update yolov3

configs/ppyolo/ppyolo.yml

+architecture: YOLOv3
+use_gpu: true
+max_iters: 500000
+log_smooth_window: 100
+log_iter: 100
+save_dir: output
+snapshot_iter: 10000
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
+weights: output/ppyolo/model_final
+num_classes: 80
+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: 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:
+    background_label: -1
+    keep_top_k: 100
+    # nms_threshold: 0.45
+    # nms_top_k: 1000
+    normalized: false
+    score_threshold: 0.01
+  drop_block: true
+
+YOLOv3Loss:
+  batch_size: 24
+  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
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 400000
+    - 450000
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+_READER_: 'ppyolo_reader.yml'

configs/ppyolo/ppyolo_lb.yml

+architecture: YOLOv3
+use_gpu: true
+max_iters: 250000
+log_smooth_window: 100
+log_iter: 100
+save_dir: output
+snapshot_iter: 10000
+metric: COCO
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
+weights: output/ppyolo_lb/model_final
+num_classes: 80
+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: 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:
+    background_label: -1
+    keep_top_k: 100
+    # nms_threshold: 0.45
+    # nms_top_k: 1000
+    normalized: false
+    score_threshold: 0.01
+  drop_block: true
+
+YOLOv3Loss:
+  batch_size: 24
+  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
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 150000
+    - 200000
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+_READER_: 'ppyolo_reader.yml'

configs/ppyolo/ppyolo_reader.yml

+TrainReader:
+  inputs_def:
+    fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
+    num_max_boxes: 50
+  dataset:
+    !COCODataSet
+      image_dir: train2017
+      anno_path: annotations/instances_train2017.json
+      dataset_dir: dataset/coco
+      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: 24
+  shuffle: true
+  # mixup_epoch: 250
+  mixup_epoch: 25000
+  drop_last: true
+  worker_num: 8
+  bufsize: 4
+  use_process: true
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_size', 'im_id']
+    num_max_boxes: 50
+  dataset:
+    !COCODataSet
+      image_dir: val2017
+      anno_path: annotations/instances_val2017.json
+      dataset_dir: dataset/coco
+      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: 4
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 608, 608]
+    fields: ['image', 'im_size', 'im_id']
+  dataset:
+    !ImageFolder
+      anno_path: annotations/instances_val2017.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

ppdet/modeling/ops.py

@@ -30,9 +30,33 @@ __all__ = [
     'GenerateProposals', 'MultiClassNMS', 'BBoxAssigner', 'MaskAssigner',
     'RoIAlign', 'RoIPool', 'MultiBoxHead', 'SSDLiteMultiBoxHead',
     'SSDOutputDecoder', 'RetinaTargetAssign', 'RetinaOutputDecoder', 'ConvNorm',
-    'DeformConvNorm', 'MultiClassSoftNMS', 'LibraBBoxAssigner'
+    'DeformConvNorm', 'MultiClassSoftNMS', 'LibraBBoxAssigner', 'MultiClassMatrixNMS'
 ]
 
+@register
+@serializable
+class MultiClassMatrixNMS(object):
+    __op__ = fluid.layers.matrix_nms
+    __append_doc__ = True
+
+    def __init__(self,
+                 score_threshold=.05,
+                 post_threshold=.01,
+                 nms_top_k=-1,
+                 keep_top_k=100,
+                 use_gaussian=False,
+                 gaussian_sigma=2.0,
+                 normalized=False,
+                 background_label=0):
+        super(MultiClassMatrixNMS, self).__init__()
+        self.score_threshold = score_threshold
+        self.nms_top_k = nms_top_k
+        self.keep_top_k = keep_top_k
+        self.score_threshold = score_threshold
+        self.post_threshold = post_threshold
+        self.use_gaussian = use_gaussian
+        self.normalized = normalized
+        self.background_label = background_label
 
 def _conv_offset(input, filter_size, stride, padding, act=None, name=None):
     out_channel = filter_size * filter_size * 3