fix

inference.py

@@ -20,12 +20,10 @@ class DepthPredictor:
     def predict(self, image):
         # prepare image for the model
         encoding = self.feature_extractor(image, return_tensors="pt")
-        self.img = image
         # forward pass
         with torch.no_grad():
             outputs = self.model(**encoding)
             predicted_depth = outputs.predicted_depth
-            
             # interpolate to original size
             prediction = torch.nn.functional.interpolate(
                                 predicted_depth.unsqueeze(1),
@@ -43,7 +41,7 @@ class DepthPredictor:
         depth = self.predict(image)
         # Step 2: Create an RGBD image from the RGB and depth image
         depth_o3d = o3d.geometry.Image(depth)
-        image_o3d = o3d.geometry.Image(image)
+        image_o3d = o3d.geometry.Image(np.array(image))
         rgbd_image = o3d.geometry.RGBDImage.create_from_color_and_depth(image_o3d, depth_o3d, convert_rgb_to_intensity=False)
         # Step 3: Create a PointCloud from the RGBD image
         pcd = o3d.geometry.PointCloud.create_from_rgbd_image(rgbd_image, o3d.camera.PinholeCameraIntrinsic(o3d.camera.PinholeCameraIntrinsicParameters.PrimeSenseDefault))