C4W3_Lab1: batching instead of for-loop

Course Q&A TensorFlow Developer Professional Sequences, Time Series and Prediction
1

Hi All,

I think there is a bug in Lab1 of Week 3 when batching and instead of the for-loop (at the end of the lab):

image
image1066×871 47.4 KB

it seems that some rank information is missing. Thanks for having a look at it.

KR,

2

According to the error the issue is with the input, do you an input layer with the right shape? Or are you building the model right?

3

Thanks for bringing this up. The staff have been informed about this.

While you wait, please comment / remove the entire cell shown below, retrain the model and then the predict using model_forecast:

# Initialize a list
forecast = []

# Reduce the original series
forecast_series = series[split_time - window_size:]

# Use the model to predict data points per window size
for time in range(len(forecast_series) - window_size):
  forecast.append(model.predict(forecast_series[time:time + window_size][np.newaxis], verbose=0))

# Convert to a numpy array and drop single dimensional axes
results = np.array(forecast).squeeze()

# Plot the results
plot_series(time_valid, (x_valid, results))