JanCuhel I see that for the unit test, the Luxonis team is leveraging these weights. I have been using the weights directly from the yolov10 repo, should the weights from the v10 repo and ultralytics weights not be identical?

`'yolov10n': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10n.pt',`

'yolov10s': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10s.pt',

'yolov10m': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10m.pt',

'yolov10b': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10b.pt',

'yolov10l': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10l.pt',

'yolov10x': 'https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov10x.pt',

    JanCuhel Hi Jan, just as a follow up I attempted to upload a custom model trained on the ultralytics weights in the same fashion and ran into the same error.

      In addition when manually uploading the custom v10 weights from the ultralytics weights and the standard v10 weights and this is the error that occurs, I believe there may possibly be an error in the backend when detecting the custom v10 weights?
      Automatic version detected: YoloV8 (detection only)

        JanCuhel When I try to manually select the YOLOv10 export option with the weights, I get this in response "Automatic version detected: YoloV8 (detection only)".

            JanCuhel

            I will email you sample output weights, training is as follows with the best.pt weights selected.

            d_config = int(dataset_config["epochs"])`

            y_pths = str(dataset_config["yaml"])

            wtgs = str(dataset_config["weights"])

            batch_size = 32

            img_size = 640

            train_cmd = f'yolo detect train model=weights/{wtgs} data={y_pths} batch={batch_size} epochs={d_config} imgsz={img_size} workers=8 device=0 name={x_name}'

              ChrisCoutureDelValle

              and do you manually select the export version, did you do it after uploading the weights or before? You must do it only after the weights are uploaded, because whenever a model's weights are uploaded the automatic version detector is executed to suggest you a detection version, however you are still free to choose whatever export option you want.

                  Hi @ChrisCoutureDelValle and @arnavaggs,

                  Apologies, I somehow didn't notice your messages. As I already wrote you via email, we found the source of the issue and are currently in the stage of implementing the fix into our tools. As soon as the fix will be deployed, I'll let you know. It should be in the following days.

                  Best,
                  Jan

                  6 days later

                  Hi @JanCuhel @jakaskerl ,

                  It's been 25 days since this thread was set to Answered and and the tool is still non-functioning for v10. Were there more issues than just the export layer causing a delay?

                  Hi @ChrisCoutureDelValle and @arnavaggs,

                  I'm sorry for the delay in my response. As you mentioned, some unexpected hiccups were on the way, but they're all solved now, and the fix has been deployed. I tested it on the model you shared with me, and the model was exported.

                  Best,
                  Jan

                    In the end, is it faster or slower than yoloV8 on RCV2?

                    Hi @Thor,

                    in the end, the YOLOv10 is still slightly slower than YOLOv8. Here are the measured latencies:

                    Best
                    Jan