Tùy chỉnh Trainer#

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer

class CustomTrainer(DetectionTrainer):
    """A custom trainer that extends DetectionTrainer with additional functionality."""

    # Add your customizations here

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=10, trainer=CustomTrainer)

import numpy as np

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer
from ultralytics.utils import LOGGER

class MetricsTrainer(DetectionTrainer):
    """Custom trainer that computes and logs F1 score at the end of each epoch."""

    def validate(self):
        """Run validation and compute per-class F1 scores."""
        metrics, fitness = super().validate()
        if metrics is None:
            return metrics, fitness

        if hasattr(self.validator, "metrics") and hasattr(self.validator.metrics, "box"):
            box = self.validator.metrics.box
            f1_per_class = box.f1
            class_indices = box.ap_class_index
            names = self.validator.names

            valid_f1 = f1_per_class[f1_per_class > 0]
            mean_f1 = np.mean(valid_f1) if len(valid_f1) > 0 else 0.0

            LOGGER.info(f"Mean F1 Score: {mean_f1:.4f}")
            per_class_str = [
                f"{names[i]}: {f1_per_class[j]:.3f}" for j, i in enumerate(class_indices) if f1_per_class[j] > 0
            ]
            LOGGER.info(f"Per-class F1: {per_class_str}")

        return metrics, fitness

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=5, trainer=MetricsTrainer)

import torch
from torch import nn

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer
from ultralytics.nn.tasks import DetectionModel
from ultralytics.utils import RANK
from ultralytics.utils.loss import E2ELoss, v8DetectionLoss

class WeightedDetectionLoss(v8DetectionLoss):
    """Detection loss with class weights applied to BCE classification loss."""

    def __init__(self, model, class_weights=None, tal_topk=10, tal_topk2=None):
        """Initialize loss with optional per-class weights for BCE."""
        super().__init__(model, tal_topk=tal_topk, tal_topk2=tal_topk2)
        if class_weights is not None:
            self.bce = nn.BCEWithLogitsLoss(
                pos_weight=class_weights.to(self.device),
                reduction="none",
            )

class WeightedE2ELoss(E2ELoss):
    """E2E Loss with class weights for YOLO26."""

    def __init__(self, model, class_weights=None):
        """Initialize E2E loss with weighted detection loss."""

        def weighted_loss_fn(model, tal_topk=10, tal_topk2=None):
            return WeightedDetectionLoss(model, class_weights=class_weights, tal_topk=tal_topk, tal_topk2=tal_topk2)

        super().__init__(model, loss_fn=weighted_loss_fn)

class WeightedDetectionModel(DetectionModel):
    """Detection model that uses class-weighted loss."""

    def init_criterion(self):
        """Initialize weighted loss criterion with per-class weights."""
        class_weights = torch.ones(self.nc)
        class_weights[0] = 2.0  # upweight class 0
        class_weights[1] = 3.0  # upweight rare class 1
        return WeightedE2ELoss(self, class_weights=class_weights)

class WeightedTrainer(DetectionTrainer):
    """Trainer that returns a WeightedDetectionModel."""

    def get_model(self, cfg=None, weights=None, verbose=True):
        """Return a WeightedDetectionModel."""
        model = WeightedDetectionModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1)
        if weights:
            model.load(weights)
        return model

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=10, trainer=WeightedTrainer)

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer

class CustomSaveTrainer(DetectionTrainer):
    """Trainer that saves the best model based on mAP@0.5 instead of default fitness."""

    def validate(self):
        """Override fitness to use mAP@0.5 for best model selection."""
        metrics, fitness = super().validate()
        if metrics:
            fitness = metrics.get("metrics/mAP50(B)", fitness)
            if self.best_fitness is None or fitness > self.best_fitness:
                self.best_fitness = fitness
        return metrics, fitness

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=20, trainer=CustomSaveTrainer)

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer
from ultralytics.utils import LOGGER

FREEZE_EPOCHS = 5

def unfreeze_backbone(trainer):
    """Callback to unfreeze all layers after FREEZE_EPOCHS."""
    if trainer.epoch == FREEZE_EPOCHS:
        LOGGER.info(f"Epoch {trainer.epoch}: Unfreezing all layers for fine-tuning")
        for name, param in trainer.model.named_parameters():
            if not param.requires_grad:
                param.requires_grad = True
                LOGGER.info(f"  Unfroze: {name}")
        trainer.freeze_layer_names = [".dfl"]

class FreezingTrainer(DetectionTrainer):
    """Trainer with backbone freezing for first N epochs."""

    def __init__(self, *args, **kwargs):
        """Initialize and register the unfreeze callback."""
        super().__init__(*args, **kwargs)
        self.add_callback("on_train_epoch_start", unfreeze_backbone)

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=20, freeze=10, trainer=FreezingTrainer)

import torch

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionTrainer
from ultralytics.utils import LOGGER
from ultralytics.utils.torch_utils import unwrap_model

class PerLayerLRTrainer(DetectionTrainer):
    """Trainer with different learning rates for backbone and head."""

    def build_optimizer(self, model, name="auto", lr=0.001, momentum=0.9, decay=1e-5, iterations=1e5):
        """Build optimizer with separate learning rates for backbone and head."""
        backbone_params = []
        head_params = []

        unwrapped = unwrap_model(model)
        backbone_len = len(unwrapped.yaml["backbone"])  # YOLO26 backbone spans layers 0-10 (C2PSA at layer 10)

        for k, v in unwrapped.named_parameters():
            if not v.requires_grad:
                continue
            is_backbone = any(k.startswith(f"model.{i}.") for i in range(backbone_len))
            if is_backbone:
                backbone_params.append(v)
            else:
                head_params.append(v)

        backbone_lr = lr * 0.1

        optimizer = torch.optim.AdamW(
            [
                {"params": backbone_params, "lr": backbone_lr, "weight_decay": decay},
                {"params": head_params, "lr": lr, "weight_decay": decay},
            ],
        )

        LOGGER.info(
            f"PerLayerLR optimizer: backbone ({len(backbone_params)} params, lr={backbone_lr}) "
            f"| head ({len(head_params)} params, lr={lr})"
        )
        return optimizer

model = YOLO("yolo26n.pt")
model.train(data="coco8.yaml", epochs=20, trainer=PerLayerLRTrainer)

import torch
from torch import nn

from ultralytics import RTDETR
from ultralytics.models.rtdetr.train import RTDETRTrainer
from ultralytics.utils import LOGGER, colorstr
from ultralytics.utils.torch_utils import unwrap_model

class RTDETRBackboneLRTrainer(RTDETRTrainer):
    """RT-DETR trainer with a lower learning rate for backbone parameters."""

    backbone_lr_ratio = 0.1  # backbone learning rate as a fraction of head learning rate

    def build_optimizer(self, model, name="auto", lr=0.001, momentum=0.9, decay=1e-5, iterations=1e5):
        """Build an AdamW optimizer with six param groups: head and backbone x {weight, bn, bias}."""
        # Resolve optimizer name; "auto" maps to AdamW with RT-DETR-style defaults
        canonical = {"Adam", "Adamax", "AdamW", "NAdam", "RAdam", "auto"}
        name = {x.lower(): x for x in canonical}.get(name.lower(), name)
        if name == "auto":
            name, lr, momentum = "AdamW", 1e-4, 0.9
        self.args.warmup_bias_lr = 0.0  # RT-DETR warms biases from 0, unlike YOLO's 0.1
        if name not in {"Adam", "Adamax", "AdamW", "NAdam", "RAdam"}:
            raise NotImplementedError(f"This trainer only supports AdamW-family optimizers; got {name}")

        # Identify backbone parameters from model.yaml and route each param into a (section, kind) group
        unwrapped = unwrap_model(model)
        backbone_len = len(unwrapped.yaml["backbone"])
        norm_types = tuple(v for k, v in nn.__dict__.items() if "Norm" in k)
        groups = {f"{s}_{k}": [] for s in ("head", "backbone") for k in ("weight", "bn", "bias")}

        for module_name, module in unwrapped.named_modules():
            for param_name, param in module.named_parameters(recurse=False):
                if not param.requires_grad:
                    continue
                fullname = f"{module_name}.{param_name}" if module_name else param_name
                parts = fullname.split(".")
                section = (
                    "backbone"
                    if len(parts) > 1 and parts[0] == "model" and parts[1].isdigit() and int(parts[1]) < backbone_len
                    else "head"
                )
                if "bias" in param_name:
                    kind = "bias"
                elif isinstance(module, norm_types) or "logit_scale" in fullname:
                    kind = "bn"
                else:
                    kind = "weight"
                groups[f"{section}_{kind}"].append(param)

        # Build the optimizer with per-group lr and weight decay; backbone groups use lr * backbone_lr_ratio
        backbone_lr = lr * self.backbone_lr_ratio
        param_groups = [
            {"params": groups["head_weight"], "lr": lr, "weight_decay": decay, "param_group": "weight"},
            {"params": groups["head_bn"], "lr": lr, "weight_decay": 0.0, "param_group": "bn"},
            {"params": groups["head_bias"], "lr": lr, "weight_decay": 0.0, "param_group": "bias"},
            {"params": groups["backbone_weight"], "lr": backbone_lr, "weight_decay": decay, "param_group": "weight"},
            {"params": groups["backbone_bn"], "lr": backbone_lr, "weight_decay": 0.0, "param_group": "bn"},
            {"params": groups["backbone_bias"], "lr": backbone_lr, "weight_decay": 0.0, "param_group": "bias"},
        ]
        param_groups = [pg for pg in param_groups if pg["params"]]  # drop empty groups
        optimizer = getattr(torch.optim, name)(param_groups, betas=(momentum, 0.999))

        LOGGER.info(
            f"{colorstr('optimizer:')} {name}(lr={lr}, backbone_lr={backbone_lr}) with parameter groups\n"
            f"  Head:     {len(groups['head_bn'])} bn, {len(groups['head_weight'])} weight(decay={decay}), "
            f"{len(groups['head_bias'])} bias (lr={lr})\n"
            f"  Backbone: {len(groups['backbone_bn'])} bn, {len(groups['backbone_weight'])} weight(decay={decay}), "
            f"{len(groups['backbone_bias'])} bias (lr={backbone_lr})"
        )
        return optimizer

model = RTDETR("rtdetr-l.pt")
model.train(data="coco8.yaml", epochs=20, trainer=RTDETRBackboneLRTrainer)

from torch import nn

from ultralytics import RTDETR
from ultralytics.models.rtdetr.train import RTDETRTrainer

class SyncBNTrainer(RTDETRTrainer):
    """RT-DETR trainer that converts BatchNorm to SyncBatchNorm for multi-GPU training."""

    def set_model_attributes(self):
        """Run the parent setup, then convert BN to SyncBatchNorm when training on multiple GPUs."""
        super().set_model_attributes()
        if self.world_size > 1:
            self.model = nn.SyncBatchNorm.convert_sync_batchnorm(self.model)

model = RTDETR("rtdetr-l.pt")
model.train(data="coco8.yaml", epochs=20, device=[0, 1], trainer=SyncBNTrainer)

import torch

from ultralytics import RTDETR
from ultralytics.models.rtdetr.train import RTDETRTrainer

class CustomClipTrainer(RTDETRTrainer):
    """RT-DETR trainer with configurable gradient clipping."""

    clip_grad_norm = 0.1  # max gradient norm; set to 0 to disable clipping

    def optimizer_step(self):
        """Run an optimizer step with a configurable gradient-norm clip."""
        self.scaler.unscale_(self.optimizer)
        if self.clip_grad_norm > 0:
            torch.nn.utils.clip_grad_norm_(self.model.parameters(), max_norm=self.clip_grad_norm)
        self.scaler.step(self.optimizer)
        self.scaler.update()
        self.optimizer.zero_grad()
        if self.ema:
            self.ema.update(self.model)

model = RTDETR("rtdetr-l.pt")
model.train(data="coco8.yaml", epochs=20, trainer=CustomClipTrainer)