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,
@@ -36,6 +35,6 @@
   "resolution": 560,
   "sa_nheads": 8,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
+  "transformers_version": "4.51.1",
   "two_stage": true
 }

configuration_rf_detr.py

@@ -6,7 +6,7 @@ from optimum.exporters.onnx.model_configs import ViTOnnxConfig
 
 ### 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"
+#DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
 
 class RFDetrConfig(PretrainedConfig):
     model_type = 'rf-detr'
@@ -24,7 +24,7 @@ class RFDetrConfig(PretrainedConfig):
         amp: bool = True,
         num_classes: int = 90,
         num_queries: int  = 300,
-        device: Literal["cpu", "cuda", "mps"] = DEVICE,
+        # device: Literal["cpu", "cuda", "mps"] = DEVICE,
         resolution: int = 560,
         group_detr: int = 13,
         gradient_checkpointing: bool = False,
@@ -40,7 +40,7 @@ class RFDetrConfig(PretrainedConfig):
         self.layer_norm = layer_norm
         self.amp = amp
         self.num_classes = num_classes
-        self.device = device
+        # self.device = device
         self.resolution = resolution
         self.group_detr = group_detr
         self.gradient_checkpointing = gradient_checkpointing

modeling_rf_detr.py

@@ -40,7 +40,7 @@ class RFDetrModelForObjectDetection(PreTrainedModel):
             layer_norm = config.layer_norm,
             amp = config.amp,
             num_classes = config.num_classes,
-            device = config.device,
+            #device = config.device,
             resolution = config.resolution,
             group_detr = config.group_detr,
             gradient_checkpointing = config.gradient_checkpointing,
@@ -106,7 +106,7 @@ 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"]#.to(device=self.config.device, dtype=torch.float32)
             # resize boxes to model's resolution
             boxes[:, [0, 2]] *= wr
             boxes[:, [1, 3]] *= hr
@@ -117,8 +117,8 @@ class RFDetrModelForObjectDetection(PreTrainedModel):
             # 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)
+            # if "labels" in label:
+            #     label["labels"] = label["labels"].to(self.config.device)
 
     def forward(self, pixel_values: torch.Tensor, pixel_mask: torch.Tensor, labels=None, **kwargs) -> ModelOutput:
         resize = Resize((self.config.resolution, self.config.resolution)) 
@@ -135,8 +135,8 @@ class RFDetrModelForObjectDetection(PreTrainedModel):
             self.criterion.training = False
 
         # resize pixel values and mask to model's resolution
-        pixel_values = pixel_values.to(self.config.device)
-        pixel_mask = pixel_mask.to(self.config.device)
+        # pixel_values = pixel_values.to(self.config.device)
+        # pixel_mask = pixel_mask.to(self.config.device)
         pixel_values = resize(pixel_values)
         pixel_mask = resize(pixel_mask)