Add PlainDETR

src/transformers/__init__.py

@@ -403,6 +403,7 @@
     "models.depth_anything": ["DepthAnythingConfig"],
     "models.depth_pro": ["DepthProConfig"],
     "models.detr": ["DetrConfig"],
+    "models.plaindetr": ["PlaindetrConfig"],
     "models.dialogpt": [],
     "models.diffllama": ["DiffLlamaConfig"],
     "models.dinat": ["DinatConfig"],
@@ -2212,6 +2213,14 @@
             "DetrPreTrainedModel",
         ]
     )
+    _import_structure["models.plaindetr"].extend(
+        [
+            "PlaindetrForObjectDetection",
+            "PlaindetrForSegmentation",
+            "PlaindetrModel",
+            "PlaindetrPreTrainedModel",
+        ]
+    )
     _import_structure["models.diffllama"].extend(
         [
             "DiffLlamaForCausalLM",
@@ -5551,6 +5560,7 @@
     from .models.depth_anything import DepthAnythingConfig
     from .models.depth_pro import DepthProConfig
     from .models.detr import DetrConfig
+    from .models.plaindetr import PlaindetrConfig
     from .models.diffllama import DiffLlamaConfig
     from .models.dinat import DinatConfig
     from .models.dinov2 import Dinov2Config
@@ -7255,6 +7265,12 @@
             DetrModel,
             DetrPreTrainedModel,
         )
+        from .models.plaindetr import (
+            PlaindetrForObjectDetection,
+            PlaindetrForSegmentation,
+            PlaindetrModel,
+            PlaindetrPreTrainedModel,
+        )
         from .models.diffllama import (
             DiffLlamaForCausalLM,
             DiffLlamaForQuestionAnswering,

src/transformers/models/__init__.py

@@ -76,6 +76,7 @@
     depth_anything,
     depth_pro,
     detr,
+    plaindetr,
     dialogpt,
     diffllama,
     dinat,

src/transformers/models/auto/configuration_auto.py

@@ -94,6 +94,7 @@
         ("depth_pro", "DepthProConfig"),
         ("deta", "DetaConfig"),
         ("detr", "DetrConfig"),
+        ("plaindetr", "PlaindetrConfig"),
         ("diffllama", "DiffLlamaConfig"),
         ("dinat", "DinatConfig"),
         ("dinov2", "Dinov2Config"),
@@ -423,6 +424,7 @@
         ("depth_pro", "DepthPro"),
         ("deta", "DETA"),
         ("detr", "DETR"),
+        ("plaindetr", "plaindetr"),
         ("dialogpt", "DialoGPT"),
         ("diffllama", "DiffLlama"),
         ("dinat", "DiNAT"),

src/transformers/models/auto/feature_extraction_auto.py

@@ -55,6 +55,7 @@
         ("deformable_detr", "DeformableDetrFeatureExtractor"),
         ("deit", "DeiTFeatureExtractor"),
         ("detr", "DetrFeatureExtractor"),
+        ("plaindetr", "PlaindetrFeatureExtractor"),
         ("dinat", "ViTFeatureExtractor"),
         ("donut-swin", "DonutFeatureExtractor"),
         ("dpt", "DPTFeatureExtractor"),

src/transformers/models/auto/modeling_auto.py

@@ -92,6 +92,7 @@
         ("depth_pro", "DepthProModel"),
         ("deta", "DetaModel"),
         ("detr", "DetrModel"),
+        ("plaindetr", "PlaindetrModel"),
         ("diffllama", "DiffLlamaModel"),
         ("dinat", "DinatModel"),
         ("dinov2", "Dinov2Model"),
@@ -607,6 +608,7 @@
         ("depth_pro", "DepthProModel"),
         ("deta", "DetaModel"),
         ("detr", "DetrModel"),
+        ("plaindetr", "PlaindetrModel"),
         ("dinat", "DinatModel"),
         ("dinov2", "Dinov2Model"),
         ("dinov2_with_registers", "Dinov2WithRegistersModel"),
@@ -740,6 +742,7 @@
         # Do not add new models here, this class will be deprecated in the future.
         # Model for Image Segmentation mapping
         ("detr", "DetrForSegmentation"),
+        ("plaindetr", "PlaindetrForSegmentation"),
     ]
 )
 
@@ -769,6 +772,7 @@
     [
         # Model for Universal Segmentation mapping
         ("detr", "DetrForSegmentation"),
+        ("plaindetr", "PlaindetrForSegmentation"),
         ("mask2former", "Mask2FormerForUniversalSegmentation"),
         ("maskformer", "MaskFormerForInstanceSegmentation"),
         ("oneformer", "OneFormerForUniversalSegmentation"),
@@ -906,6 +910,7 @@
         ("deformable_detr", "DeformableDetrForObjectDetection"),
         ("deta", "DetaForObjectDetection"),
         ("detr", "DetrForObjectDetection"),
+        ("plaindetr", "PlaindetrForObjectDetection"),
         ("rt_detr", "RTDetrForObjectDetection"),
         ("rt_detr_v2", "RTDetrV2ForObjectDetection"),
         ("table-transformer", "TableTransformerForObjectDetection"),

src/transformers/models/plaindetr/__init__.py

@@ -0,0 +1,28 @@
+# Copyright 2025 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from typing import TYPE_CHECKING
+
+from ...utils import _LazyModule
+from ...utils.import_utils import define_import_structure
+
+
+if TYPE_CHECKING:
+    from .configuration_plaindetr import *
+    from .modeling_plaindetr import *
+else:
+    import sys
+
+    _file = globals()["__file__"]
+    sys.modules[__name__] = _LazyModule(__name__, _file, define_import_structure(_file), module_spec=__spec__)