MNIST EXAMPLE

[Bhalaji Kharthik]

Can I get the convolutional neural network structure of the model that is being used in the MNIST example in the Spresense SDK?

[CamilaSouza]

Hey, @Bhalaji-Kharthik

In the code for that example we can see the following structure for the model:

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(16, kernel_size=(7, 7), strides=(1, 1), activation='relu', input_shape=(28, 28, 1), padding="valid"),
    tf.keras.layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'),
    tf.keras.layers.Conv2D(30, kernel_size=(3, 3), strides=(1, 1), activation='tanh', padding='valid'),
    tf.keras.layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='valid'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(150, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax'),
])