更换文档检测模型

paddle_detection/configs/ttfnet/_base_/optimizer_10x.yml

@@ -0,0 +1,19 @@
+epoch: 120
+
+LearningRate:
+  base_lr: 0.015
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [80, 110]
+  - !LinearWarmup
+    start_factor: 0.2
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0004
+    type: L2

paddle_detection/configs/ttfnet/_base_/optimizer_1x.yml

@@ -0,0 +1,19 @@
+epoch: 12
+
+LearningRate:
+  base_lr: 0.015
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.2
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0004
+    type: L2

paddle_detection/configs/ttfnet/_base_/optimizer_20x.yml

@@ -0,0 +1,20 @@
+epoch: 240
+
+LearningRate:
+  base_lr: 0.015
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [160, 220]
+  - !LinearWarmup
+    start_factor: 0.2
+    steps: 1000
+
+OptimizerBuilder:
+  clip_grad_by_norm: 35
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0004
+    type: L2

paddle_detection/configs/ttfnet/_base_/pafnet.yml

@@ -0,0 +1,40 @@
+architecture: TTFNet
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+TTFNet:
+  backbone: ResNet
+  neck: TTFFPN
+  ttf_head: TTFHead
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 50
+  variant: d
+  return_idx: [0, 1, 2, 3]
+  freeze_at: -1
+  norm_decay: 0.
+  dcn_v2_stages: [1, 2, 3]
+
+TTFFPN:
+  planes: [256, 128, 64]
+  shortcut_num: [3, 2, 1]
+
+TTFHead:
+  dcn_head: true
+  hm_loss:
+    name: CTFocalLoss
+    loss_weight: 1.
+  wh_loss:
+    name: GIoULoss
+    loss_weight: 5.
+    reduction: sum
+
+BBoxPostProcess:
+  decode:
+    name: TTFBox
+    max_per_img: 100
+    score_thresh: 0.01
+    down_ratio: 4

paddle_detection/configs/ttfnet/_base_/pafnet_lite.yml

@@ -0,0 +1,44 @@
+architecture: TTFNet
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_large_x1_0_ssld_pretrained.pdparams
+norm_type: sync_bn
+
+TTFNet:
+  backbone: MobileNetV3
+  neck: TTFFPN
+  ttf_head: TTFHead
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  scale: 1.0
+  model_name: large
+  feature_maps: [5, 8, 14, 17]
+  with_extra_blocks: true
+  lr_mult_list: [0.25, 0.25, 0.5, 0.5, 0.75]
+  conv_decay: 0.00001
+  norm_decay: 0.0
+  extra_block_filters: []
+
+TTFFPN:
+  planes: [96, 48, 24]
+  shortcut_num: [2, 2, 1]
+  lite_neck: true
+  fusion_method: concat
+
+TTFHead:
+  hm_head_planes: 48
+  wh_head_planes: 24
+  lite_head: true
+  hm_loss:
+    name: CTFocalLoss
+    loss_weight: 1.
+  wh_loss:
+    name: GIoULoss
+    loss_weight: 5.
+    reduction: sum
+
+BBoxPostProcess:
+  decode:
+    name: TTFBox
+    max_per_img: 100
+    score_thresh: 0.01
+    down_ratio: 4

paddle_detection/configs/ttfnet/_base_/pafnet_lite_reader.yml

@@ -0,0 +1,37 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - RandomDistort: {brightness: [-32., 32., 0.5], random_apply: False, random_channel: True}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {aspect_ratio: NULL, cover_all_box: True}
+    - RandomFlip: {}
+    - GridMask: {upper_iter: 300000}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512], random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375], is_scale: false}
+    - Permute: {}
+    - Gt2TTFTarget: {down_ratio: 4}
+    - PadBatch: {pad_to_stride: 32}
+  batch_size: 12
+  shuffle: true
+  drop_last: true
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [320, 320], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [320, 320], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false

paddle_detection/configs/ttfnet/_base_/pafnet_reader.yml

@@ -0,0 +1,36 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomDistort: {brightness: [-32., 32., 0.5], random_apply: false, random_channel: true}
+  - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+  - RandomCrop: {aspect_ratio: NULL, cover_all_box: True}
+  - RandomFlip: {prob: 0.5}
+  batch_transforms:
+  - BatchRandomResize: {target_size: [416, 448, 480, 512, 544, 576, 608, 640, 672], keep_ratio: false}
+  - NormalizeImage: {mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375], is_scale: false}
+  - Permute: {}
+  - Gt2TTFTarget: {down_ratio: 4}
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 18
+  shuffle: true
+  drop_last: true
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [512, 512], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [512, 512], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false

paddle_detection/configs/ttfnet/_base_/ttfnet_darknet53.yml

@@ -0,0 +1,35 @@
+architecture: TTFNet
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/DarkNet53_pretrained.pdparams
+
+TTFNet:
+  backbone: DarkNet
+  neck: TTFFPN
+  ttf_head: TTFHead
+  post_process: BBoxPostProcess
+
+DarkNet:
+  depth: 53
+  freeze_at: 0
+  return_idx: [1, 2, 3, 4]
+  norm_type: bn
+  norm_decay: 0.0004
+
+TTFFPN:
+  planes: [256, 128, 64]
+  shortcut_num: [3, 2, 1]
+
+TTFHead:
+  hm_loss:
+    name: CTFocalLoss
+    loss_weight: 1.
+  wh_loss:
+    name: GIoULoss
+    loss_weight: 5.
+    reduction: sum
+
+BBoxPostProcess:
+  decode:
+    name: TTFBox
+    max_per_img: 100
+    score_thresh: 0.01
+    down_ratio: 4

paddle_detection/configs/ttfnet/_base_/ttfnet_reader.yml

@@ -0,0 +1,33 @@
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomFlip: {prob: 0.5}
+  - Resize: {interp: 1, target_size: [512, 512], keep_ratio: False}
+  - NormalizeImage: {mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375], is_scale: false}
+  - Permute: {}
+  batch_transforms:
+  - Gt2TTFTarget: {down_ratio: 4}
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 12
+  shuffle: true
+  drop_last: true
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [512, 512], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 1, target_size: [512, 512], keep_ratio: False}
+  - NormalizeImage: {is_scale: false, mean: [123.675, 116.28, 103.53], std: [58.395, 57.12, 57.375]}
+  - Permute: {}
+  batch_size: 1
+  drop_last: false