In the exploration exercises some portions are still pertaining to mnist, instead of fashion_mnist.
mnist = tf.keras.datasets.mnist->
mnist = tf.keras.datasets.fashion_mnist
- Exercises 2, 4, 5, and 7: no impact on the global meaning, just for consistency
- Exercise 3: the dimensions in the error message don't match the explanation
- Exercise 6: just might have an issue with the 128-neuron hidden layer not having the same behavior as the baseline 512-neuron layer in terms of loss evolution
- Exercise 8, the 95% in the text should be changed to 60% (95% was for mnist)