._prepare_pred(pred, pbatch)
stat["conf"] = predn[:, 4]
stat["pred_cls"] = predn[:, 5]
# Evaluate
if nl:
stat["tp"] = self._process_batch(predn, bbox, cls)
if self.args.plots:
self.confusion_matrix.process_batch(predn, bbox, cls)
for k in self.stats.keys():
self.stats[k].append(stat[k])
# 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, pbatch["ori_shape"], file)
def finalize_metrics(self, *args, **kwargs):
"""Set final values for metrics speed and confusion matrix."""
self.metrics.speed = self.speed
self.metrics.confusion_matrix = self.confusion_matrix
def get_stats(self):
"""Returns metrics statistics and results dictionary."""
stats = {k: torch.cat(v, 0).cpu().numpy() for k, v in self.stats.items()} # to numpy
if len(stats) and stats["tp"].any():
self.metrics.process(**stats)
self.nt_per_class = np.bincount(
stats["target_cls"].astype(int), minlength=self.nc
) # number of targets per class
return self.metrics.results_dict
def print_results(self):
"""Prints training/validation set metrics per class."""
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:
for normalize in True, False:
self.confusion_matrix.plot(
save_dir=self.save_dir, names=self.names.values(), normalize=normalize, on_plot=self.on_plot
)
def _process_batch(self, detections, gt_bboxes, gt_cls):
"""
Return correct prediction matrix.
Args:
detections (torch.Tensor): Tensor of shape [N, 6] representing detections.
Each detection is of the format: x1, y1, x2, y2, conf, class.
labels (torch.Tensor): Tensor of shape [M, 5] representing labels.
Each label is of the format: class, x1, y1, x2, y2.
Returns:
(torch.Tensor): Correct prediction matrix of shape [N, 10] for 10 IoU levels.
"""
iou = box_iou(gt_bboxes, detections[:, :4])
return self.match_predictions(detections[:, 5], gt_cls, iou)
def build_dataset(self, img_path, mode="val", batch=None):
"""
Build YOLO Dataset.
Args:
img_path (str): Path to the folder containing images.
mode (str): `train` mode or `val` mode, users are able to customize different augmentations for each mode.
batch (int, optional): Size of batches, this is for `rect`. Defaults to None.
"""
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, stride=self.stride)
def get_dataloader(self, dataset_path, batch_size):
"""Construct and return dataloader."""
dataset = self.build_dataset(dataset_path, batch=batch_size, mode="val")
return build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1) # return dataloader
def plot_val_samples(self, batch, ni):
"""Plot validation image samples."""
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,
on_plot=self.on_plot,
)
def plot_predictions(self, batch, preds, ni):
"""Plots predicted bounding boxes on input images and saves the result."""
plot_images(
batch["img"],
*output_to_target(preds, max_det=self.args.max_det),
paths=batch["im_file"],
fname=self.save_dir / f"val_batch{ni}_pred.jpg",
names=self.names,
on_plot=self.on_plot,
) # pred
def save_one_txt(self, predn, save_conf, shape, file):
"""Save YOLO detections to a txt file in normalized coordinates in a specific format."""
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):
"""Serialize YOLO predictions to COCO json format."""
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])]
+ (1 if self.is_lvis else 0), # index starts from 1 if it's lvis
"bbox": [round(x, 3) for x in b],
"score": round(p[4], 5),
}
)
def eval_json(self, stats):
"""Evaluates YOLO output in JSON format and returns performance statistics."""
if self.args.save_json and (self.is_coco or self.is_lvis) and len(self.jdict):
pred_json = self.save_dir / "predictions.json" # predictions
anno_json = (
self.data["path"]
/ "annotations"
/ ("instances_val2017.json" if self.is_coco else f"lvis_v1_{self.args.split}.json")
) # annotations
pkg = "pycocotools" if self.is_coco else "lvis"
LOGGER.info(f"\nEvaluating {pkg} mAP using {pred_json} and {anno_json}...")
try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
for x in pred_json, anno_json:
assert x.is_file(), f"{x} file not found"
check_requirements("pycocotools>=2.0.6" if self.is_coco else "lvis>=0.5.3")
if self.is_coco:
from pycocotools.coco import COCO # noqa
from pycocotools.cocoeval import COCOeval # noqa
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")
else:
from lvis import LVIS, LVISEval
anno = LVIS(str(anno_json)) # init annotations api
pred = anno._load_json(str(pred_json)) # init predictions api (must pass string, not Path)
eval = LVISEval(anno, pred, "bbox")
eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files] # images to eval
eval.evaluate()
eval.accumulate()
eval.summarize()
if self.is_lvis:
eval.print_results() # explicitly call print_results
# update mAP50-95 and mAP50
stats[self.metrics.keys[-1]], stats[self.metrics.keys[-2]] = (
eval.stats[:2] if self.is_coco else [eval.results["AP50"], eval.results["AP"]]
)
except Exception as e:
LOGGER.warning(f"{pkg} unable to run: {e}")
return stats