更换文档检测模型

paddle_detection/configs/yolov3/_base_/optimizer_270e.yml

@@ -0,0 +1,21 @@
+epoch: 270
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 216
+    - 243
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

paddle_detection/configs/yolov3/_base_/optimizer_40e.yml

@@ -0,0 +1,21 @@
+epoch: 40
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - name: PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 32
+    - 36
+  - name: LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 100
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

paddle_detection/configs/yolov3/_base_/yolov3_darknet53.yml

@@ -0,0 +1,41 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/DarkNet53_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: DarkNet
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+DarkNet:
+  depth: 53
+  return_idx: [2, 3, 4]
+
+# use default config
+# YOLOv3FPN:
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_mobilenet_v1.yml

@@ -0,0 +1,43 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV1_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: MobileNet
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNet:
+  scale: 1
+  feature_maps: [4, 6, 13]
+  with_extra_blocks: false
+  extra_block_filters: []
+
+# use default config
+# YOLOv3FPN:
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_mobilenet_v3_large.yml

@@ -0,0 +1,44 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_large_x1_0_ssld_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: MobileNetV3
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  model_name: large
+  scale: 1.
+  with_extra_blocks: false
+  extra_block_filters: []
+  feature_maps: [7, 13, 16]
+
+# use default config
+# YOLOv3FPN:
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_mobilenet_v3_small.yml

@@ -0,0 +1,44 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_small_x1_0_ssld_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: MobileNetV3
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  model_name: small
+  scale: 1.
+  with_extra_blocks: false
+  extra_block_filters: []
+  feature_maps: [4, 9, 12]
+
+# use default config
+# YOLOv3FPN:
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_r34.yml

@@ -0,0 +1,41 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet34_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: ResNet
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 34
+  return_idx: [1, 2, 3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_r50vd_dcn.yml

@@ -0,0 +1,45 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams
+norm_type: sync_bn
+
+YOLOv3:
+  backbone: ResNet
+  neck: YOLOv3FPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 50
+  variant: d
+  return_idx: [1, 2, 3]
+  dcn_v2_stages: [3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
+
+# YOLOv3FPN:
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    nms_threshold: 0.45
+    nms_top_k: 1000

paddle_detection/configs/yolov3/_base_/yolov3_reader.yml

@@ -0,0 +1,44 @@
+worker_num: 2
+TrainReader:
+  inputs_def:
+    num_max_boxes: 50
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - 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
+  drop_last: true
+  mixup_epoch: 250
+  use_shared_memory: true
+
+EvalReader:
+  inputs_def:
+    num_max_boxes: 50
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 608, 608]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1