更换文档检测模型

paddle_detection/configs/picodet/_base_/optimizer_300e.yml

@@ -0,0 +1,18 @@
+epoch: 300
+
+LearningRate:
+  base_lr: 0.32
+  schedulers:
+  - name: CosineDecay
+    max_epochs: 300
+  - name: LinearWarmup
+    start_factor: 0.1
+    steps: 300
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.00004
+    type: L2

paddle_detection/configs/picodet/_base_/picodet_320_reader.yml

@@ -0,0 +1,42 @@
+worker_num: 6
+eval_height: &eval_height 320
+eval_width: &eval_width 320
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomCrop: {}
+  - RandomFlip: {prob: 0.5}
+  - RandomDistort: {}
+  batch_transforms:
+  - BatchRandomResize: {target_size: [256, 288, 320, 352, 384], random_size: True, random_interp: True, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  - PadGT: {}
+  batch_size: 64
+  shuffle: true
+  drop_last: true
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 8
+  shuffle: false
+
+
+TestReader:
+  inputs_def:
+    image_shape: [1, 3, *eval_height, *eval_width]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 1

paddle_detection/configs/picodet/_base_/picodet_416_reader.yml

@@ -0,0 +1,42 @@
+worker_num: 6
+eval_height: &eval_height 416
+eval_width: &eval_width 416
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomCrop: {}
+  - RandomFlip: {prob: 0.5}
+  - RandomDistort: {}
+  batch_transforms:
+  - BatchRandomResize: {target_size: [352, 384, 416, 448, 480], random_size: True, random_interp: True, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  - PadGT: {}
+  batch_size: 64
+  shuffle: true
+  drop_last: true
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 8
+  shuffle: false
+
+
+TestReader:
+  inputs_def:
+    image_shape: [1, 3, *eval_height, *eval_width]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 1

paddle_detection/configs/picodet/_base_/picodet_640_reader.yml

@@ -0,0 +1,42 @@
+worker_num: 6
+eval_height: &eval_height 640
+eval_width: &eval_width 640
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomCrop: {}
+  - RandomFlip: {prob: 0.5}
+  - RandomDistort: {}
+  batch_transforms:
+  - BatchRandomResize: {target_size: [576, 608, 640, 672, 704], random_size: True, random_interp: True, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  - PadGT: {}
+  batch_size: 32
+  shuffle: true
+  drop_last: true
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 8
+  shuffle: false
+
+
+TestReader:
+  inputs_def:
+    image_shape: [1, 3, *eval_height, *eval_width]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 1

paddle_detection/configs/picodet/_base_/picodet_v2.yml

@@ -0,0 +1,61 @@
+architecture: PicoDet
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/LCNet_x1_5_pretrained.pdparams
+
+PicoDet:
+  backbone: LCNet
+  neck: LCPAN
+  head: PicoHeadV2
+
+LCNet:
+  scale: 1.5
+  feature_maps: [3, 4, 5]
+
+LCPAN:
+  out_channels: 128
+  use_depthwise: True
+  num_features: 4
+
+PicoHeadV2:
+  conv_feat:
+    name: PicoFeat
+    feat_in: 128
+    feat_out: 128
+    num_convs: 4
+    num_fpn_stride: 4
+    norm_type: bn
+    share_cls_reg: True
+    use_se: True
+  fpn_stride: [8, 16, 32, 64]
+  feat_in_chan: 128
+  prior_prob: 0.01
+  reg_max: 7
+  cell_offset: 0.5
+  grid_cell_scale: 5.0
+  static_assigner_epoch: 100
+  use_align_head: True
+  static_assigner:
+    name: ATSSAssigner
+    topk: 9
+    force_gt_matching: False
+  assigner:
+    name: TaskAlignedAssigner
+    topk: 13
+    alpha: 1.0
+    beta: 6.0
+  loss_class:
+    name: VarifocalLoss
+    use_sigmoid: False
+    iou_weighted: True
+    loss_weight: 1.0
+  loss_dfl:
+    name: DistributionFocalLoss
+    loss_weight: 0.5
+  loss_bbox:
+    name: GIoULoss
+    loss_weight: 2.5
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 1000
+    keep_top_k: 100
+    score_threshold: 0.025
+    nms_threshold: 0.6