Support FocalNet backbone and dino_focalnet

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: DETRBBoxPostProcess
+
+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}
+
+DETRBBoxPostProcess:
+  num_top_queries: 300

ppdet/modeling/architectures/detr.py

@@ -69,7 +69,7 @@ def _forward(self):
         body_feats = self.backbone(self.inputs)
 
         # Transformer
-        pad_mask = self.inputs['pad_mask'] if self.training else None
+        pad_mask = self.inputs.get('pad_mask', None)
         out_transformer = self.transformer(body_feats, pad_mask, self.inputs)
 
         # DETR Head

ppdet/modeling/backbones/__init__.py

@@ -35,6 +35,7 @@
 from . import vision_transformer
 from . import mobileone
 from . import trans_encoder
+from . import focalnet
 
 from .vgg import *
 from .resnet import *
@@ -57,6 +58,6 @@
 from .csp_darknet import *
 from .convnext import *
 from .vision_transformer import *
-from .vision_transformer import *
 from .mobileone import *
 from .trans_encoder import *
+from .focalnet import *