| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173 |
- architecture: YOLOv3
- use_gpu: false
- use_xpu: true
- max_iters: 1200
- log_iter: 1
- save_dir: output
- snapshot_iter: 200
- metric: VOC
- map_type: integral
- pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/yolov3_darknet.tar
- weights: output/yolov3_darknet_roadsign_xpu/model_final
- num_classes: 4
- finetune_exclude_pretrained_params: ['yolo_output']
- use_fine_grained_loss: false
- YOLOv3:
- backbone: DarkNet
- yolo_head: YOLOv3Head
- DarkNet:
- norm_type: bn
- norm_decay: 0.
- depth: 53
- 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.
- yolo_loss: YOLOv3Loss
- nms:
- background_label: -1
- keep_top_k: 100
- nms_threshold: 0.45
- nms_top_k: 1000
- normalized: false
- score_threshold: 0.01
- YOLOv3Loss:
- ignore_thresh: 0.7
- label_smooth: true
- LearningRate:
- base_lr: 0.000125 #0.00025
- schedulers:
- - !PiecewiseDecay
- gamma: 0.1
- milestones:
- - 800 #400
- - 1100 #550
- - !LinearWarmup
- start_factor: 0.
- steps: 200 #200
- 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, 352, 384, 416, 448, 480, 512, 544, 576, 608]
- 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 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: [[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: 2
- 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: 4
- 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
|
