mirror of
https://github.com/ultralytics/ultralytics.git
synced 2025-09-15 15:48:41 +08:00
Improve config YAMLs (#22011)
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: Laughing-q <1185102784@qq.com> Co-authored-by: Jing Qiu <61612323+Laughing-q@users.noreply.github.com> Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher
GitHub
parent
9b46d8d81c
commit
0f0fed4148
@ -7,122 +7,124 @@ task: detect # (str) YOLO task, i.e. detect, segment, classify, pose, obb
|
||||
mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark
|
||||
|
||||
# Train settings -------------------------------------------------------------------------------------------------------
|
||||
model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml
|
||||
model: # (str, optional) path to model file, i.e. yolov8n.pt or yolov8n.yaml
|
||||
data: # (str, optional) path to data file, i.e. coco8.yaml
|
||||
epochs: 100 # (int) number of epochs to train for
|
||||
time: # (float, optional) number of hours to train for, overrides epochs if supplied
|
||||
patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
|
||||
batch: 16 # (int) number of images per batch (-1 for AutoBatch)
|
||||
imgsz: 640 # (int | list) input images size as int for train and val modes, or list[h,w] for predict and export modes
|
||||
time: # (float, optional) max hours to train; overrides epochs if set
|
||||
patience: 100 # (int) early stop after N epochs without val improvement
|
||||
batch: 16 # (int) batch size; use -1 for AutoBatch
|
||||
imgsz: 640 # (int | list) train/val use int (square); predict/export may use [h,w]
|
||||
save: True # (bool) save train checkpoints and predict results
|
||||
save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
|
||||
cache: False # (bool) True/ram, disk or False. Use cache for data loading
|
||||
device: # (int | str | list) device: CUDA device=0 or [0,1,2,3] or "cpu/mps" or -1 or [-1,-1] to auto-select idle GPUs
|
||||
workers: 8 # (int) number of worker threads for data loading (per RANK if DDP)
|
||||
project: # (str, optional) project name
|
||||
name: # (str, optional) experiment name, results saved to 'project/name' directory
|
||||
exist_ok: False # (bool) whether to overwrite existing experiment
|
||||
pretrained: True # (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str)
|
||||
optimizer: auto # (str) optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto]
|
||||
verbose: True # (bool) whether to print verbose output
|
||||
save_period: -1 # (int) save checkpoint every N epochs; disabled if < 1
|
||||
cache: False # (bool | str) cache images in RAM (True/'ram') or on 'disk' to speed dataloading; False disables
|
||||
device: # (int | str | list) device: 0 or [0,1,2,3] for CUDA, 'cpu'/'mps', or -1/[-1,-1] to auto-select idle GPUs
|
||||
workers: 8 # (int) dataloader workers (per RANK if DDP)
|
||||
project: # (str, optional) project name for results root
|
||||
name: # (str, optional) experiment name; results in 'project/name'
|
||||
exist_ok: False # (bool) overwrite existing 'project/name' if True
|
||||
pretrained: True # (bool | str) use pretrained weights (bool) or load weights from path (str)
|
||||
optimizer: auto # (str) optimizer: SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, or auto
|
||||
verbose: True # (bool) print verbose logs during training/val
|
||||
seed: 0 # (int) random seed for reproducibility
|
||||
deterministic: True # (bool) whether to enable deterministic mode
|
||||
single_cls: False # (bool) train multi-class data as single-class
|
||||
rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
|
||||
cos_lr: False # (bool) use cosine learning rate scheduler
|
||||
close_mosaic: 10 # (int) disable mosaic augmentation for final epochs (0 to disable)
|
||||
resume: False # (bool) resume training from last checkpoint
|
||||
amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
|
||||
fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)
|
||||
profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers
|
||||
freeze: # (int | list, optional) freeze first n layers, or freeze list of layer indices during training
|
||||
multi_scale: False # (bool) Whether to use multiscale during training
|
||||
compile: False # (bool | str) Enable torch.compile() with backend='inductor'. True → "default", False → disable, or str mode
|
||||
deterministic: True # (bool) enable deterministic ops; reproducible but may be slower
|
||||
single_cls: False # (bool) treat all classes as a single class
|
||||
rect: False # (bool) rectangular batches for train; rectangular batching for val when mode='val'
|
||||
cos_lr: False # (bool) cosine learning rate scheduler
|
||||
close_mosaic: 10 # (int) disable mosaic augmentation for final N epochs (0 to keep enabled)
|
||||
resume: False # (bool) resume training from last checkpoint in the run dir
|
||||
amp: True # (bool) Automatic Mixed Precision (AMP) training; True runs AMP capability check
|
||||
fraction: 1.0 # (float) fraction of training dataset to use (1.0 = all)
|
||||
profile: False # (bool) profile ONNX/TensorRT speeds during training for loggers
|
||||
freeze: # (int | list, optional) freeze first N layers (int) or specific layer indices (list)
|
||||
multi_scale: False # (bool) multiscale training by varying image size
|
||||
compile: False # (bool | str) enable torch.compile() backend='inductor'; True="default", False=off, or "default|reduce-overhead|max-autotune"
|
||||
|
||||
# Segmentation
|
||||
overlap_mask: True # (bool) merge object masks into a single image mask during training (segment train only)
|
||||
mask_ratio: 4 # (int) mask downsample ratio (segment train only)
|
||||
overlap_mask: True # (bool) merge instance masks into one mask during training (segment only)
|
||||
mask_ratio: 4 # (int) mask downsample ratio (segment only)
|
||||
|
||||
# Classification
|
||||
dropout: 0.0 # (float) use dropout regularization (classify train only)
|
||||
dropout: 0.0 # (float) dropout for classification head (classify only)
|
||||
|
||||
# Val/Test settings ----------------------------------------------------------------------------------------------------
|
||||
val: True # (bool) validate/test during training
|
||||
split: val # (str) dataset split to use for validation, i.e. 'val', 'test' or 'train'
|
||||
save_json: False # (bool) save results to JSON file
|
||||
conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val)
|
||||
iou: 0.7 # (float) intersection over union (IoU) threshold for NMS
|
||||
val: True # (bool) run validation/testing during training
|
||||
split: val # (str) dataset split to evaluate: 'val', 'test' or 'train'
|
||||
save_json: False # (bool) save results to COCO JSON for external evaluation
|
||||
conf: # (float, optional) confidence threshold; defaults: predict=0.25, val=0.001
|
||||
iou: 0.7 # (float) IoU threshold used for NMS
|
||||
max_det: 300 # (int) maximum number of detections per image
|
||||
half: False # (bool) use half precision (FP16)
|
||||
half: False # (bool) use half precision (FP16) if supported
|
||||
dnn: False # (bool) use OpenCV DNN for ONNX inference
|
||||
plots: True # (bool) save plots and images during train/val
|
||||
|
||||
# Predict settings -----------------------------------------------------------------------------------------------------
|
||||
source: # (str, optional) source directory for images or videos
|
||||
vid_stride: 1 # (int) video frame-rate stride
|
||||
stream_buffer: False # (bool) buffer all streaming frames (True) or return the most recent frame (False)
|
||||
visualize: False # (bool) visualize model features (predict) or visualize TP, FP, FN (val)
|
||||
augment: False # (bool) apply image augmentation to prediction sources
|
||||
source: # (str, optional) path/dir/URL/stream for images or videos; e.g. 'ultralytics/assets' or '0' for webcam
|
||||
vid_stride: 1 # (int) read every Nth frame for video sources
|
||||
stream_buffer: False # (bool) True buffers all frames; False keeps the most recent frame for low-latency streams
|
||||
visualize: False # (bool) visualize model features (predict) or TP/FP/FN confusion (val)
|
||||
augment: False # (bool) apply test-time augmentation during prediction
|
||||
agnostic_nms: False # (bool) class-agnostic NMS
|
||||
classes: # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3]
|
||||
retina_masks: False # (bool) use high-resolution segmentation masks
|
||||
embed: # (list[int], optional) return feature vectors/embeddings from given layers
|
||||
classes: # (int | list[int], optional) filter by class id(s), e.g. 0 or [0,2,3]
|
||||
retina_masks: False # (bool) use high-resolution segmentation masks (segment)
|
||||
embed: # (list[int], optional) return feature embeddings from given layer indices
|
||||
|
||||
# Visualize settings ---------------------------------------------------------------------------------------------------
|
||||
show: False # (bool) show predicted images and videos if environment allows
|
||||
save_frames: False # (bool) save predicted individual video frames
|
||||
save_txt: False # (bool) save results as .txt file
|
||||
save_conf: False # (bool) save results with confidence scores
|
||||
save_crop: False # (bool) save cropped images with results
|
||||
show_labels: True # (bool) show prediction labels, i.e. 'person'
|
||||
show_conf: True # (bool) show prediction confidence, i.e. '0.99'
|
||||
show_boxes: True # (bool) show prediction boxes
|
||||
line_width: # (int, optional) line width of the bounding boxes. Scaled to image size if None.
|
||||
show: False # (bool) show images/videos in a window if supported
|
||||
save_frames: False # (bool) save individual frames from video predictions
|
||||
save_txt: False # (bool) save results as .txt files (xywh format)
|
||||
save_conf: False # (bool) save confidence scores with results
|
||||
save_crop: False # (bool) save cropped prediction regions to files
|
||||
show_labels: True # (bool) draw class labels on images, e.g. 'person'
|
||||
show_conf: True # (bool) draw confidence values on images, e.g. '0.99'
|
||||
show_boxes: True # (bool) draw bounding boxes on images
|
||||
line_width: # (int, optional) line width of boxes; auto-scales with image size if not set
|
||||
|
||||
# Export settings ------------------------------------------------------------------------------------------------------
|
||||
format: torchscript # (str) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats
|
||||
keras: False # (bool) use Kera=s
|
||||
optimize: False # (bool) TorchScript: optimize for mobile
|
||||
int8: False # (bool) CoreML/TF INT8 quantization
|
||||
dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes
|
||||
simplify: True # (bool) ONNX: simplify model using `onnxslim`
|
||||
opset: # (int, optional) ONNX: opset version
|
||||
workspace: # (float, optional) TensorRT: workspace size (GiB), `None` will let TensorRT auto-allocate memory
|
||||
nms: False # (bool) CoreML: add NMS
|
||||
format: torchscript # (str) target format, e.g. torchscript|onnx|openvino|engine|coreml|saved_model|pb|tflite|edgetpu|tfjs|paddle|mnn|ncnn|imx|rknn
|
||||
keras: False # (bool) TF SavedModel only (format=saved_model); enable Keras layers during export
|
||||
optimize: False # (bool) TorchScript only; apply mobile optimizations to the scripted model
|
||||
int8: False # (bool) INT8/PTQ where supported (openvino, tflite, tfjs, engine, imx); needs calibration data/fraction
|
||||
dynamic: False # (bool) dynamic shapes for torchscript, onnx, openvino, engine; enable variable image sizes
|
||||
simplify: True # (bool) ONNX/engine only; run graph simplifier for cleaner ONNX before runtime conversion
|
||||
opset: # (int, optional) ONNX/engine only; opset version for export; leave unset to use a tested default
|
||||
workspace: # (float, optional) engine (TensorRT) only; workspace size in GiB, e.g. 4
|
||||
nms: False # (bool) fuse NMS into exported model when backend supports; if True, conf/iou apply (agnostic_nms except coreml)
|
||||
|
||||
# Hyperparameters ------------------------------------------------------------------------------------------------------
|
||||
lr0: 0.01 # (float) initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
|
||||
lrf: 0.01 # (float) final learning rate (lr0 * lrf)
|
||||
momentum: 0.937 # (float) SGD momentum/Adam beta1
|
||||
weight_decay: 0.0005 # (float) optimizer weight decay 5e-4
|
||||
warmup_epochs: 3.0 # (float) warmup epochs (fractions ok)
|
||||
warmup_momentum: 0.8 # (float) warmup initial momentum
|
||||
warmup_bias_lr: 0.1 # (float) warmup initial bias lr
|
||||
lr0: 0.01 # (float) initial learning rate (SGD=1e-2, Adam/AdamW=1e-3)
|
||||
lrf: 0.01 # (float) final LR fraction; final LR = lr0 * lrf
|
||||
momentum: 0.937 # (float) SGD momentum or Adam beta1
|
||||
weight_decay: 0.0005 # (float) weight decay (L2 regularization)
|
||||
warmup_epochs: 3.0 # (float) warmup epochs (fractions allowed)
|
||||
warmup_momentum: 0.8 # (float) initial momentum during warmup
|
||||
warmup_bias_lr: 0.1 # (float) bias learning rate during warmup
|
||||
box: 7.5 # (float) box loss gain
|
||||
cls: 0.5 # (float) cls loss gain (scale with pixels)
|
||||
dfl: 1.5 # (float) dfl loss gain
|
||||
pose: 12.0 # (float) pose loss gain
|
||||
kobj: 1.0 # (float) keypoint obj loss gain
|
||||
nbs: 64 # (int) nominal batch size
|
||||
hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
|
||||
hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
|
||||
hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
|
||||
degrees: 0.0 # (float) image rotation (+/- deg)
|
||||
translate: 0.1 # (float) image translation (+/- fraction)
|
||||
scale: 0.5 # (float) image scale (+/- gain)
|
||||
shear: 0.0 # (float) image shear (+/- deg)
|
||||
perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
|
||||
flipud: 0.0 # (float) image flip up-down (probability)
|
||||
fliplr: 0.5 # (float) image flip left-right (probability)
|
||||
bgr: 0.0 # (float) image channel BGR (probability)
|
||||
mosaic: 1.0 # (float) image mosaic (probability)
|
||||
mixup: 0.0 # (float) image mixup (probability)
|
||||
cutmix: 0.0 # (float) image cutmix (probability)
|
||||
copy_paste: 0.0 # (float) segment copy-paste (probability)
|
||||
copy_paste_mode: "flip" # (str) the method to do copy_paste augmentation (flip, mixup)
|
||||
auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix)
|
||||
erasing: 0.4 # (float) probability of random erasing during classification training (0-0.9), 0 means no erasing, must be less than 1.0.
|
||||
cls: 0.5 # (float) classification loss gain
|
||||
dfl: 1.5 # (float) distribution focal loss gain
|
||||
pose: 12.0 # (float) pose loss gain (pose tasks)
|
||||
kobj: 1.0 # (float) keypoint objectness loss gain (pose tasks)
|
||||
nbs: 64 # (int) nominal batch size used for loss normalization
|
||||
hsv_h: 0.015 # (float) HSV hue augmentation fraction
|
||||
hsv_s: 0.7 # (float) HSV saturation augmentation fraction
|
||||
hsv_v: 0.4 # (float) HSV value (brightness) augmentation fraction
|
||||
degrees: 0.0 # (float) rotation degrees (+/-)
|
||||
translate: 0.1 # (float) translation fraction (+/-)
|
||||
scale: 0.5 # (float) scale gain (+/-)
|
||||
shear: 0.0 # (float) shear degrees (+/-)
|
||||
perspective: 0.0 # (float) perspective fraction (0–0.001 typical)
|
||||
flipud: 0.0 # (float) vertical flip probability
|
||||
fliplr: 0.5 # (float) horizontal flip probability
|
||||
bgr: 0.0 # (float) RGB↔BGR channel swap probability
|
||||
mosaic: 1.0 # (float) mosaic augmentation probability
|
||||
mixup: 0.0 # (float) MixUp augmentation probability
|
||||
cutmix: 0.0 # (float) CutMix augmentation probability
|
||||
copy_paste: 0.0 # (float) segmentation copy-paste probability
|
||||
copy_paste_mode: flip # (str) copy-paste strategy for segmentation: flip or mixup
|
||||
auto_augment: randaugment # (str) classification auto augmentation policy: randaugment, autoaugment, augmix
|
||||
erasing: 0.4 # (float) random erasing probability for classification (0–0.9), <1.0
|
||||
|
||||
# Custom config.yaml ---------------------------------------------------------------------------------------------------
|
||||
cfg: # (str, optional) for overriding defaults.yaml
|
||||
cfg: # (str, optional) path to a config.yaml that overrides defaults
|
||||
|
||||
# Tracker settings ------------------------------------------------------------------------------------------------------
|
||||
tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]
|
||||
tracker: botsort.yaml # (str) tracker config file: botsort.yaml or bytetrack.yaml
|
||||
|
||||
@ -1,22 +1,21 @@
|
||||
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
||||
|
||||
# Default Ultralytics settings for BoT-SORT tracker when using mode="track"
|
||||
# For documentation and examples see https://docs.ultralytics.com/modes/track/
|
||||
# For BoT-SORT source code see https://github.com/NirAharon/BoT-SORT
|
||||
# BoT-SORT tracker defaults for mode="track"
|
||||
# Docs: https://docs.ultralytics.com/modes/track/
|
||||
|
||||
tracker_type: botsort # tracker type, ['botsort', 'bytetrack']
|
||||
track_high_thresh: 0.25 # threshold for the first association
|
||||
track_low_thresh: 0.1 # threshold for the second association
|
||||
new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
|
||||
track_buffer: 30 # buffer to calculate the time when to remove tracks
|
||||
match_thresh: 0.8 # threshold for matching tracks
|
||||
fuse_score: True # Whether to fuse confidence scores with the iou distances before matching
|
||||
# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now)
|
||||
tracker_type: botsort # (str) Tracker backend: botsort|bytetrack; choose botsort to enable BoT-SORT features
|
||||
track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
|
||||
track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
|
||||
new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
|
||||
track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
|
||||
match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
|
||||
fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections
|
||||
|
||||
# BoT-SORT specifics
|
||||
gmc_method: sparseOptFlow # (str) Global motion compensation: sparseOptFlow|orb|none; helps moving camera scenes
|
||||
|
||||
# BoT-SORT settings
|
||||
gmc_method: sparseOptFlow # method of global motion compensation
|
||||
# ReID model related thresh
|
||||
proximity_thresh: 0.5 # minimum IoU for valid match with ReID
|
||||
appearance_thresh: 0.8 # minimum appearance similarity for ReID
|
||||
with_reid: False
|
||||
model: auto # uses native features if detector is YOLO else yolo11n-cls.pt
|
||||
proximity_thresh: 0.5 # (float) Min IoU to consider tracks proximate for ReID; higher is stricter
|
||||
appearance_thresh: 0.8 # (float) Min appearance similarity for ReID; raise to avoid identity swaps
|
||||
with_reid: False # (bool) Enable ReID model use; needs extra model and compute
|
||||
model: auto # (str) ReID model name/path; "auto" uses detector features if available
|
||||
|
||||
@ -1,14 +1,12 @@
|
||||
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
||||
|
||||
# Default Ultralytics settings for ByteTrack tracker when using mode="track"
|
||||
# For documentation and examples see https://docs.ultralytics.com/modes/track/
|
||||
# For ByteTrack source code see https://github.com/ifzhang/ByteTrack
|
||||
# ByteTrack tracker defaults for mode="track"
|
||||
# Docs: https://docs.ultralytics.com/modes/track/
|
||||
|
||||
tracker_type: bytetrack # tracker type, ['botsort', 'bytetrack']
|
||||
track_high_thresh: 0.25 # threshold for the first association
|
||||
track_low_thresh: 0.1 # threshold for the second association
|
||||
new_track_thresh: 0.25 # threshold for init new track if the detection does not match any tracks
|
||||
track_buffer: 30 # buffer to calculate the time when to remove tracks
|
||||
match_thresh: 0.8 # threshold for matching tracks
|
||||
fuse_score: True # Whether to fuse confidence scores with the iou distances before matching
|
||||
# min_box_area: 10 # threshold for min box areas(for tracker evaluation, not used for now)
|
||||
tracker_type: bytetrack # (str) Tracker backend: botsort|bytetrack; choose bytetrack for the classic baseline
|
||||
track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
|
||||
track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
|
||||
new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
|
||||
track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
|
||||
match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
|
||||
fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections
|
||||
|
||||
Loading…
Reference in New Issue
Block a user