Tinyml Workshop Runtime Error

Running through the tutorial: [Nano 33 BLE Sense Rev2](https://docs.arduino.cc/hardware/nano-33-ble-sense-rev2)
Get Started With Machine Learning on Arduino

In arduino_tinyml_workshop.ipynb in Colab
Got data and uploaded to Colab.
Running the cells, got to the cell: Run with Test Data'
Runtime errors on these lines:
plt.plot(inputs_test, outputs_test, 'b.', label='Actual')
plt.plot(inputs_test, predictions, 'r.', label='Predicted')

Added in a few prints of data...

**OUTPUT WITH ERRORS:**
1/1 [==============================] - 0s 39ms/step
predictions =
[[1. 0. ]
[0.998 0.002]
[0. 1. ]
[1. 0. ]]
inputs_test =
[[0.701375 0.520875 0.378875 ... 0.500183 0.499817 0.499878 ]
[0.5895 0.461625 0.743125 ... 0.500534 0.50016775 0.50004575]
[0.68425 0.4585 0.71725 ... 0.4999695 0.4987335 0.49971 ]
[0.66625 0.51975 0.3385 ... 0.500885 0.500702 0.5009155 ]]
actual =
[[1. 0.]
[1. 0.]
[0. 1.]
[1. 0.]]
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
[](https://localhost:8080/#) in ()
10 plt.clf()
11 plt.title('Training data predicted vs actual values')
---> 12 plt.plot(inputs_test, outputs_test, 'b.', label='Actual')
13 plt.plot(inputs_test, predictions, 'r.', label='Predicted')
14 plt.show()

3 frames
[/usr/local/lib/python3.10/dist-packages/matplotlib/axes/_base.py](https://localhost:8080/#) in _plot_args(self, tup, kwargs, return_kwargs, ambiguous_fmt_datakey)
520 ncx, ncy = x.shape[1], y.shape[1]
521 if ncx > 1 and ncy > 1 and ncx != ncy:
--> 522 raise ValueError(f"x has {ncx} columns but y has {ncy} columns")
523 if ncx == 0 or ncy == 0:
524 return []

ValueError: x has 714 columns but y has 2 columns

Open arduino_tinyml_workshop.ipynb in Colab and start at the “Run with Test Data” cell. Inspect the reported plotting lines alongside the printed shapes for inputs_test, outputs_test, and predictions, then rerun the cell. Done means the tutorial cell completes without the reported ValueError and displays the actual and predicted data plots.

Scritto dal modello di indicizzazione a partire dal testo della issue.