how to predict multiple outputs with keras model?

187 views Asked by You Hur At 14 November 2019 at 14:24

i have a h5 model with 2 dense outputs.

i wanted to predict the values with a single camera but i got this error message.

degree = float(model.predict(image, batch_size=1))
TypeError: only size-1 arrays can be converted to Python scalars

the predict values must be 2 so i guess it's a dimension problem because it did work well with a model file which has 1 dense output.

I tried put np.array before model.predict but i got a same error message.

How should i change the prediction code?

TechQA.