Hi,
New to Len Studio and ML for that matter. I used Microsoft Custom Vision to create an ML Model based on object detection. When I try to upload the model I receive the following message.Failed to add resource: The ONNX network's output 'model_outputs0' dimensions should be non-negative.
Is this because the 'object' I'm using is relatively flat (it's an image on shirt).
Thanks for your help!
What system are you using?
Have you downloaded the latest version of Lens Studio?
Is this issue causing Lens Studio to crash?
Version
Graphics
Attach a screenshot of the issue:
Name:
Email:
What is this most relevant to?
Please enter a brief description of your issue:
Unfortunately, it's likely due to the operating system or hardware you're using – since they don't meet the system requirements for Lens Studio.
Still, we hear you loud and clear, and are logging the issue in case there's ever a workaround we can provide!
Minimum Requirements
Operating System: Windows 10 (64 bit); MacOS 10.11+
Hardware: Minimum of Intel Core i3 2.5Ghz or AMD Phenom II 2.6Ghz with 4 GB RAM; Intel HD Graphics 4000 / Nvidia GeForce 710 / AMD Radeon HD 6450 or better; screen resolution of 1280x768 or higher
Keep an eye out for a followup email from us. We may have a couple more questions for you, or we might already have a solution to offer.
Happy creating!
Hi R. Scott Salandy-Defour,
Would mind sharing your model with us for investigation? Dimension here refers to the shape to your model output which should always be positive. For example a classification model that classifies `cats` from `dogs` should produce an output of dimension [1,2] (e.g [0.95, 0.05]), where the position of the largest value corresponds to the model's prediction.
Eric
Hi Eric, Thanks for getting back to me. Not sure if it's allowed but I tried to share with a google drive link. Let me know if I should try something else.
https://drive.google.com/drive/folders/1J9M8pKB1vQL0FbuFBbliwUS32ztPb4zH?usp=sharing
Hi R. Scott Salandy-Defour,
Thanks for sharing your model. I looked into your model and turns out it is expecting dynamic batch sizes which we do not support currently. Modifying the model input and output requires some non-trivial ML knowledge. Therefore I would recommend check models in our tutorials and also in Torchvision.models and see if any of them can solve your current task.
Thanks,
Eric