# Ultralytics YOLO 🚀, GPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training

task: "detect" # choices=['detect', 'segment', 'classify', 'init'] # init is a special case. Specify task to run.
mode: "train" # choices=['train', 'val', 'predict'] # mode to run task in.

# Train settings -------------------------------------------------------------------------------------------------------
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: 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
device: null # cuda device, i.e. 0 or 0,1,2,3 or cpu. Device to run on
workers: 8 # number of worker threads for data loading
project: null # project name
name: null # experiment name
exist_ok: False # whether to overwrite existing experiment
pretrained: False # whether to use a pretrained model
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
single_cls: False # train multi-class data as single-class
image_weights: False # use weighted image selection for training
rect: False # support rectangular training
cos_lr: False # use cosine learning rate scheduler
close_mosaic: 10 # disable mosaic augmentation for final 10 epochs
resume: False # resume training from last checkpoint
# Segmentation
overlap_mask: True # masks should overlap during training
mask_ratio: 4 # mask downsample ratio
# Classification
dropout: 0.0  # use dropout regularization

# Val/Test settings ----------------------------------------------------------------------------------------------------
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: null # object confidence threshold for detection (default 0.25 predict, 0.001 val)
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
plots: True # show plots during training

# Prediction settings --------------------------------------------------------------------------------------------------
source: null # source directory for images or videos
show: False # show results if possible
save_txt: False # save results as .txt file
save_conf: False # save results with confidence scores
save_crop: False # save cropped images with results
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)
visualize: False # visualize results
augment: False # apply data augmentation to images
agnostic_nms: False # class-agnostic NMS
retina_masks: False # use retina masks for object detection

# Export settings ------------------------------------------------------------------------------------------------------
format: torchscript # format to export to
keras: False  # use Keras
optimize: False  # TorchScript: optimize for mobile
int8: False  # CoreML/TF INT8 quantization
dynamic: False  # ONNX/TF/TensorRT: dynamic axes
simplify: False  # ONNX: simplify model
opset: 17  # ONNX: opset version
workspace: 4  # TensorRT: workspace size (GB)
nms: False  # CoreML: add NMS

# Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
momentum: 0.937  # SGD momentum/Adam beta1
weight_decay: 0.0005  # optimizer weight decay 5e-4
warmup_epochs: 3.0  # warmup epochs (fractions ok)
warmup_momentum: 0.8  # warmup initial momentum
warmup_bias_lr: 0.1  # warmup initial bias lr
box: 7.5  # box loss gain
cls: 0.5  # cls loss gain (scale with pixels)
dfl: 1.5  # dfl loss gain
fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
label_smoothing: 0.0
nbs: 64  # nominal batch size
hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4  # image HSV-Value augmentation (fraction)
degrees: 0.0  # image rotation (+/- deg)
translate: 0.1  # image translation (+/- fraction)
scale: 0.5  # image scale (+/- gain)
shear: 0.0  # image shear (+/- deg)
perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
flipud: 0.0  # image flip up-down (probability)
fliplr: 0.5  # image flip left-right (probability)
mosaic: 1.0  # image mosaic (probability)
mixup: 0.0  # image mixup (probability)
copy_paste: 0.0  # segment copy-paste (probability)

# Hydra configs --------------------------------------------------------------------------------------------------------
hydra:
  output_subdir: null  # disable hydra directory creation
  run:
    dir: .

# Debug, do not modify -------------------------------------------------------------------------------------------------
v5loader: False  # use legacy YOLOv5 dataloader