Samuel Stainback

The model was trained with 1280x1024. The problem was the model export, actually. I didn't realize the export script needed the same size arguments to set the correct input size....

These are top-level using statements. They don't require braces like the older syntax. They are a feature of newer code. Use VS 2022 and the latest C# version. Alternatively, you...

I don't understand wtf he said fixed it... BUT... I was having the same issue and the key was the "Dimensions" property on the inherited class. I left it as...

the inherited class you write. for a custom model, he says you have to inherit from the yolomodel base class. it has a property for "dimensions." but, after reading more,...

Yeah, I've learned that in the past week or so. The anchors come from the yolo config files but I'm still not sure about strides (which all seem to be...

Once your model is in ONNX format, you can use Netron to inspect it and see the input/output. You use this info to set the values in your inherited model...

> Is this problem reproducible in the colab? I cannot reproduce it on my system. Maybe it might be something with your env? try setting up a new env and...

Also, to be very clear: I run the ultralytics docker image via Docker Desktop w/ WSL2 integration. This error *only* occurs when using the v5loader. However, if I run the...

> What happens when you run it without `v5Loader=True` It works then. However, there is another issue reported in [#363](https://github.com/ultralytics/ultralytics/issues/363) that is the reason I'm using the v5loader. My dataset...

> @sstainba looks there's something wrong about your PIL/ font. But this error occurs in the image-plotting process of the first epoch, actually it won't affect the training process itself,...