Spaces:
Running
on
T4
Running
on
T4
File size: 2,950 Bytes
a2b0f6f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# Ultralytics YOLO 🚀, AGPL-3.0 license
from copy import copy
import torch
from ultralytics.nn.tasks import RTDETRDetectionModel
from ultralytics.yolo.utils import DEFAULT_CFG, RANK, colorstr
from ultralytics.yolo.v8.detect import DetectionTrainer
from .val import RTDETRDataset, RTDETRValidator
class RTDETRTrainer(DetectionTrainer):
def get_model(self, cfg=None, weights=None, verbose=True):
"""Return a YOLO detection model."""
model = RTDETRDetectionModel(cfg, nc=self.data['nc'], verbose=verbose and RANK == -1)
if weights:
model.load(weights)
return model
def build_dataset(self, img_path, mode='val', batch=None):
"""Build RTDETR 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 RTDETRDataset(
img_path=img_path,
imgsz=self.args.imgsz,
batch_size=batch,
augment=mode == 'train', # no augmentation
hyp=self.args,
rect=False, # no rect
cache=self.args.cache or None,
prefix=colorstr(f'{mode}: '),
data=self.data)
def get_validator(self):
"""Returns a DetectionValidator for RTDETR model validation."""
self.loss_names = 'giou_loss', 'cls_loss', 'l1_loss'
return RTDETRValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))
def preprocess_batch(self, batch):
"""Preprocesses a batch of images by scaling and converting to float."""
batch = super().preprocess_batch(batch)
bs = len(batch['img'])
batch_idx = batch['batch_idx']
gt_bbox, gt_class = [], []
for i in range(bs):
gt_bbox.append(batch['bboxes'][batch_idx == i].to(batch_idx.device))
gt_class.append(batch['cls'][batch_idx == i].to(device=batch_idx.device, dtype=torch.long))
return batch
def train(cfg=DEFAULT_CFG, use_python=False):
"""Train and optimize RTDETR model given training data and device."""
model = 'rtdetr-l.yaml'
data = cfg.data or 'coco128.yaml' # or yolo.ClassificationDataset("mnist")
device = cfg.device if cfg.device is not None else ''
# NOTE: F.grid_sample which is in rt-detr does not support deterministic=True
# NOTE: amp training causes nan outputs and end with error while doing bipartite graph matching
args = dict(model=model,
data=data,
device=device,
imgsz=640,
exist_ok=True,
batch=4,
deterministic=False,
amp=False)
trainer = RTDETRTrainer(overrides=args)
trainer.train()
if __name__ == '__main__':
train()
|