| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129 |
- architecture: YOLOv3
- use_gpu: true
- max_iters: 20000
- log_iter: 20
- save_dir: output
- snapshot_iter: 200
- metric: VOC
- map_type: 11point
- pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar
- weights: output/yolov3_mobilenet_v1_fruit/best_model
- num_classes: 3
- finetune_exclude_pretrained_params: ['yolo_output']
- use_fine_grained_loss: false
- YOLOv3:
- backbone: MobileNet
- yolo_head: YOLOv3Head
- MobileNet:
- norm_type: sync_bn
- norm_decay: 0.
- conv_group_scale: 1
- with_extra_blocks: false
- 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: 0.00001
- schedulers:
- - !PiecewiseDecay
- gamma: 0.1
- milestones:
- - 15000
- - 18000
- - !LinearWarmup
- start_factor: 0.
- steps: 100
- OptimizerBuilder:
- optimizer:
- momentum: 0.9
- type: Momentum
- regularizer:
- factor: 0.0005
- type: L2
- _READER_: 'yolov3_reader.yml'
- # will merge TrainReader into yolov3_reader.yml
- TrainReader:
- inputs_def:
- image_shape: [3, 608, 608]
- fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
- num_max_boxes: 50
- dataset:
- !VOCDataSet
- dataset_dir: dataset/fruit
- anno_path: train.txt
- with_background: false
- use_default_label: false
- sample_transforms:
- - !DecodeImage
- to_rgb: true
- with_mixup: false
- - !NormalizeBox {}
- - !ExpandImage
- max_ratio: 4.0
- mean: [123.675, 116.28, 103.53]
- prob: 0.5
- - !RandomInterpImage
- max_size: 0
- target_size: 608
- - !RandomFlipImage
- is_normalized: true
- prob: 0.5
- - !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
- - !BboxXYXY2XYWH {}
- batch_transforms:
- - !RandomShape
- sizes: [608]
- - !Permute
- channel_first: true
- to_bgr: false
- batch_size: 1
- shuffle: true
- mixup_epoch: -1
- EvalReader:
- batch_size: 1
- inputs_def:
- image_shape: [3, 608, 608]
- fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
- num_max_boxes: 50
- dataset:
- !VOCDataSet
- dataset_dir: dataset/fruit
- anno_path: val.txt
- use_default_label: false
- with_background: false
- TestReader:
- batch_size: 1
- dataset:
- !ImageFolder
- anno_path: dataset/fruit/label_list.txt
- use_default_label: false
- with_background: false
|
