A new version of yolo has just been released, yolov10. Does luxonis plan to support this new version on their cameras?

Hi all, A new version of [DepthAI tools](https://tools.luxonis.com/) with support for YOLOv10 export is deployed. Decoding on the device can be tested using [this script.](https://github.com/luxonis/depthai-experiments/blob/master/gen2-yolo/device-decoding/main_api.py)

Hi @"EwoudPool"#1266 We don't yet have a conversion for V9, so can't say for sure. If we get enough customer demand, we will implement it. Not sure how much of an improvement it would be though. Thanks Jaka

@"jakaskerl"#p22996 Yolo V10 is a significant upgrade, we'd like to see it supported asap. See attached [upl-image-preview url=https://discuss.luxonis.com/assets/files/2024-05-27/1716819893-740913-screenshot-2024-05-27-at-162356.png]

In addition to higher MAP, YOLOv10 has far fewer params to the point where the 's' size model may be practical to run on the Myriad (depending on how many operators spill over). Would you be able to open source the firmware so the community can make these changes itself rather than Luxonis having to do this internally each time a new model comes out? Previously Intel has been a blocker to open sourcing the parts relating to the MX, but is this still the case? What about with RVC4?

Hi @"rmaxwell"#1300 I doubt we can make it opensource (not sure on the contracts). I have passed the feature-request to our ML team. Thanks, Jaka

Hey, Thanks for the thread everyone! We are actively working on adding support for YoloV10 to tools.luxonis.com and device (FW). No ETA we can commit to, but should be in the next few weeks. Unfortunately it is not easy for us to open source the firmware, so I'll have to ask for some patience. We are aware of constraints on that, so we are looking to simplify the process with RVC4. While I doubt we could expose FW directly, we are working on concept of HostNodes. Those can then run on your host in case of RVC2 (this might be inefficient if you are sending data back to the device) or directly on the device in case of RVC4.

Hi all, Looking forward to the v10 release, will it be available from the conversion API with version: Literal["v10"] = "v10" and at the URL "https://tools.luxonis.com/yolov10"? Thanks, Chris

@"ChrisCoutureDelValle"#p23072 Likely yes for the version, can't yet guarantee for the URL.

Hi all, A small update on adding YOLOv10 support: 1. We are waiting for the YOLOv10 support in the Ultralytics library to be able to add it to tools.luxonis.com. Otherwise, it's ready in the development environment. 2. We are working on adding FW YOLOv10 post-processing support.

@"NikitaSokovnin"#p23421 Awesome thanks for the update.

Hello all, Just wondering on progress for v10 availability. Thanks, Chris

Support for V10

JanCuhel

This seems like that your models are for some reason not compatible with the ones we are testing on. Could you please (both of you @ChrisCoutureDelValle and @arnavaggs) provide us with more information, for example, specify what is the source of the model you've used (e.g. did you downloaded from Ultralytics)? It would help me a lot if you'd share your models with me, so that I could take a closer look. You can either share it with me via Google Drive or you can send it to me via email. My email is jan.cuhel@luxonis.com.

Best,
Jan

ChrisCoutureDelValle

JanCuhel Following up its a standard custom trained model leveraging these weights. THU-MIG/yolov10releases/download/v1.1/yolov10n.pt

ChrisCoutureDelValle

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

@ChrisCoutureDelValle yes, you're right, we are using weights from Ultralytics. I'll check whether the weights from Ultralytics differ from the ones you are using and get back to you.

Best,

Jan

ChrisCoutureDelValle

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.

ChrisCoutureDelValle

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

ChrisCoutureDelValle

Have you tried to manually select YOLOv10 export option? And if not, could you please try that?

Best,
Jan

ChrisCoutureDelValle

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 just tried to export THU-MIG/yolov10releases/download/v1.1/yolov10n.pt with the both YOLOv10 and YOLOv8 option and it was successful, this seems like the training makes the weights somehow not compatible with the export. Could you please provide us with more details about your training of the model?

Best,
Jan

ChrisCoutureDelValle

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}'

JanCuhel

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.

ChrisCoutureDelValle

JanCuhel Hi Jan, any updates on the layer fix for the v10 conversion?

arnavaggs

JanCuhel

Hi Jan, just wanted to bump Chris' latest message.

JanCuhel

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

ChrisCoutureDelValle

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?

JanCuhel

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

ChrisCoutureDelValle

JanCuhel Thank you!

Thor

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

JanCuhel

Hi @Thor,

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

Best
Jan

JanCuhel

@ChrisCoutureDelValle you're welcome!

« Previous Page