| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198 |
- architecture: YOLOv3
- use_gpu: false
- use_xpu: true
- max_iters: 5000
- log_iter: 1
- save_dir: output
- snapshot_iter: 500
- metric: VOC
- pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/ppyolo.pdparams
- weights: output/ppyolo_roadsign_kunlun/model_final
- num_classes: 4
- finetune_exclude_pretrained_params: ['yolo_output']
- 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: 'bn'
- freeze_at: 0
- freeze_norm: false
- norm_decay: 0.
- depth: 50
- feature_maps: [3, 4, 5]
- variant: d
- dcn_v2_stages: [5]
- YOLOv3Head:
- 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]]
- norm_decay: 0.
- coord_conv: true
- iou_aware: true
- iou_aware_factor: 0.4
- scale_x_y: 1.05
- spp: true
- 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
- iou_aware_loss: IouAwareLoss
- IouLoss:
- loss_weight: 2.5
- max_height: 608
- max_width: 608
- IouAwareLoss:
- loss_weight: 1.0
- max_height: 608
- max_width: 608
- MatrixNMS:
- background_label: -1
- keep_top_k: 100
- normalized: false
- score_threshold: 0.01
- post_threshold: 0.01
- LearningRate:
- base_lr: 0.0001
- schedulers:
- - !PiecewiseDecay
- gamma: 0.1
- milestones:
- - 800
- - 110
- - !LinearWarmup
- start_factor: 0
- steps: 100
- OptimizerBuilder:
- optimizer:
- momentum: 0.9
- type: Momentum
- regularizer:
- factor: 0.0005
- type: L2
- TrainReader:
- inputs_def:
- fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
- num_max_boxes: 50
- dataset:
- !VOCDataSet
- dataset_dir: dataset/roadsign_voc
- anno_path: train.txt
- 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]
- ratio: 1.5
- - !RandomCrop {}
- - !RandomFlipImage
- is_normalized: false
- - !NormalizeBox {}
- - !PadBox
- num_max_boxes: 50
- - !BboxXYXY2XYWH {}
- batch_transforms:
- - !RandomShape
- sizes: [320]
- random_inter: True
- - !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
- 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]
- batch_size: 8
- shuffle: true
- mixup_epoch: 250
- drop_last: true
- worker_num: 2
- bufsize: 2
- use_process: false #true
- EvalReader:
- inputs_def:
- fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
- num_max_boxes: 50
- dataset:
- !VOCDataSet
- dataset_dir: dataset/roadsign_voc
- anno_path: valid.txt
- with_background: false
- sample_transforms:
- - !DecodeImage
- to_rgb: True
- - !ResizeImage
- target_size: 608
- interp: 2
- - !NormalizeImage
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- is_scale: True
- is_channel_first: false
- - !PadBox
- num_max_boxes: 50
- - !Permute
- to_bgr: false
- channel_first: True
- batch_size: 1
- drop_empty: false
- worker_num: 4
- bufsize: 2
- TestReader:
- inputs_def:
- image_shape: [3, 608, 608]
- fields: ['image', 'im_size', 'im_id']
- dataset:
- !ImageFolder
- anno_path: dataset/roadsign_voc/label_list.txt
- with_background: false
- sample_transforms:
- - !DecodeImage
- to_rgb: True
- - !ResizeImage
- target_size: 608
- interp: 2
- - !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
- batch_size: 1
|
