xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.12 - Hydra removal (#506)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Pronoy Mandal <lukex9442@gmail.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
This commit is contained in:
Glenn Jocher
2023-01-21 00:45:19 +01:00
committed by GitHub
parent 6eec39162a
commit c5fccc3fc4
37 changed files with 395 additions and 469 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ultralytics/yolo/v8/__init__.py
View File

@ -1,6 +1,5 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
from ultralytics.yolo.configs import hydra_patch # noqa (patch hydra CLI)
from ultralytics.yolo.v8 import classify, detect, segment
__all__ = ["classify", "segment", "detect"]

6
ultralytics/yolo/v8/classify/predict.py
View File

@ -1,11 +1,10 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import hydra
import torch
from ultralytics.yolo.engine.predictor import BasePredictor
from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import DEFAULT_CONFIG, ROOT, is_git_directory
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, is_git_directory
from ultralytics.yolo.utils.plotting import Annotator
@ -64,8 +63,7 @@ class ClassificationPredictor(BasePredictor):
return log_string
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def predict(cfg):
def predict(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n-cls.pt" # or "resnet18"
cfg.source = cfg.source if cfg.source is not None else ROOT / "assets" if is_git_directory() \
else "https://ultralytics.com/images/bus.jpg"

10
ultralytics/yolo/v8/classify/train.py
View File

@ -1,6 +1,5 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import hydra
import torch
import torchvision
@ -8,13 +7,13 @@ from ultralytics.nn.tasks import ClassificationModel, attempt_load_one_weight
from ultralytics.yolo import v8
from ultralytics.yolo.data import build_classification_dataloader
from ultralytics.yolo.engine.trainer import BaseTrainer
from ultralytics.yolo.utils import DEFAULT_CONFIG
from ultralytics.yolo.utils import DEFAULT_CFG
from ultralytics.yolo.utils.torch_utils import strip_optimizer
class ClassificationTrainer(BaseTrainer):
def __init__(self, config=DEFAULT_CONFIG, overrides=None):
def __init__(self, config=DEFAULT_CFG, overrides=None):
if overrides is None:
overrides = {}
overrides["task"] = "classify"
@ -136,8 +135,7 @@ class ClassificationTrainer(BaseTrainer):
# self.run_callbacks('on_fit_epoch_end')
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def train(cfg):
def train(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n-cls.pt" # or "resnet18"
cfg.data = cfg.data or "mnist160" # or yolo.ClassificationDataset("mnist")
@ -152,7 +150,7 @@ def train(cfg):
# trainer.train()
from ultralytics import YOLO
model = YOLO(cfg.model)
model.train(**cfg)
model.train(**vars(cfg))
if __name__ == "__main__":

7
ultralytics/yolo/v8/classify/val.py
View File

@ -1,10 +1,8 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import hydra
from ultralytics.yolo.data import build_classification_dataloader
from ultralytics.yolo.engine.validator import BaseValidator
from ultralytics.yolo.utils import DEFAULT_CONFIG
from ultralytics.yolo.utils import DEFAULT_CFG
from ultralytics.yolo.utils.metrics import ClassifyMetrics
@ -46,8 +44,7 @@ class ClassificationValidator(BaseValidator):
self.logger.info(pf % ("all", self.metrics.top1, self.metrics.top5))
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def val(cfg):
def val(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n-cls.pt" # or "resnet18"
cfg.data = cfg.data or "imagenette160"
validator = ClassificationValidator(args=cfg)

6
ultralytics/yolo/v8/detect/predict.py
View File

@ -1,11 +1,10 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import hydra
import torch
from ultralytics.yolo.engine.predictor import BasePredictor
from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import DEFAULT_CONFIG, ROOT, is_git_directory, ops
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, is_git_directory, ops
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
@ -81,8 +80,7 @@ class DetectionPredictor(BasePredictor):
return log_string
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def predict(cfg):
def predict(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n.pt"
cfg.source = cfg.source if cfg.source is not None else ROOT / "assets" if is_git_directory() \
else "https://ultralytics.com/images/bus.jpg"

10
ultralytics/yolo/v8/detect/train.py
View File

@ -2,7 +2,6 @@
from copy import copy
import hydra
import torch
import torch.nn as nn
@ -11,7 +10,7 @@ from ultralytics.yolo import v8
from ultralytics.yolo.data import build_dataloader
from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
from ultralytics.yolo.engine.trainer import BaseTrainer
from ultralytics.yolo.utils import DEFAULT_CONFIG, colorstr
from ultralytics.yolo.utils import DEFAULT_CFG, colorstr
from ultralytics.yolo.utils.loss import BboxLoss
from ultralytics.yolo.utils.ops import xywh2xyxy
from ultralytics.yolo.utils.plotting import plot_images, plot_results
@ -30,7 +29,7 @@ class DetectionTrainer(BaseTrainer):
imgsz=self.args.imgsz,
batch_size=batch_size,
stride=gs,
hyp=dict(self.args),
hyp=vars(self.args),
augment=mode == "train",
cache=self.args.cache,
pad=0 if mode == "train" else 0.5,
@ -195,8 +194,7 @@ class Loss:
return loss.sum() * batch_size, loss.detach() # loss(box, cls, dfl)
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def train(cfg):
def train(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n.pt"
cfg.data = cfg.data or "coco128.yaml" # or yolo.ClassificationDataset("mnist")
cfg.device = cfg.device if cfg.device is not None else ''
@ -204,7 +202,7 @@ def train(cfg):
# trainer.train()
from ultralytics import YOLO
model = YOLO(cfg.model)
model.train(**cfg)
model.train(**vars(cfg))
if __name__ == "__main__":

8
ultralytics/yolo/v8/detect/val.py
View File

@ -3,14 +3,13 @@
import os
from pathlib import Path
import hydra
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_CONFIG, colorstr, ops, yaml_load
from ultralytics.yolo.utils import DEFAULT_CFG, colorstr, ops, yaml_load
from ultralytics.yolo.utils.checks import check_file, check_requirements
from ultralytics.yolo.utils.metrics import ConfusionMatrix, DetMetrics, box_iou
from ultralytics.yolo.utils.plotting import output_to_target, plot_images
@ -168,7 +167,7 @@ class DetectionValidator(BaseValidator):
imgsz=self.args.imgsz,
batch_size=batch_size,
stride=gs,
hyp=dict(self.args),
hyp=vars(self.args),
cache=False,
pad=0.5,
rect=True,
@ -232,8 +231,7 @@ class DetectionValidator(BaseValidator):
return stats
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def val(cfg):
def val(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n.pt"
cfg.data = cfg.data or "coco128.yaml"
validator = DetectionValidator(args=cfg)

6
ultralytics/yolo/v8/segment/predict.py
View File

@ -1,10 +1,9 @@
# Ultralytics YOLO 🚀, GPL-3.0 license
import hydra
import torch
from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import DEFAULT_CONFIG, ROOT, is_git_directory, ops
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, is_git_directory, ops
from ultralytics.yolo.utils.plotting import colors, save_one_box
from ultralytics.yolo.v8.detect.predict import DetectionPredictor
@ -98,8 +97,7 @@ class SegmentationPredictor(DetectionPredictor):
return log_string
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def predict(cfg):
def predict(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n-seg.pt"
cfg.source = cfg.source if cfg.source is not None else ROOT / "assets" if is_git_directory() \
else "https://ultralytics.com/images/bus.jpg"

10
ultralytics/yolo/v8/segment/train.py
View File

@ -2,13 +2,12 @@
from copy import copy
import hydra
import torch
import torch.nn.functional as F
from ultralytics.nn.tasks import SegmentationModel
from ultralytics.yolo import v8
from ultralytics.yolo.utils import DEFAULT_CONFIG
from ultralytics.yolo.utils import DEFAULT_CFG
from ultralytics.yolo.utils.ops import crop_mask, xyxy2xywh
from ultralytics.yolo.utils.plotting import plot_images, plot_results
from ultralytics.yolo.utils.tal import make_anchors
@ -19,7 +18,7 @@ from ultralytics.yolo.v8.detect.train import Loss
# BaseTrainer python usage
class SegmentationTrainer(v8.detect.DetectionTrainer):
def __init__(self, config=DEFAULT_CONFIG, overrides=None):
def __init__(self, config=DEFAULT_CFG, overrides=None):
if overrides is None:
overrides = {}
overrides["task"] = "segment"
@ -141,8 +140,7 @@ class SegLoss(Loss):
return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean()
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def train(cfg):
def train(cfg=DEFAULT_CFG):
cfg.model = cfg.model or "yolov8n-seg.pt"
cfg.data = cfg.data or "coco128-seg.yaml" # or yolo.ClassificationDataset("mnist")
cfg.device = cfg.device if cfg.device is not None else ''
@ -150,7 +148,7 @@ def train(cfg):
# trainer.train()
from ultralytics import YOLO
model = YOLO(cfg.model)
model.train(**cfg)
model.train(**vars(cfg))
if __name__ == "__main__":

6
ultralytics/yolo/v8/segment/val.py
View File

@ -4,12 +4,11 @@ import os
from multiprocessing.pool import ThreadPool
from pathlib import Path
import hydra
import numpy as np
import torch
import torch.nn.functional as F
from ultralytics.yolo.utils import DEFAULT_CONFIG, NUM_THREADS, ops
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
@ -243,8 +242,7 @@ class SegmentationValidator(DetectionValidator):
return stats
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
def val(cfg):
def val(cfg=DEFAULT_CFG):
cfg.data = cfg.data or "coco128-seg.yaml"
validator = SegmentationValidator(args=cfg)
validator(model=cfg.model)