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

Simplify argument names (#141)

Browse Source
This commit is contained in:
Glenn Jocher
2023-01-03 19:47:56 +01:00
committed by GitHub
parent d74de2582c
commit 3c18aa5278
9 changed files with 22 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ultralytics/yolo/configs/default.yaml
View File

@ -9,7 +9,7 @@ model: null # i.e. yolov8n.pt, yolov8n.yaml. Path to model file
data: null # i.e. coco128.yaml. Path to data file
epochs: 100 # number of epochs to train for
patience: 50 # TODO: epochs to wait for no observable improvement for early stopping of training
batch_size: 16 # number of images per batch
batch: 16 # number of images per batch
imgsz: 640 # size of input images
save: True # save checkpoints
cache: False # True/ram, disk or False. Use cache for data loading
@ -23,7 +23,6 @@ optimizer: 'SGD' # optimizer to use, choices=['SGD', 'Adam', 'AdamW', 'RMSProp']
verbose: False # whether to print verbose output
seed: 0 # random seed for reproducibility
deterministic: True # whether to enable deterministic mode
local_rank: -1 # local rank for distributed training
single_cls: False # train multi-class data as single-class
image_weights: False # use weighted image selection for training
rect: False # support rectangular training
@ -40,8 +39,8 @@ dropout: False # use dropout regularization
val: True # validate/test during training
save_json: False # save results to JSON file
save_hybrid: False # save hybrid version of labels (labels + additional predictions)
conf_thres: 0.001 # object confidence threshold for detection
iou_thres: 0.7 # intersection over union threshold for NMS
conf: 0.001 # object confidence threshold for detection
iou: 0.7 # intersection over union (IoU) threshold for NMS
max_det: 300 # maximum number of detections per image
half: False # use half precision (FP16)
dnn: False # use OpenCV DNN for ONNX inference
@ -57,7 +56,6 @@ hide_labels: False # hide labels
hide_conf: False # hide confidence scores
vid_stride: 1 # video frame-rate stride
line_thickness: 3 # bounding box thickness (pixels)
update: False # Update all models
visualize: False # visualize results
augment: False # apply data augmentation to images
agnostic_nms: False # class-agnostic NMS

6
ultralytics/yolo/engine/exporter.py
View File

@ -164,14 +164,14 @@ class Exporter:
assert not self.args.dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic'
# Checks
# if self.args.batch_size == model.args['batch_size']: # user has not modified training batch_size
self.args.batch_size = 1
# if self.args.batch == model.args['batch_size']: # user has not modified training batch_size
self.args.batch = 1
self.imgsz = check_imgsz(self.args.imgsz, stride=model.stride, min_dim=2) # check image size
if self.args.optimize:
assert self.device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'
# Input
im = torch.zeros(self.args.batch_size, 3, *self.imgsz).to(self.device)
im = torch.zeros(self.args.batch, 3, *self.imgsz).to(self.device)
file = Path(getattr(model, 'pt_path', None) or model.yaml['yaml_file'])
if file.suffix == '.yaml':
file = Path(file.name)

2
ultralytics/yolo/engine/trainer.py
View File

@ -102,7 +102,7 @@ class BaseTrainer:
yaml_save(self.save_dir / 'args.yaml', OmegaConf.to_container(self.args, resolve=True)) # save run args
self.last, self.best = self.wdir / 'last.pt', self.wdir / 'best.pt' # checkpoint paths
self.batch_size = self.args.batch_size
self.batch_size = self.args.batch
self.epochs = self.args.epochs
self.start_epoch = 0
if RANK == -1:

8
ultralytics/yolo/engine/validator.py
View File

@ -87,18 +87,18 @@ class BaseValidator:
callbacks.add_integration_callbacks(self)
self.run_callbacks('on_val_start')
assert model is not None, "Either trainer or model is needed for validation"
self.device = select_device(self.args.device, self.args.batch_size)
self.device = select_device(self.args.device, self.args.batch)
self.args.half &= self.device.type != 'cpu'
model = AutoBackend(model, device=self.device, dnn=self.args.dnn, fp16=self.args.half)
self.model = model
stride, pt, jit, engine = model.stride, model.pt, model.jit, model.engine
imgsz = check_imgsz(self.args.imgsz, stride=stride)
if engine:
self.args.batch_size = model.batch_size
self.args.batch = model.batch_size
else:
self.device = model.device
if not pt and not jit:
self.args.batch_size = 1 # export.py models default to batch-size 1
self.args.batch = 1 # export.py models default to batch-size 1
self.logger.info(
f'Forcing --batch-size 1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models')
@ -110,7 +110,7 @@ class BaseValidator:
if self.device.type == 'cpu':
self.args.workers = 0 # faster CPU val as time dominated by inference, not dataloading
self.dataloader = self.dataloader or \
self.get_dataloader(data.get("val") or data.set("test"), self.args.batch_size)
self.get_dataloader(data.get("val") or data.set("test"), self.args.batch)
self.data = data
model.eval()

4
ultralytics/yolo/v8/detect/predict.py
View File

@ -20,8 +20,8 @@ class DetectionPredictor(BasePredictor):
def postprocess(self, preds, img, orig_img):
preds = ops.non_max_suppression(preds,
self.args.conf_thres,
self.args.iou_thres,
self.args.conf,
self.args.iou,
agnostic=self.args.agnostic_nms,
max_det=self.args.max_det)

4
ultralytics/yolo/v8/detect/val.py
View File

@ -58,8 +58,8 @@ class DetectionValidator(BaseValidator):
def postprocess(self, preds):
preds = ops.non_max_suppression(preds,
self.args.conf_thres,
self.args.iou_thres,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=True,
agnostic=self.args.single_cls,

4
ultralytics/yolo/v8/segment/predict.py
View File

@ -14,8 +14,8 @@ class SegmentationPredictor(DetectionPredictor):
masks = []
# TODO: filter by classes
p = ops.non_max_suppression(preds[0],
self.args.conf_thres,
self.args.iou_thres,
self.args.conf,
self.args.iou,
agnostic=self.args.agnostic_nms,
max_det=self.args.max_det,
nm=32)

4
ultralytics/yolo/v8/segment/val.py
View File

@ -60,8 +60,8 @@ class SegmentationValidator(DetectionValidator):
def postprocess(self, preds):
p = ops.non_max_suppression(preds[0],
self.args.conf_thres,
self.args.iou_thres,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=True,
agnostic=self.args.single_cls,