fix: Add and forward timm_model_kwargs to timm.create_model

Author: harshaljanjani

src/transformers/models/omdet_turbo/configuration_omdet_turbo.py

@@ -149,8 +149,7 @@ def __init__(
         # Init timm backbone with hardcoded values for BC
         timm_default_kwargs = {
             "out_indices": [1, 2, 3],
-            "img_size": image_size,
-            "always_partition": True,
+            "timm_model_kwargs": {"img_size": image_size, "always_partition": True},
         }
         backbone_config, kwargs = consolidate_backbone_kwargs_to_config(
             backbone_config=backbone_config,
@@ -161,6 +160,16 @@ def __init__(
             **kwargs,
         )
 
+        if getattr(backbone_config, "model_type", None) == "timm_backbone" and not getattr(
+            backbone_config, "timm_model_kwargs", None
+        ):
+            timm_extra = {}
+            for attr in ("img_size", "always_partition"):
+                if hasattr(backbone_config, attr):
+                    timm_extra[attr] = getattr(backbone_config, attr)
+            if timm_extra:
+                backbone_config.timm_model_kwargs = timm_extra
+
         if text_config is None:
             logger.info("`text_config` is `None`. Initializing the config with the default `clip_text_model`")
             text_config = CONFIG_MAPPING["clip_text_model"]()

src/transformers/models/timm_backbone/configuration_timm_backbone.py

@@ -31,6 +31,8 @@ class TimmBackboneConfig(BackboneConfigMixin, PreTrainedConfig):
         Whether to output only the features or also the logits.
     freeze_batch_norm_2d (`bool`, *optional*, defaults to `False`):
         Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`.
+    timm_model_kwargs (`dict`, *optional*):
+        Additional keyword arguments to pass to `timm.create_model` (e.g. `{"img_size": 640}`).
 
     Example:
     ```python
@@ -57,6 +59,7 @@ def __init__(
         out_indices=None,
         freeze_batch_norm_2d=False,
         output_stride=None,
+        timm_model_kwargs=None,
         **kwargs,
     ):
         self.backbone = backbone
@@ -65,6 +68,7 @@ def __init__(
         self.out_indices = out_indices if out_indices is not None else [-1]
         self.output_stride = output_stride
         self.freeze_batch_norm_2d = freeze_batch_norm_2d
+        self.timm_model_kwargs = timm_model_kwargs if timm_model_kwargs is not None else {}
 
         super().__init__(**kwargs)
 

src/transformers/models/timm_backbone/modeling_timm_backbone.py

@@ -49,6 +49,7 @@ def __init__(self, config, **kwargs):
         out_indices = config.out_indices if getattr(config, "out_indices", None) is not None else (-1,)
         pretrained = kwargs.pop("pretrained", False)
         in_chans = kwargs.pop("in_chans", config.num_channels)
+        timm_model_kwargs = getattr(config, "timm_model_kwargs", {})
 
         backbone = timm.create_model(
             config.backbone,
@@ -58,6 +59,7 @@ def __init__(self, config, **kwargs):
             in_chans=in_chans,
             out_indices=out_indices,
             output_stride=config.output_stride,
+            **timm_model_kwargs,
             **kwargs,
         )