xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-24 06:14:55 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Replace nosave and noval with save and val (#127)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-01-01 17:50:06 +01:00 committed by GitHub
parent 598f17a472
commit 63c7a74691
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 74 additions and 77 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

114
ultralytics/yolo/configs/default.yaml
View File

@ -1,71 +1,69 @@
# YOLO 🚀 by Ultralytics, GPL-3.0 license # YOLO 🚀 by Ultralytics, GPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training # Default training settings and hyperparameters for medium-augmentation COCO training
# Task and Mode task: "classify" # choices=['detect', 'segment', 'classify', 'init'] # init is a special case. Specify task to run.
task: "classify" # choices=['detect', 'segment', 'classify', 'init'] # init is a special case mode: "train" # choices=['train', 'val', 'predict'] # mode to run task in.
mode: "train" # choice=['train', 'val', 'predict']
# Train settings ------------------------------------------------------------------------------------------------------- # Train settings -------------------------------------------------------------------------------------------------------
model: null # i.e. yolov5s.pt, yolo.yaml model: null # i.e. yolov5s.pt, yolo.yaml. Path to model file
data: null # i.e. coco128.yaml data: null # i.e. coco128.yaml. Path to data file
epochs: 100 epochs: 100 # number of epochs to train for
batch_size: 16 batch_size: 16 # number of images per batch
imgsz: 640 imgsz: 640 # size of input images
nosave: False save: True # save checkpoints
cache: False # True/ram, disk or False cache: False # True/ram, disk or False. Use cache for data loading
device: '' # cuda device, i.e. 0 or 0,1,2,3 or cpu device: '' # cuda device, i.e. 0 or 0,1,2,3 or cpu. Device to run on
workers: 8 workers: 8 # number of worker threads for data loading
project: null project: null # project name
name: null name: null # experiment name
exist_ok: False exist_ok: False # whether to overwrite existing experiment
pretrained: False pretrained: False # whether to use a pretrained model
optimizer: 'SGD' # choices=['SGD', 'Adam', 'AdamW', 'RMSProp'] optimizer: 'SGD' # optimizer to use, choices=['SGD', 'Adam', 'AdamW', 'RMSProp']
verbose: False verbose: False # whether to print verbose output
seed: 0 seed: 0 # random seed for reproducibility
deterministic: True deterministic: True # whether to enable deterministic mode
local_rank: -1 local_rank: -1 # local rank for distributed training
single_cls: False # train multi-class data as single-class single_cls: False # train multi-class data as single-class
image_weights: False # use weighted image selection for training image_weights: False # use weighted image selection for training
rect: False # support rectangular training rect: False # support rectangular training
cos_lr: False # use cosine LR scheduler cos_lr: False # use cosine learning rate scheduler
close_mosaic: 10 # disable mosaic for final 10 epochs close_mosaic: 10 # disable mosaic augmentation for final 10 epochs
resume: False resume: False # resume training from last checkpoint
# Segmentation # Segmentation
overlap_mask: True # masks overlap overlap_mask: True # masks should overlap during training
mask_ratio: 4 # mask downsample ratio mask_ratio: 4 # mask downsample ratio
# Classification # Classification
dropout: False # use dropout dropout: False # use dropout regularization
# Val/Test settings ---------------------------------------------------------------------------------------------------- # Val/Test settings ----------------------------------------------------------------------------------------------------
noval: False val: True # validate/test during training
save_json: False save_json: False # save results to JSON file
save_hybrid: False save_hybrid: False # save hybrid version of labels (labels + additional predictions)
conf_thres: 0.001 conf_thres: 0.001 # object confidence threshold for detection
iou_thres: 0.7 iou_thres: 0.7 # intersection over union threshold for NMS
max_det: 300 max_det: 300 # maximum number of detections per image
half: False half: False # use half precision (FP16)
dnn: False # use OpenCV DNN for ONNX inference dnn: False # use OpenCV DNN for ONNX inference
plots: True plots: True # show plots during training
# Prediction settings -------------------------------------------------------------------------------------------------- # Prediction settings --------------------------------------------------------------------------------------------------
source: "ultralytics/assets/" source: "ultralytics/assets" # source directory for images or videos
view_img: False show: False # show results if possible
save_txt: False save_txt: False # save results as .txt file
save_conf: False save_conf: False # save results with confidence scores
save_crop: False save_crop: False # save cropped images with results
hide_labels: False # hide labels hide_labels: False # hide labels
hide_conf: False hide_conf: False # hide confidence scores
vid_stride: 1 # video frame-rate stride vid_stride: 1 # video frame-rate stride
line_thickness: 3 # bounding box thickness (pixels) line_thickness: 3 # bounding box thickness (pixels)
update: False # Update all models update: False # Update all models
visualize: False visualize: False # visualize results
augment: False augment: False # apply data augmentation to images
agnostic_nms: False # class-agnostic NMS agnostic_nms: False # class-agnostic NMS
retina_masks: False retina_masks: False # use retina masks for object detection
# Export settings ------------------------------------------------------------------------------------------------------ # Export settings ------------------------------------------------------------------------------------------------------
format: torchscript format: torchscript # format to export to
keras: False # use Keras keras: False # use Keras
optimize: False # TorchScript: optimize for mobile optimize: False # TorchScript: optimize for mobile
int8: False # CoreML/TF INT8 quantization int8: False # CoreML/TF INT8 quantization
@ -103,11 +101,11 @@ mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability) mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability) copy_paste: 0.0 # segment copy-paste (probability)
# For debugging. Don't change
v5loader: False
# Hydra configs -------------------------------------------------------------------------------------------------------- # Hydra configs --------------------------------------------------------------------------------------------------------
hydra: hydra:
output_subdir: null # disable hydra directory creation output_subdir: null # disable hydra directory creation
run: run:
dir: . dir: .
# Debug, do not modify -------------------------------------------------------------------------------------------------
v5loader: False # use legacy YOLOv5 dataloader

2
ultralytics/yolo/data/build.py
View File

@ -67,7 +67,7 @@ def build_dataloader(cfg, batch_size, img_path, stride=32, label_path=None, rank
augment=mode == "train", # augmentation augment=mode == "train", # augmentation
hyp=cfg, # TODO: probably add a get_hyps_from_cfg function hyp=cfg, # TODO: probably add a get_hyps_from_cfg function
rect=cfg.rect if mode == "train" else True, # rectangular batches rect=cfg.rect if mode == "train" else True, # rectangular batches
cache=None if cfg.noval else cfg.get("cache", None), cache=cfg.get("cache", None),
single_cls=cfg.get("single_cls", False), single_cls=cfg.get("single_cls", False),
stride=int(stride), stride=int(stride),
pad=0.0 if mode == "train" else 0.5, pad=0.0 if mode == "train" else 0.5,

7
ultralytics/yolo/engine/predictor.py
View File

@ -104,7 +104,6 @@ class BasePredictor:
def setup(self, source=None, model=None): def setup(self, source=None, model=None):
# source # source
source = str(source or self.args.source) source = str(source or self.args.source)
self.save_img = not self.args.nosave and not source.endswith('.txt')
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file) webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
@ -168,10 +167,10 @@ class BasePredictor:
p = Path(path) p = Path(path)
s += self.write_results(i, preds, (p, im, im0s)) s += self.write_results(i, preds, (p, im, im0s))
if self.args.view_img: if self.args.show:
self.show(p) self.show(p)
if self.save_img: if self.args.save:
self.save_preds(vid_cap, i, str(self.save_dir / p.name)) self.save_preds(vid_cap, i, str(self.save_dir / p.name))
# Print time (inference-only) # Print time (inference-only)
@ -182,7 +181,7 @@ class BasePredictor:
LOGGER.info( LOGGER.info(
f'Speed: %.1fms pre-process, %.1fms inference, %.1fms postprocess per image at shape {(1, 3, *self.imgsz)}' f'Speed: %.1fms pre-process, %.1fms inference, %.1fms postprocess per image at shape {(1, 3, *self.imgsz)}'
% t) % t)
if self.args.save_txt or self.save_img: if self.args.save_txt or self.args.save:
s = f"\n{len(list(self.save_dir.glob('labels/*.txt')))} labels saved to {self.save_dir / 'labels'}" if self.args.save_txt else '' s = f"\n{len(list(self.save_dir.glob('labels/*.txt')))} labels saved to {self.save_dir / 'labels'}" if self.args.save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}{s}") LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}{s}")

22
ultralytics/yolo/engine/trainer.py
View File

@ -244,12 +244,12 @@ class BaseTrainer:
for i, batch in pbar: for i, batch in pbar:
self.trigger_callbacks("on_train_batch_start") self.trigger_callbacks("on_train_batch_start")
# update dataloader attributes (optional) # Update dataloader attributes (optional)
if epoch == (self.epochs - self.args.close_mosaic) and hasattr(self.train_loader.dataset, 'mosaic'): if epoch == (self.epochs - self.args.close_mosaic) and hasattr(self.train_loader.dataset, 'mosaic'):
LOGGER.info("Closing dataloader mosaic") LOGGER.info("Closing dataloader mosaic")
self.train_loader.dataset.mosaic = False self.train_loader.dataset.mosaic = False
# warmup # Warmup
ni = i + nb * epoch ni = i + nb * epoch
if ni <= nw: if ni <= nw:
xi = [0, nw] # x interp xi = [0, nw] # x interp
@ -261,7 +261,7 @@ class BaseTrainer:
if 'momentum' in x: if 'momentum' in x:
x['momentum'] = np.interp(ni, xi, [self.args.warmup_momentum, self.args.momentum]) x['momentum'] = np.interp(ni, xi, [self.args.warmup_momentum, self.args.momentum])
# forward # Forward
with torch.cuda.amp.autocast(self.amp): with torch.cuda.amp.autocast(self.amp):
batch = self.preprocess_batch(batch) batch = self.preprocess_batch(batch)
preds = self.model(batch["img"]) preds = self.model(batch["img"])
@ -271,15 +271,15 @@ class BaseTrainer:
self.tloss = (self.tloss * i + self.loss_items) / (i + 1) if self.tloss is not None \ self.tloss = (self.tloss * i + self.loss_items) / (i + 1) if self.tloss is not None \
else self.loss_items else self.loss_items
# backward # Backward
self.scaler.scale(self.loss).backward() self.scaler.scale(self.loss).backward()
# optimize - https://pytorch.org/docs/master/notes/amp_examples.html # Optimize - https://pytorch.org/docs/master/notes/amp_examples.html
if ni - last_opt_step >= self.accumulate: if ni - last_opt_step >= self.accumulate:
self.optimizer_step() self.optimizer_step()
last_opt_step = ni last_opt_step = ni
# log # Log
mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB) mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
loss_len = self.tloss.shape[0] if len(self.tloss.size()) else 1 loss_len = self.tloss.shape[0] if len(self.tloss.size()) else 1
losses = self.tloss if loss_len > 1 else torch.unsqueeze(self.tloss, 0) losses = self.tloss if loss_len > 1 else torch.unsqueeze(self.tloss, 0)
@ -298,17 +298,17 @@ class BaseTrainer:
self.trigger_callbacks("on_train_epoch_end") self.trigger_callbacks("on_train_epoch_end")
if rank in {-1, 0}: if rank in {-1, 0}:
# validation # Validation
self.trigger_callbacks('on_val_start') self.trigger_callbacks('on_val_start')
self.ema.update_attr(self.model, include=['yaml', 'nc', 'args', 'names', 'stride', 'class_weights']) self.ema.update_attr(self.model, include=['yaml', 'nc', 'args', 'names', 'stride', 'class_weights'])
final_epoch = (epoch + 1 == self.epochs) final_epoch = (epoch + 1 == self.epochs)
if not self.args.noval or final_epoch: if self.args.val or final_epoch:
self.metrics, self.fitness = self.validate() self.metrics, self.fitness = self.validate()
self.trigger_callbacks('on_val_end') self.trigger_callbacks('on_val_end')
self.save_metrics(metrics={**self.label_loss_items(self.tloss), **self.metrics, **lr}) self.save_metrics(metrics={**self.label_loss_items(self.tloss), **self.metrics, **lr})
# save model # Save model
if (not self.args.nosave) or (epoch + 1 == self.epochs): if self.args.save or (epoch + 1 == self.epochs):
self.save_model() self.save_model()
self.trigger_callbacks('on_model_save') self.trigger_callbacks('on_model_save')
@ -319,7 +319,7 @@ class BaseTrainer:
# TODO: termination condition # TODO: termination condition
if rank in {-1, 0}: if rank in {-1, 0}:
# do the last evaluation with best.pt # Do final val with best.pt
self.log(f'\n{epoch - self.start_epoch + 1} epochs completed in ' self.log(f'\n{epoch - self.start_epoch + 1} epochs completed in '
f'{(time.time() - self.train_time_start) / 3600:.3f} hours.') f'{(time.time() - self.train_time_start) / 3600:.3f} hours.')
self.final_eval() self.final_eval()

2
ultralytics/yolo/v8/classify/predict.py
View File

@ -43,7 +43,7 @@ class ClassificationPredictor(BasePredictor):
# write # write
text = '\n'.join(f'{prob[j]:.2f} {self.model.names[j]}' for j in top5i) text = '\n'.join(f'{prob[j]:.2f} {self.model.names[j]}' for j in top5i)
if self.save_img or self.args.view_img: # Add bbox to image if self.args.save or self.args.show: # Add bbox to image
self.annotator.text((32, 32), text, txt_color=(255, 255, 255)) self.annotator.text((32, 32), text, txt_color=(255, 255, 255))
if self.args.save_txt: # Write to file if self.args.save_txt: # Write to file
with open(f'{self.txt_path}.txt', 'a') as f: with open(f'{self.txt_path}.txt', 'a') as f:

2
ultralytics/yolo/v8/detect/predict.py
View File

@ -66,7 +66,7 @@ class DetectionPredictor(BasePredictor):
with open(f'{self.txt_path}.txt', 'a') as f: with open(f'{self.txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n') f.write(('%g ' * len(line)).rstrip() % line + '\n')
if self.save_img or self.args.save_crop or self.args.view_img: # Add bbox to image if self.args.save or self.args.save_crop or self.args.show: # Add bbox to image
c = int(cls) # integer class c = int(cls) # integer class
label = None if self.args.hide_labels else ( label = None if self.args.hide_labels else (
self.model.names[c] if self.args.hide_conf else f'{self.model.names[c]} {conf:.2f}') self.model.names[c] if self.args.hide_conf else f'{self.model.names[c]} {conf:.2f}')

2
ultralytics/yolo/v8/segment/predict.py
View File

@ -81,7 +81,7 @@ class SegmentationPredictor(DetectionPredictor):
with open(f'{self.txt_path}.txt', 'a') as f: with open(f'{self.txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n') f.write(('%g ' * len(line)).rstrip() % line + '\n')
if self.save_img or self.args.save_crop or self.args.view_img: if self.args.save or self.args.save_crop or self.args.show:
c = int(cls) # integer class c = int(cls) # integer class
label = None if self.args.hide_labels else ( label = None if self.args.hide_labels else (
self.model.names[c] if self.args.hide_conf else f'{self.model.names[c]} {conf:.2f}') self.model.names[c] if self.args.hide_conf else f'{self.model.names[c]} {conf:.2f}')