Geron Chap 10 Building an Image Classifier Using the Sequential API 20221231

Using Keras to Load the Dataset

• p 297, 298

 $ cd $ML_PATH

 $ source tfenv/bin/activate

 $ python3
 
 >>> from tensorflow import keras
     ...

 >>> fashion_mnist = keras.datasets.fashion_mnist

 >>> (x_train_full, y_train_full), (x_test, y_test) = fashion_mnist.load_data()
     Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz
     29515/29515 [==============================] - 0s 1us/step
     Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz
     26421880/26421880 [==============================] - 31s 1us/step
     Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz
     5148/5148 [==============================] - 0s 0us/step
     Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz
     4422102/4422102 [==============================] - 7s 2us/step
 
 >>> x_train_full.shape
     (60000, 28, 28)

 >>> x_train_full.dtype
     dtype('uint8')

 >>> y_valid, y_train = y_train_full[:5000], y_train_full[5000:]

 >>> class_names = ["T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",
     ...                "Sandal", "Shirt", "Sneaker", "Bag", "Ankel boot"]

 >>> class_names[0]
     'T-shirt/top'