add pcb baseline config (#1455)

configs/pcb/README.md

+# 印刷电路板（PCB）瑕疵数据集模型
+- 印刷电路板（PCB）瑕疵数据集：[数据下载链接](http://robotics.pkusz.edu.cn/resources/dataset/)，是一个公共的合成PCB数据集，由北京大学发布，其中包含1386张图像以及6种缺陷（缺失孔，鼠标咬伤，开路，短路，杂散，伪铜），用于检测，分类和配准任务。我们选取了其中适用与检测任务的693张图像，随机选择593张图像作为训练集，100张图像作为验证集。AIStudio数据集链接：[印刷电路板（PCB）瑕疵数据集](https://aistudio.baidu.com/aistudio/datasetdetail/52914)
+
+## 已提供的基线模型
+- YOLOv3-Darknet
+- Faster-RCNN-R34
+- FCOS-R50-FPN
+
+## 优化后高mAP模型
+将在9月29日发布,敬请期待。

configs/pcb/faster_fpn_reader.yml

+TrainReader:
+  inputs_def:
+    fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd']
+  dataset:
+    !COCODataSet
+    image_dir: images
+    anno_path: Annotations/train.json
+    dataset_dir: /home/aistudio/work/PCB_DATASET
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !RandomFlipImage
+    prob: 0.5
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    target_size: 800
+    max_size: 1333
+    interp: 1
+    use_cv2: true
+  - !Permute
+    to_bgr: false
+    channel_first: true
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+    use_padded_im_info: false
+  batch_size: 1
+  shuffle: true
+  worker_num: 2
+  use_process: false
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_info', 'im_id', 'im_shape']
+  dataset:
+    !COCODataSet
+    image_dir: images
+    anno_path: Annotations/val.json
+    dataset_dir: /home/aistudio/work/PCB_DATASET
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+    with_mixup: false
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    interp: 1
+    max_size: 1333
+    target_size: 800
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+    use_padded_im_info: true
+  batch_size: 1
+  shuffle: false
+  drop_empty: false
+  worker_num: 2
+
+TestReader:
+  inputs_def:
+    # set image_shape if needed
+    fields: ['image', 'im_info', 'im_id', 'im_shape']
+  dataset:
+    !ImageFolder
+    anno_path: /home/aistudio/work/PCB_DATASET/Annotations/val.json
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+    with_mixup: false
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    interp: 1
+    max_size: 1333
+    target_size: 800
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 32
+    use_padded_im_info: true
+  batch_size: 1
+  shuffle: false

configs/pcb/faster_rcnn_r34_fpn_1x.yml

+architecture: FasterRCNN
+max_iters: 3558
+use_gpu: true
+snapshot_iter: 1000
+log_smooth_window: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar
+metric: COCO
+weights: output/faster_rcnn_r34_fpn_1x/model_final
+num_classes: 7
+
+FasterRCNN:
+  backbone: ResNet
+  fpn: FPN
+  rpn_head: FPNRPNHead
+  roi_extractor: FPNRoIAlign
+  bbox_head: BBoxHead
+  bbox_assigner: BBoxAssigner
+
+ResNet:
+  norm_type: bn
+  norm_decay: 0.
+  depth: 34
+  feature_maps: [2, 3, 4, 5]
+  freeze_at: 2
+
+FPN:
+  min_level: 2
+  max_level: 6
+  num_chan: 256
+  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
+
+FPNRPNHead:
+  anchor_generator:
+    anchor_sizes: [32, 64, 128, 256, 512]
+    aspect_ratios: [0.5, 1.0, 2.0]
+    stride: [16.0, 16.0]
+    variance: [1.0, 1.0, 1.0, 1.0]
+  anchor_start_size: 32
+  min_level: 2
+  max_level: 6
+  num_chan: 256
+  rpn_target_assign:
+    rpn_batch_size_per_im: 256
+    rpn_fg_fraction: 0.5
+    rpn_positive_overlap: 0.7
+    rpn_negative_overlap: 0.3
+    rpn_straddle_thresh: 0.0
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 2000
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+FPNRoIAlign:
+  canconical_level: 4
+  canonical_size: 224
+  min_level: 2
+  max_level: 5
+  box_resolution: 7
+  sampling_ratio: 2
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
+  bg_thresh_lo: 0.0
+  bg_thresh_hi: 0.5
+  fg_fraction: 0.25
+  fg_thresh: 0.5
+
+BBoxHead:
+  head: TwoFCHead
+  nms:
+    keep_top_k: 100
+    nms_threshold: 0.5
+    score_threshold: 0.05
+
+TwoFCHead:
+  mlp_dim: 1024
+
+LearningRate:
+  base_lr: 0.0025
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [2372, 3261]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+_READER_: 'faster_fpn_reader.yml'
+TrainReader:
+  batch_size: 2

configs/pcb/fcos_r50_fpn_1x.yml

+architecture: FCOS
+max_iters: 3558
+use_gpu: true
+snapshot_iter: 1000
+log_smooth_window: 20
+log_iter: 20
+save_dir: output
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
+metric: COCO
+weights: output/fcos_r50_fpn_1x/model_final
+num_classes: 6
+
+FCOS:
+  backbone: ResNet
+  fpn: FPN
+  fcos_head: FCOSHead
+
+ResNet:
+  norm_type: affine_channel
+  norm_decay: 0.
+  depth: 50
+  feature_maps: [3, 4, 5]
+  freeze_at: 2
+
+FPN:
+  min_level: 3
+  max_level: 7
+  num_chan: 256
+  use_c5: false
+  spatial_scale: [0.03125, 0.0625, 0.125]
+  has_extra_convs: true
+
+FCOSHead:
+  num_classes: 80
+  fpn_stride: [8, 16, 32, 64, 128]
+  num_convs: 4
+  norm_type: "gn"
+  fcos_loss: FCOSLoss
+  norm_reg_targets: True
+  centerness_on_reg: True
+  use_dcn_in_tower: False
+  nms: MultiClassNMS
+
+MultiClassNMS:
+  score_threshold: 0.025
+  nms_top_k: 1000
+  keep_top_k: 100
+  nms_threshold: 0.6
+  background_label: -1
+
+FCOSLoss:
+  loss_alpha: 0.25
+  loss_gamma: 2.0
+  iou_loss_type: "giou"
+  reg_weights: 1.0
+
+LearningRate:
+  base_lr: 0.00125
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [2372, 3261]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+TrainReader:
+  inputs_def:
+    fields: ['image', 'im_info', 'fcos_target']
+  dataset:
+    !COCODataSet
+    image_dir: images
+    anno_path: Annotations/train.json
+    dataset_dir: /home/aistudio/work/PCB_DATASET
+    with_background: false
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+  - !RandomFlipImage
+    prob: 0.5
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    target_size: 800
+    max_size: 1333
+    interp: 1
+    use_cv2: true
+  - !Permute
+    to_bgr: false
+    channel_first: true
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+    use_padded_im_info: false
+  - !Gt2FCOSTarget
+    object_sizes_boundary: [64, 128, 256, 512]
+    center_sampling_radius: 1.5
+    downsample_ratios: [8, 16, 32, 64, 128]
+    norm_reg_targets: True
+  batch_size: 2
+  shuffle: true
+  worker_num: 4
+  use_process: false
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_id', 'im_shape', 'im_info']
+  dataset:
+    !COCODataSet
+    image_dir: images
+    anno_path: Annotations/val.json
+    dataset_dir: /home/aistudio/work/PCB_DATASET
+    with_background: false
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+    with_mixup: false
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    target_size: 800
+    max_size: 1333
+    interp: 1
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+    use_padded_im_info: true
+  batch_size: 1
+  shuffle: false
+  worker_num: 2
+  use_process: false
+
+TestReader:
+  inputs_def:
+    # set image_shape if needed
+    fields: ['image', 'im_id', 'im_shape', 'im_info']
+  dataset:
+    !ImageFolder
+    anno_path: /home/aistudio/work/PCB_DATASET/Annotations/val.json
+    with_background: false
+  sample_transforms:
+  - !DecodeImage
+    to_rgb: true
+    with_mixup: false
+  - !NormalizeImage
+    is_channel_first: false
+    is_scale: true
+    mean: [0.485,0.456,0.406]
+    std: [0.229, 0.224,0.225]
+  - !ResizeImage
+    interp: 1
+    max_size: 1333
+    target_size: 800
+    use_cv2: true
+  - !Permute
+    channel_first: true
+    to_bgr: false
+  batch_transforms:
+  - !PadBatch
+    pad_to_stride: 128
+    use_padded_im_info: true
+  batch_size: 1
+  shuffle: false

configs/pcb/yolov3_darknet.yml

+architecture: YOLOv3
+use_gpu: true
+max_iters: 1780
+log_smooth_window: 20
+save_dir: output
+snapshot_iter: 1000
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar
+weights: output/yolov3_darknet/model_final
+num_classes: 6
+use_fine_grained_loss: false
+
+YOLOv3:
+  backbone: DarkNet
+  yolo_head: YOLOv3Head
+
+DarkNet:
+  norm_type: sync_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:
+  # batch_size here is only used for fine grained loss, not used
+  # for training batch_size setting, training batch_size setting
+  # is in configs/yolov3_reader.yml TrainReader.batch_size, batch
+  # size here should be set as same value as TrainReader.batch_size
+  batch_size: 8
+  ignore_thresh: 0.7
+  label_smooth: true
+
+LearningRate:
+  base_lr: 0.00025
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 1180
+    - 1630
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+_READER_: 'yolov3_reader.yml'

configs/pcb/yolov3_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/train.json
+      dataset_dir: /home/aistudio/work/PCB_DATASET
+      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: [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: 8
+  shuffle: true
+  mixup_epoch: 250
+  drop_last: true
+  worker_num: 8
+  bufsize: 16
+  use_process: true
+
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_size', 'im_id']
+    num_max_boxes: 50
+  dataset:
+    !COCODataSet
+      image_dir: images
+      anno_path: Annotations/val.json
+      dataset_dir: /home/aistudio/work/PCB_DATASET
+      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: 8
+  drop_empty: false
+  worker_num: 8
+  bufsize: 16
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 608, 608]
+    fields: ['image', 'im_size', 'im_id']
+  dataset:
+    !ImageFolder
+      anno_path: /home/aistudio/work/PCB_DATASET/Annotations/val.json
+      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