更换文档检测模型

paddle_detection/configs/dino/_base_/dino_focalnet.yml

@@ -0,0 +1,45 @@
+architecture: DETR
+# pretrain_weights: # rewrite in FocalNet.pretrained in ppdet/modeling/backbones/focalnet.py
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/focalnet_large_lrf_384_fl4_pretrained.pdparams
+hidden_dim: 256
+use_focal_loss: True
+
+DETR:
+  backbone: FocalNet
+  transformer: DINOTransformer
+  detr_head: DINOHead
+  post_process: DETRPostProcess
+
+FocalNet:
+  arch: 'focalnet_L_384_22k_fl4'
+  out_indices: [1, 2, 3]
+  pretrained: https://bj.bcebos.com/v1/paddledet/models/pretrained/focalnet_large_lrf_384_fl4_pretrained.pdparams
+
+DINOTransformer:
+  num_queries: 900
+  position_embed_type: sine
+  num_levels: 4
+  nhead: 8
+  num_encoder_layers: 6
+  num_decoder_layers: 6
+  dim_feedforward: 2048
+  dropout: 0.0
+  activation: relu
+  pe_temperature: 20
+  pe_offset: 0.0
+  num_denoising: 100
+  label_noise_ratio: 0.5
+  box_noise_scale: 1.0
+  learnt_init_query: True
+
+DINOHead:
+  loss:
+    name: DINOLoss
+    loss_coeff: {class: 1, bbox: 5, giou: 2}
+    aux_loss: True
+    matcher:
+      name: HungarianMatcher
+      matcher_coeff: {class: 2, bbox: 5, giou: 2}
+
+DETRPostProcess:
+  num_top_queries: 300

paddle_detection/configs/dino/_base_/dino_r50.yml

@@ -0,0 +1,49 @@
+architecture: DETR
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+hidden_dim: 256
+use_focal_loss: True
+
+
+DETR:
+  backbone: ResNet
+  transformer: DINOTransformer
+  detr_head: DINOHead
+  post_process: DETRPostProcess
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [1, 2, 3]
+  lr_mult_list: [0.0, 0.1, 0.1, 0.1]
+  num_stages: 4
+
+DINOTransformer:
+  num_queries: 900
+  position_embed_type: sine
+  num_levels: 4
+  nhead: 8
+  num_encoder_layers: 6
+  num_decoder_layers: 6
+  dim_feedforward: 2048
+  dropout: 0.0
+  activation: relu
+  pe_temperature: 20
+  pe_offset: 0.0
+  num_denoising: 100
+  label_noise_ratio: 0.5
+  box_noise_scale: 1.0
+  learnt_init_query: True
+
+DINOHead:
+  loss:
+    name: DINOLoss
+    loss_coeff: {class: 1, bbox: 5, giou: 2}
+    aux_loss: True
+    matcher:
+      name: HungarianMatcher
+      matcher_coeff: {class: 2, bbox: 5, giou: 2}
+
+DETRPostProcess:
+  num_top_queries: 300

paddle_detection/configs/dino/_base_/dino_reader.yml

@@ -0,0 +1,40 @@
+worker_num: 4
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - RandomFlip: {prob: 0.5}
+    - RandomSelect: { transforms1: [ RandomShortSideResize: { short_side_sizes: [ 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800 ], max_size: 1333 } ],
+                      transforms2: [
+                          RandomShortSideResize: { short_side_sizes: [ 400, 500, 600 ] },
+                          RandomSizeCrop: { min_size: 384, max_size: 600 },
+                          RandomShortSideResize: { short_side_sizes: [ 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800 ], max_size: 1333 } ]
+    }
+    - NormalizeImage: {is_scale: true, mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225]}
+    - NormalizeBox: {}
+    - BboxXYXY2XYWH: {}
+    - Permute: {}
+  batch_transforms:
+    - PadMaskBatch: {pad_to_stride: -1, return_pad_mask: true}
+  batch_size: 4
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+  use_shared_memory: false
+
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [800, 1333], keep_ratio: True}
+    - NormalizeImage: {is_scale: true, mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225]}
+    - Permute: {}
+  batch_size: 1
+
+
+TestReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [800, 1333], keep_ratio: True}
+    - 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/dino/_base_/dino_swin.yml

@@ -0,0 +1,46 @@
+architecture: DETR
+# pretrain_weights: # rewrite in SwinTransformer.pretrained in ppdet/modeling/backbones/swin_transformer.py
+hidden_dim: 256
+use_focal_loss: True
+
+DETR:
+  backbone: SwinTransformer
+  transformer: DINOTransformer
+  detr_head: DINOHead
+  post_process: DETRPostProcess
+
+SwinTransformer:
+  arch: 'swin_L_384' # ['swin_T_224', 'swin_S_224', 'swin_B_224', 'swin_L_224', 'swin_B_384', 'swin_L_384']
+  ape: false
+  drop_path_rate: 0.2
+  patch_norm: true
+  out_indices: [1, 2, 3]
+
+DINOTransformer:
+  num_queries: 900
+  position_embed_type: sine
+  num_levels: 4
+  nhead: 8
+  num_encoder_layers: 6
+  num_decoder_layers: 6
+  dim_feedforward: 2048
+  dropout: 0.0
+  activation: relu
+  pe_temperature: 10000
+  pe_offset: -0.5
+  num_denoising: 100
+  label_noise_ratio: 0.5
+  box_noise_scale: 1.0
+  learnt_init_query: True
+
+DINOHead:
+  loss:
+    name: DINOLoss
+    loss_coeff: {class: 1, bbox: 5, giou: 2}
+    aux_loss: True
+    matcher:
+      name: HungarianMatcher
+      matcher_coeff: {class: 2, bbox: 5, giou: 2}
+
+DETRPostProcess:
+  num_top_queries: 300

paddle_detection/configs/dino/_base_/optimizer_1x.yml

@@ -0,0 +1,16 @@
+epoch: 12
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [11]
+    use_warmup: false
+
+OptimizerBuilder:
+  clip_grad_by_norm: 0.1
+  regularizer: false
+  optimizer:
+    type: AdamW
+    weight_decay: 0.0001

paddle_detection/configs/dino/_base_/optimizer_2x.yml

@@ -0,0 +1,16 @@
+epoch: 24
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [20]
+    use_warmup: false
+
+OptimizerBuilder:
+  clip_grad_by_norm: 0.1
+  regularizer: false
+  optimizer:
+    type: AdamW
+    weight_decay: 0.0001

paddle_detection/configs/dino/_base_/optimizer_3x.yml

@@ -0,0 +1,16 @@
+epoch: 36
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [33]
+    use_warmup: false
+
+OptimizerBuilder:
+  clip_grad_by_norm: 0.1
+  regularizer: false
+  optimizer:
+    type: AdamW
+    weight_decay: 0.0001