Upload model

config.json

@@ -11,7 +11,6 @@
   "ca_nheads": 16,
   "dec_layers": 3,
   "dec_n_points": 2,
-  "device": "cpu",
   "encoder": "dinov2_windowed_small",
   "gradient_checkpointing": false,
   "group_detr": 13,

configuration_rf_detr.py

@@ -7,8 +7,6 @@ from optimum.utils import DummyVisionInputGenerator
 
 ### modified from https://github.com/roboflow/rf-detr/blob/main/rfdetr/config.py
 
-DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-
 class RFDetrConfig(PretrainedConfig):
     model_type = 'rf-detr'
 
@@ -25,7 +23,6 @@ class RFDetrConfig(PretrainedConfig):
         amp: bool = True,
         num_classes: int = 90,
         num_queries: int  = 300,
-        device: Literal["cpu", "cuda", "mps"] = DEVICE,
         resolution: int = 560,
         group_detr: int = 13,
         gradient_checkpointing: bool = False,
@@ -41,7 +38,6 @@ class RFDetrConfig(PretrainedConfig):
         self.layer_norm = layer_norm
         self.amp = amp
         self.num_classes = num_classes
-        self.device = device
         self.resolution = resolution
         self.group_detr = group_detr
         self.gradient_checkpointing = gradient_checkpointing

modeling_rf_detr.py

@@ -41,7 +41,6 @@ class RFDetrModelForObjectDetection(PreTrainedModel):
             layer_norm = config.layer_norm,
             amp = config.amp,
             num_classes = config.num_classes,
-            device = config.device,
             resolution = config.resolution,
             group_detr = config.group_detr,
             gradient_checkpointing = config.gradient_checkpointing,
@@ -112,16 +111,14 @@ class RFDetrModelForObjectDetection(PreTrainedModel):
         wr = self.config.resolution / float(w)
         
         for label in labels:
-            boxes = label["boxes"].to(device=self.config.device, dtype=torch.float32)
+            boxes = label["boxes"]
             # resize boxes to model's resolution
             boxes[:, [0, 2]] *= wr
             boxes[:, [1, 3]] *= hr
             # normalize to [0, 1] by model's resolution
             boxes[:] /= self.config.resolution
             label["boxes"] = boxes
-            if "labels" in label:
-                label["labels"] = label["labels"].to(self.config.device)
-
+            
     ### modified from https://github.com/roboflow/rf-detr/blob/develop/rfdetr/models/backbone/dinov2_with_windowed_attn.py
     def _onnx_interpolate_pos_encoding(self, embeddings: torch.Tensor, height: int, width: int) -> torch.Tensor:
         """