Patrícia Mika Sakugawa comments

Repositories
Issues
Comments

Results 5 comments of


                                            Patrícia Mika Sakugawa

When using data tensors as input to a model, you should specify the `steps` argument.

I am having the same error for inference. Do you know where the problem might be? `Traceback (most recent call last): File "detect.py", line 42, in pred_bbox = model.predict(img_tensor) File...

When using data tensors as input to a model, you should specify the `steps` argument.

I am testing with the kite.jpg image The print(img_tensor) gives: `Tensor("ExpandDims:0", shape=(1, 608, 608, 3), dtype=float32)`

When using data tensors as input to a model, you should specify the `steps` argument.

Yes, same error

When using data tensors as input to a model, you should specify the `steps` argument.

Ok, I will give it a try. Thanks!

Grayscale prediction

Thanks for the reply It doesn't work. Even adjusting other parts of the code, the output isn't the same as from darknet