内容参考自：README_cn.md · PaddlePaddle/PaddleDetection - 码云 - 开源中国 (gitee.com)
说明：用于帮助自己理解参数，后续会更新，可能有错误的地方，请不吝赐教。
# YOLO系列模型参数配置教程
标签： 模型参数配置
++++++++++++++++++++++++++ppyolo_r18vd.yml++++++++++++++++++++++++++++++++architecture: YOLOv3 #模型的名称use_gpu: true #是否使用GPU
max_iters: 15500 #最大的迭代次数 log_iter: 10 #输出指定区间的平均结果，如10次的平均结果，也即打印log的间隔 se_dir: output snapshot_iter: 1550 metric: COCO pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar weights: output/ppyolo_r18/model_final num_classes: 9 use_fine_grained_loss: true use_ema: true ema_decay: 0.9998 YOLOv3: backbone: ResNet yolo_head: YOLOv3Head use_fine_grained_loss: true ResNet: norm_type: sync_bn freeze_at: 0 freeze_norm: false norm_decay: 0. depth: 18 feature_maps: [4, 5] variant: d YOLOv3Head: anchor_masks: [[3, 4, 5], [0, 1, 2]] anchors: [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]] norm_decay: 0. conv_block_num: 0 scale_x_y: 1.05 yolo_loss: YOLOv3Loss nms: MatrixNMS drop_block: true YOLOv3Loss: ignore_thresh: 0.7 scale_x_y: 1.05 label_smooth: false use_fine_grained_loss: true iou_loss: IouLoss IouLoss: loss_weight: 2.5 max_height: 640 max_width: 640 MatrixNMS: background_label: -1 keep_top_k: 100 normalized: false score_threshold: 0.01 post_threshold: 0.01 LearningRate: base_lr: 0.004 #学习率决定了权值更新的速度，学习率大，更新的就快，但太快容易越过最优值，而学习率太小又更新的慢，效率低，一般学习率随着训练的进行不断更改，先高一点，然后慢慢降低 schedulers: - !PiecewiseDecay gamma: 0.1 milestones:#学习率变动因子：如迭代到10000次时，学习率衰减十倍，15000次迭代时，学习率又会在前一个学习率的基础上衰减十倍 - 10000 - 15000 - !LinearWarmup start_factor: 0. steps: 4000 #学习率变动步长 OptimizerBuilder: optimizer: momentum: 0.9 #动量，影响梯度下降到最优的速度，一般默认0.9 type: Momentum regularizer: factor: 0.0005 #权重衰减正则系数，防止过拟合 type: L2 _READER_: 'ppyolo_reader.yml' TrainReader: inputs_def: fields: ['image', 'gt_bbox', 'gt_class', 'gt_score'] num_max_boxes: 50 dataset: !COCODataSet image_dir: images anno_path: annotations/val.json dataset_dir: /home/aistudio/data/data101204/NGdet_v4-concat with_background: false sample_transforms: - !DecodeImage to_rgb: True with_mixup: True - !MixupImage alpha: 1.5 beta: 1.5 - !ColorDistort {} - !RandomExpand fill_value: [123.675, 116.28, 103.53] - !RandomCrop {} - !RandomFlipImage is_normalized: false - !NormalizeBox {} - !PadBox num_max_boxes: 50 - !BboxXYXY2XYWH {} batch_transforms: - !RandomShape sizes: [ 352, 384, 416, 448, 480, 512, 544, 576, 608,640] - !NormalizeImage mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] is_scale: True is_channel_first: false - !Permute to_bgr: false channel_first: True # Gt2YoloTarget is only used when use_fine_grained_loss set as true, # this operator will be deleted automatically if use_fine_grained_loss # is set as false - !Gt2YoloTarget anchor_masks: [[3, 4, 5], [0, 1, 2]] #anchors是可以事先通过cmd指令计算出来的，是和图片数量，width,height以及cluster(就是下面的num的值，即想要使用的anchors的数量)相关的预选框，可以手工挑选，也可以通过k-means算法从训练样本中学出 anchors: [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]] downsample_ratios: [32, 16] batch_size: 8 shuffle: true mixup_epoch: 100 #大于最大epoch，表示训练过程一直使用mixup数据增广 drop_last: true worker_num: 8 bufsize: 8 use_process: true
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
以`ppyolo_r50vd_dcn_1x_coco.yml`为例，这个模型由五个子配置文件组成：
- 数据配置文件 `coco_detection.yml`
```yaml# 数据评估类型metric: COCO# 数据集的类别数num_classes: 80
# TrainDatasetTrainDataset: !COCODataSet # 图像数据路径，相对 dataset_dir 路径，os.path.join(dataset_dir, image_dir) image_dir: train2017 # 标注文件路径，相对 dataset_dir 路径，os.path.join(dataset_dir, anno_path) anno_path: annotations/instances_train2017.json # 数据文件夹 dataset_dir: dataset/coco # data_fields data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
EvalDataset: !COCODataSet # 图像数据路径，相对 dataset_dir 路径，os.path.join(dataset_dir, image_dir) image_dir: val2017 # 标注文件路径，相对 dataset_dir 路径，os.path.join(dataset_dir, anno_path) anno_path: annotations/instances_val2017.json # 数据文件夹，os.path.join(dataset_dir, anno_path) dataset_dir: dataset/coco
TestDataset: !ImageFolder # 标注文件路径，相对 dataset_dir 路径 anno_path: annotations/instances_val2017.json```
- 优化器配置文件 `optimizer_1x.yml`
```yaml# 总训练轮数epoch: 405
# 学习率设置LearningRate: # 默认为8卡训学习率 base_lr: 0.01 # 学习率调整策略 schedulers: - !PiecewiseDecay gamma: 0.1 # 学习率变化位置(轮数) milestones: - 243 - 324 # Warmup - !LinearWarmup start_factor: 0. steps: 4000
# 优化器OptimizerBuilder: # 优化器 optimizer: momentum: 0.9 type: Momentum # 正则化 regularizer: factor: 0.0005 type: L2```
- 数据读取配置文件 `ppyolo_reader.yml`
```yaml# 每张GPU reader进程个数worker_num: 2# 训练数据TrainReader: inputs_def: num_max_boxes: 50 # 训练数据transforms sample_transforms: - Decode: {} - Mixup: {alpha: 1.5, beta: 1.5} - RandomDistort: {} - RandomExpand: {fill_value: [123.675, 116.28, 103.53]} - RandomCrop: {} - RandomFlip: {} # batch_transforms batch_transforms: - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608], random_size: True, random_interp: True, keep_ratio: False} - NormalizeBox: {} - PadBox: {num_max_boxes: 50} - BboxXYXY2XYWH: {} - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True} - Permute: {} - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]} # 训练时batch_size batch_size: 24 # 读取数据是是否乱序 shuffle: true # 是否丢弃最后不能完整组成batch的数据 drop_last: true # mixup_epoch，大于最大epoch，表示训练过程一直使用mixup数据增广 mixup_epoch: 25000 # 是否通过共享内存进行数据读取加速，需要保证共享内存大小(如/dev/shm)满足大于1G use_shared_memory: true
# 评估数据EvalReader: # 评估数据transforms sample_transforms: - Decode: {} - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2} - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True} - Permute: {} # 评估时batch_size batch_size: 8 # 是否丢弃没有标注的数据 drop_empty: false
# 测试数据TestReader: inputs_def: image_shape: [3, 608, 608] # 测试数据transforms sample_transforms: - Decode: {} - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2} - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True} - Permute: {} # 测试时batch_size batch_size: 1```
- 模型配置文件 `ppyolo_r50vd_dcn.yml`
```yaml# 模型结构类型architecture: YOLOv3# 预训练模型地址pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams# norm_typenorm_type: sync_bn# 是否使用emause_ema: true# ema_decayema_decay: 0.9998
# YOLOv3YOLOv3: # backbone backbone: ResNet # neck neck: PPYOLOFPN # yolo_head yolo_head: YOLOv3Head # post_process post_process: BBoxPostProcess
# backboneResNet: # depth depth: 50 # variant variant: d # return_idx, 0 represent res2 return_idx: [1, 2, 3] # dcn_v2_stages dcn_v2_stages: [3] # freeze_at freeze_at: -1 # freeze_norm freeze_norm: false # norm_decay norm_decay: 0.
# PPYOLOFPNPPYOLOFPN: # 是否coord_conv coord_conv: true # 是否drop_block drop_block: true # block_size block_size: 3 # keep_prob keep_prob: 0.9 # 是否spp spp: true
# YOLOv3HeadYOLOv3Head: # anchors anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]] # anchor_masks anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]] # loss loss: YOLOv3Loss # 是否使用iou_aware iou_aware: true # iou_aware_factor iou_aware_factor: 0.4
# YOLOv3LossYOLOv3Loss: # ignore_thresh ignore_thresh: 0.7 # downsample downsample: [32, 16, 8] # 是否label_smooth label_smooth: false # scale_x_y scale_x_y: 1.05 # iou_loss iou_loss: IouLoss # iou_aware_loss iou_aware_loss: IouAwareLoss
# IouLossIouLoss: loss_weight: 2.5 loss_square: true
# IouAwareLossIouAwareLoss: loss_weight: 1.0
# BBoxPostProcessBBoxPostProcess: decode: name: YOLOBox conf_thresh: 0.01 downsample_ratio: 32 clip_bbox: true scale_x_y: 1.05 # nms 配置 nms: name: MatrixNMS keep_top_k: 100 score_threshold: 0.01 post_threshold: 0.01 nms_top_k: -1 background_label: -1
```
- 运行时置文件 `runtime.yml`
```yaml# 是否使用gpuuse_gpu: true# 日志打印间隔log_iter: 20# se_dirse_dir: output# 模型保存间隔时间snapshot_epoch: 1```