KERAS and MNIST#
Let’s start by trying to reproduce our MNIST example using Keras. Because there are a lot more options in Keras, we can add more layers and different activation functions.
Important
Keras requires a backend, which can be tensorflow, pytorch, or jax. By default it will assume tensorflow.
To use pytorch instead, set the environment variable:
export KERAS_BACKEND="torch"
before launching Jupyter.
import keras
import matplotlib.pyplot as plt
import numpy as np
We follow the example for setting up the network: Vict0rSch/deep_learning
The MNIST data#
The keras library can download the MNIST data directly and provides a function to give us both the training and test images and the corresponding digits. This is already in a format that Keras wants, so we don’t use the classes that we defined earlier.
from keras.datasets import mnist
(X_train, y_train), (X_test, y_test) = mnist.load_data()
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
0/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0s/step
1114112/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
10780672/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
11490434/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
As before, the training set consists of 60000 digits represented as a 28x28 array (there are no color channels, so this is grayscale data). They are also integer data.
X_train.shape
(60000, 28, 28)
X_train.dtype
dtype('uint8')
Let’s look at the first digit and the “y” value (target) associated with it—that’s the correct answer.
plt.imshow(X_train[0], cmap="gray_r")
print(y_train[0])
5
Preparing the Data#
The neural network takes a 1-d vector of input and will return a 1-d vector of output. We need to convert our data to this form.
We’ll scale the image data to fall in [0, 1) and the numerical output to be categorized as an array. Finally, we need the input data to be one-dimensional, so we fill flatten the 28x28 images into a single 784 vector.
X_train = X_train.astype('float32')/255
X_test = X_test.astype('float32')/255
X_train = np.reshape(X_train, (60000, 784))
X_test = np.reshape(X_test, (10000, 784))
X_train[0]
array([0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0.01176471, 0.07058824, 0.07058824,
0.07058824, 0.49411765, 0.53333336, 0.6862745 , 0.10196079,
0.6509804 , 1. , 0.96862745, 0.49803922, 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.11764706, 0.14117648, 0.36862746, 0.6039216 ,
0.6666667 , 0.99215686, 0.99215686, 0.99215686, 0.99215686,
0.99215686, 0.88235295, 0.6745098 , 0.99215686, 0.9490196 ,
0.7647059 , 0.2509804 , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.19215687, 0.93333334,
0.99215686, 0.99215686, 0.99215686, 0.99215686, 0.99215686,
0.99215686, 0.99215686, 0.99215686, 0.9843137 , 0.3647059 ,
0.32156864, 0.32156864, 0.21960784, 0.15294118, 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.07058824, 0.85882354, 0.99215686, 0.99215686,
0.99215686, 0.99215686, 0.99215686, 0.7764706 , 0.7137255 ,
0.96862745, 0.94509804, 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0.3137255 , 0.6117647 , 0.41960785, 0.99215686, 0.99215686,
0.8039216 , 0.04313726, 0. , 0.16862746, 0.6039216 ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0.05490196,
0.00392157, 0.6039216 , 0.99215686, 0.3529412 , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0.54509807,
0.99215686, 0.74509805, 0.00784314, 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0.04313726, 0.74509805, 0.99215686,
0.27450982, 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.13725491, 0.94509804, 0.88235295, 0.627451 ,
0.42352942, 0.00392157, 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0.31764707, 0.9411765 , 0.99215686, 0.99215686, 0.46666667,
0.09803922, 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0.1764706 ,
0.7294118 , 0.99215686, 0.99215686, 0.5882353 , 0.10588235,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.0627451 , 0.3647059 ,
0.9882353 , 0.99215686, 0.73333335, 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.9764706 , 0.99215686,
0.9764706 , 0.2509804 , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.18039216, 0.50980395,
0.7176471 , 0.99215686, 0.99215686, 0.8117647 , 0.00784314,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0.15294118,
0.5803922 , 0.8980392 , 0.99215686, 0.99215686, 0.99215686,
0.98039216, 0.7137255 , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0.09411765, 0.44705883, 0.8666667 , 0.99215686, 0.99215686,
0.99215686, 0.99215686, 0.7882353 , 0.30588236, 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.09019608, 0.25882354, 0.8352941 , 0.99215686,
0.99215686, 0.99215686, 0.99215686, 0.7764706 , 0.31764707,
0.00784314, 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0.07058824, 0.67058825, 0.85882354,
0.99215686, 0.99215686, 0.99215686, 0.99215686, 0.7647059 ,
0.3137255 , 0.03529412, 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0.21568628, 0.6745098 ,
0.8862745 , 0.99215686, 0.99215686, 0.99215686, 0.99215686,
0.95686275, 0.52156866, 0.04313726, 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0.53333336, 0.99215686, 0.99215686, 0.99215686,
0.83137256, 0.5294118 , 0.5176471 , 0.0627451 , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. , 0. ,
0. , 0. , 0. , 0. ], dtype=float32)
As we did in our example, we will use categorical data. Keras includes routines to categorize data. In our case, since there are 10 possible digits, we want to put the output into 10 categories (represented by 10 neurons)
from keras.utils import to_categorical
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
Now let’s look at the target for the first training digit. We know from above that it was ‘5’. Here we see that there is a 1 in the index corresponding to 5 (remember we start counting at 0 in python).
y_train[0]
array([0., 0., 0., 0., 0., 1., 0., 0., 0., 0.])
Build the Neural Network#
Now we’ll build the neural network. We will have 2 hidden layers, and the number of neurons will look like:
784 → 500 → 300 → 10
Layers#
Let’s start by setting up the layers. For each layer, we tell keras the number of output neurons. It infers the number of inputs from the previous layer (with the exception of the input layer, where we need to tell it what to expect as input).
Properties on the layers:
Input layer: this just tells the network how many input nodes to expect.
Dense layers: We will use a dense network. This means that all neurons in one layer are connected to all neurons in the next layer (sometimes the term “fully-connected” is used here).
Activation function: We previously used the sigmoid function. Now we’ll use rectified linear unit (see also http://ml-cheatsheet.readthedocs.io/en/latest/activation_functions.html#relu) for all but the last layer.
For the very last layer (the output layer), we use a softmax activation. This is commonly used with categorical data (like we have) and has the nice property that all of entries add to 1 (so we can interpret them as probabilities).
See https://keras.io/api/layers/activations/ for a list of activation functions supported.
Dropout: for some of the layers, we will specify a dropout. This means that we will ignore some of the neurons in a layer during training (randomly selected at the specified probability). This can help present overfitting of the network.
Here’s a nice discussion: https://medium.com/@amarbudhiraja/https-medium-com-amarbudhiraja-learning-less-to-learn-better-dropout-in-deep-machine-learning-74334da4bfc5
from keras.models import Sequential
from keras.layers import Input, Dense, Dropout, Activation
model = Sequential()
model.add(Input(shape=(784,)))
model.add(Dense(500, activation="relu"))
model.add(Dropout(0.4))
model.add(Dense(300, activation="relu"))
model.add(Dropout(0.4))
model.add(Dense(10, activation="softmax"))
Loss function#
We need to specify what we want to optimize and how we are going to do it.
Recall: the loss (or cost) function measures how well our predictions match the expected target. Previously we were using the sum of the squares of the error.
For categorical data, like we have, the “cross-entropy” metric is often used. See here for an explanation: https://jamesmccaffrey.wordpress.com/2013/11/05/why-you-should-use-cross-entropy-error-instead-of-classification-error-or-mean-squared-error-for-neural-network-classifier-training/
Optimizer#
We also need to specify an optimizer. This could be gradient descent, as we used before. Here’s a list of the optimizers supoprted by keras: https://keras.io/api/optimizers/ We’ll use RMPprop, which builds off of gradient descent and includes some momentum.
Finally, we need to specify a metric that is evaluated during training and testing. We’ll use "accuracy" here. This means that we’ll see the accuracy of our model reported as we are training and testing.
More details on these options is here: https://keras.io/api/models/model/
from keras.optimizers import RMSprop
rms = RMSprop()
model.compile(loss='categorical_crossentropy',
optimizer=rms, metrics=['accuracy'])
Summary#
Finally, we can get a summary of the model:
model.summary()
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩ │ dense (Dense) │ (None, 500) │ 392,500 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ dropout (Dropout) │ (None, 500) │ 0 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ dense_1 (Dense) │ (None, 300) │ 150,300 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ dropout_1 (Dropout) │ (None, 300) │ 0 │ ├─────────────────────────────────┼────────────────────────┼───────────────┤ │ dense_2 (Dense) │ (None, 10) │ 3,010 │ └─────────────────────────────────┴────────────────────────┴───────────────┘
Total params: 545,810 (2.08 MB)
Trainable params: 545,810 (2.08 MB)
Non-trainable params: 0 (0.00 B)
We see that we have > 500k parameters to train!
Train#
For training, we pass in the inputs and target and the number of epochs to run and it will optimize the network by adjusting the weights between the nodes in the layers.
The number of epochs is the number of times the entire data set is passed forward and backward through the network. The batch size is the number of training pairs you pass through the network at a given time. You update the parameter in your model (the weights) once for each batch. This makes things more efficient and less noisy.
Tip
We also pass in the test data as “validation” which will allow us to see how well we are doing as we train.
epochs = 20
batch_size = 256
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size,
validation_data=(X_test, y_test), verbose=2)
Epoch 1/20
235/235 - 4s - 17ms/step - accuracy: 0.8877 - loss: 0.3664 - val_accuracy: 0.9589 - val_loss: 0.1411
Epoch 2/20
235/235 - 4s - 16ms/step - accuracy: 0.9524 - loss: 0.1594 - val_accuracy: 0.9700 - val_loss: 0.0966
Epoch 3/20
235/235 - 4s - 17ms/step - accuracy: 0.9644 - loss: 0.1173 - val_accuracy: 0.9740 - val_loss: 0.0788
Epoch 4/20
235/235 - 4s - 17ms/step - accuracy: 0.9712 - loss: 0.0956 - val_accuracy: 0.9762 - val_loss: 0.0752
Epoch 5/20
235/235 - 4s - 17ms/step - accuracy: 0.9742 - loss: 0.0824 - val_accuracy: 0.9784 - val_loss: 0.0712
Epoch 6/20
235/235 - 4s - 17ms/step - accuracy: 0.9781 - loss: 0.0718 - val_accuracy: 0.9768 - val_loss: 0.0807
Epoch 7/20
235/235 - 4s - 17ms/step - accuracy: 0.9796 - loss: 0.0646 - val_accuracy: 0.9792 - val_loss: 0.0697
Epoch 8/20
235/235 - 4s - 18ms/step - accuracy: 0.9819 - loss: 0.0589 - val_accuracy: 0.9816 - val_loss: 0.0642
Epoch 9/20
235/235 - 4s - 17ms/step - accuracy: 0.9830 - loss: 0.0542 - val_accuracy: 0.9812 - val_loss: 0.0687
Epoch 10/20
235/235 - 4s - 17ms/step - accuracy: 0.9848 - loss: 0.0478 - val_accuracy: 0.9833 - val_loss: 0.0640
Epoch 11/20
235/235 - 4s - 17ms/step - accuracy: 0.9848 - loss: 0.0474 - val_accuracy: 0.9827 - val_loss: 0.0641
Epoch 12/20
235/235 - 4s - 17ms/step - accuracy: 0.9870 - loss: 0.0418 - val_accuracy: 0.9849 - val_loss: 0.0602
Epoch 13/20
235/235 - 4s - 17ms/step - accuracy: 0.9867 - loss: 0.0414 - val_accuracy: 0.9837 - val_loss: 0.0622
Epoch 14/20
235/235 - 4s - 16ms/step - accuracy: 0.9882 - loss: 0.0363 - val_accuracy: 0.9833 - val_loss: 0.0628
Epoch 15/20
235/235 - 4s - 18ms/step - accuracy: 0.9889 - loss: 0.0353 - val_accuracy: 0.9843 - val_loss: 0.0632
Epoch 16/20
235/235 - 4s - 17ms/step - accuracy: 0.9888 - loss: 0.0341 - val_accuracy: 0.9838 - val_loss: 0.0642
Epoch 17/20
235/235 - 4s - 17ms/step - accuracy: 0.9903 - loss: 0.0304 - val_accuracy: 0.9834 - val_loss: 0.0651
Epoch 18/20
235/235 - 4s - 17ms/step - accuracy: 0.9899 - loss: 0.0306 - val_accuracy: 0.9840 - val_loss: 0.0646
Epoch 19/20
235/235 - 4s - 17ms/step - accuracy: 0.9909 - loss: 0.0289 - val_accuracy: 0.9848 - val_loss: 0.0632
Epoch 20/20
235/235 - 4s - 18ms/step - accuracy: 0.9916 - loss: 0.0257 - val_accuracy: 0.9851 - val_loss: 0.0613
<keras.src.callbacks.history.History at 0x7f4cc8ff5550>
Test#
keras has a routine, evaluate() that can take the inputs and targets of a test data set and return the loss value and accuracy (or other defined metrics) on this data.
Here we see we are > 98% accurate on the test data—this is the data that the model has never seen before (and was not trained with).
loss_value, accuracy = model.evaluate(X_test, y_test, batch_size=16)
print(accuracy)
1/625 ━━━━━━━━━━━━━━━━━━━━ 3s 6ms/step - accuracy: 1.0000 - loss: 0.0016
12/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 1.0000 - loss: 0.0014
22/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9978 - loss: 0.0187
33/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9955 - loss: 0.0344
44/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9940 - loss: 0.0447
55/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9925 - loss: 0.0517
66/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9915 - loss: 0.0557
77/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9905 - loss: 0.0591
88/625 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9893 - loss: 0.0634
97/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9883 - loss: 0.0661
107/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9873 - loss: 0.0691
118/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9864 - loss: 0.0717
129/625 ━━━━━━━━━━━━━━━━━━━━ 3s 6ms/step - accuracy: 0.9856 - loss: 0.0737
134/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9852 - loss: 0.0746
145/625 ━━━━━━━━━━━━━━━━━━━━ 3s 6ms/step - accuracy: 0.9846 - loss: 0.0763
153/625 ━━━━━━━━━━━━━━━━━━━━ 3s 6ms/step - accuracy: 0.9841 - loss: 0.0773
162/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9836 - loss: 0.0782
172/625 ━━━━━━━━━━━━━━━━━━━━ 3s 7ms/step - accuracy: 0.9832 - loss: 0.0793
184/625 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.9827 - loss: 0.0803
195/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9823 - loss: 0.0811
206/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9820 - loss: 0.0817
218/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9818 - loss: 0.0821
230/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9816 - loss: 0.0827
241/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9814 - loss: 0.0831
253/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9812 - loss: 0.0835
265/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9811 - loss: 0.0839
274/625 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.9810 - loss: 0.0841
285/625 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.9809 - loss: 0.0843
296/625 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.9808 - loss: 0.0844
307/625 ━━━━━━━━━━━━━━━━━━━━ 2s 6ms/step - accuracy: 0.9808 - loss: 0.0845
312/625 ━━━━━━━━━━━━━━━━━━━━ 2s 7ms/step - accuracy: 0.9807 - loss: 0.0845
322/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9807 - loss: 0.0845
332/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9807 - loss: 0.0844
339/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9807 - loss: 0.0843
350/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9807 - loss: 0.0841
361/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9808 - loss: 0.0839
372/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9808 - loss: 0.0837
383/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9808 - loss: 0.0835
394/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9808 - loss: 0.0833
405/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9808 - loss: 0.0830
416/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9809 - loss: 0.0827
427/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9809 - loss: 0.0825
439/625 ━━━━━━━━━━━━━━━━━━━━ 1s 6ms/step - accuracy: 0.9809 - loss: 0.0822
450/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9810 - loss: 0.0819
461/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9810 - loss: 0.0816
472/625 ━━━━━━━━━━━━━━━━━━━━ 1s 7ms/step - accuracy: 0.9811 - loss: 0.0813
483/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9811 - loss: 0.0809
488/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9812 - loss: 0.0807
499/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9812 - loss: 0.0804
508/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9813 - loss: 0.0801
515/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9814 - loss: 0.0798
526/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9814 - loss: 0.0794
537/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9815 - loss: 0.0791
548/625 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.9816 - loss: 0.0787
559/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9816 - loss: 0.0783
570/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9817 - loss: 0.0779
581/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9818 - loss: 0.0776
592/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9819 - loss: 0.0772
604/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9819 - loss: 0.0768
615/625 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step - accuracy: 0.9820 - loss: 0.0765
625/625 ━━━━━━━━━━━━━━━━━━━━ 4s 6ms/step - accuracy: 0.9851 - loss: 0.0613
0.9850999712944031
Predicting#
Suppose we simply want to ask our neural network to predict the target for an input. We can use the predict() method to return the category array with the predictions. We can then use np.argmax() to select the most probable.
np.argmax(model.predict(np.array([X_test[0]])))
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step
np.int64(7)
y_test[0]
array([0., 0., 0., 0., 0., 0., 0., 1., 0., 0.])
Now let’s loop over the test set and print out what we predict vs. the true answer for those we get wrong. We can also plot the image of the digit.
wrong = 0
max_wrong = 10
for n, (x, y) in enumerate(zip(X_test, y_test)):
try:
res = model.predict(np.array([x]), verbose=0)
if np.argmax(res) != np.argmax(y):
print("test {}: prediction = {}, truth is {}".format(n, np.argmax(res), np.argmax(y)))
plt.imshow(x.reshape(28, 28), cmap="gray_r")
plt.show()
wrong += 1
if (wrong > max_wrong-1):
break
except KeyboardInterrupt:
print("stopping")
break
test 247: prediction = 2, truth is 4
test 259: prediction = 0, truth is 6
test 321: prediction = 7, truth is 2
test 445: prediction = 0, truth is 6
test 447: prediction = 9, truth is 4
test 582: prediction = 2, truth is 8
test 619: prediction = 8, truth is 1
test 674: prediction = 3, truth is 5
test 691: prediction = 4, truth is 8
test 720: prediction = 8, truth is 5
Experimenting#
There are a number of things we can play with to see how the network performance changes:
batch size
adding or removing hidden layers
changing the dropout
changing the activation function
Callbacks#
Keras allows for callbacks each epoch to store some information. These can allow you to, for example, plot of the accuracy vs. epoch by adding a callback. Take a look here for some inspiration:
https://www.tensorflow.org/api_docs/python/tf/keras/callbacks/History
Going Further#
Convolutional neural networks are often used for image recognition, especially with larger images. They use filter to try to recognize patterns in portions of images (A tile). See this for a keras example: