energy164 / bitmaponnxprediction Goto Github PK

Found this example and tried a model exported from teachablemachine to SavedModel and then tf2onnx.
With 10 images of two class each (left hand 10 pics, right hand 10 pics) I get 100% hitrate on website prior to export
using the training sample as prediction input.
Using tf2onnx 1.9.3 when converting to onnx I get a warning (Runtime warning) but it looks good else. (Tried 1.10 latest also)
Using the slight modified source code I do not get 100% hitrate with same input for prediction, about 50/60 % and unreliable.

No clue on how to validate onnx model.

Hi, I used this example to load in a pretrained multi class classifier in ONNX.

It was working fine for a while but today I upgraded the ONNX to 2.0.1 from 1.7.1 and now I receive an exception on this line:
var data = mlContext.Data.LoadFromEnumerable(new List());

Exception:
data.loadfromenumerable could not determine an idataview type

Because the imageInputData list is null I guess. I'm not too sure about it. What else can I make it?

Any advice would be appreciated. Thank you.