因为笔者目前做船舶感知检测的方向，想对yolov8进行改进创新。故从零开始学习yolov8。
参考博客：
YOLOv8详解:损失函数、Anchor-Free、样本分配策略；以及与v5的对比_yolov8损失函数-优快云博客
一、损失函数
损失函数的权重在ultralytics/cfg/default.yaml中可以找到：
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Global configuration YAML with settings and hyperparameters for YOLO training, validation, prediction and export
# For documentation see https://docs.ultralytics.com/usage/cfg/
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
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
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, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
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
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: None # (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
# 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)
# Classification
dropout: 0.0 # (float) use dropout regularization (classify train 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
save_hybrid: False # (bool) save hybrid version of labels (labels + additional predictions)
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
max_det: 300 # (int) maximum number of detections per image
half: False # (bool) use half precision (FP16)
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
augment: False # (bool) apply image augmentation to prediction sources
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
# 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.
# 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: None # (float, optional) TensorRT: workspace size (GiB), `None` will let TensorRT auto-allocate memory
nms: False # (bool) CoreML: add NMS
# 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
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)
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.
crop_fraction: 1.0 # (float) image crop fraction for classification (0.1-1), 1.0 means no crop, must be greater than 0.
# Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg: # (str, optional) for overriding defaults.yaml
# Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]
损失函数定义的文件在ultralytics/utils/loss.py
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
import torch
import torch.nn as nn
import torch.nn.functional as F
from ultralytics.utils.metrics import OKS_SIGMA
from ultralytics.utils.ops import crop_mask, xywh2xyxy, xyxy2xywh
from ultralytics.utils.tal import RotatedTaskAlignedAssigner, TaskAlignedAssigner, dist2bbox, dist2rbox, make_anchors
from ultralytics.utils.torch_utils import autocast
from .metrics import bbox_iou, probiou
from .tal import bbox2dist
class VarifocalLoss(nn.Module):
"""
Varifocal loss by Zhang et al.
https://arxiv.org/abs/2008.13367.
"""
def __init__(self):
"""Initialize the VarifocalLoss class."""
super().__init__()
@staticmethod
def forward(pred_score, gt_score, label, alpha=0.75, gamma=2.0):
"""Computes varfocal loss."""
weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
with autocast(enabled=False):
loss = (
(F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction="none") * weight)
.mean(1)
.sum()
)
return loss
class FocalLoss(nn.Module):
"""Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)."""
def __init__(self):
"""Initializer for FocalLoss class with no parameters."""
super().__init__()
@staticmethod
def forward(pred, label, gamma=1.5, alpha=0.25):
"""Calculates and updates confusion matrix for object detection/classification tasks."""
loss = F.binary_cross_entropy_with_logits(pred, label, reduction="none")
# p_t = torch.exp(-loss)
#
最低0.47元/天 解锁文章
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
