Skip to content

Instantly share code, notes, and snippets.

@ser1zw
Created June 10, 2018 17:09
Show Gist options
  • Save ser1zw/7b68b965fd39ddeb9012f9664b463c19 to your computer and use it in GitHub Desktop.
Save ser1zw/7b68b965fd39ddeb9012f9664b463c19 to your computer and use it in GitHub Desktop.
# https://www.tensorflow.org/get_started/eager
# Configure imports and eager execution
from __future__ import absolute_import, division, print_function
import os
import matplotlib.pyplot as plt
import tensorflow as tf
import tensorflow.contrib.eager as tfe
tf.enable_eager_execution()
print("TensorFlow version: {}".format(tf.VERSION))
print("Eager execution: {}".format(tf.executing_eagerly()))
# Import and parse the training dataset
train_dataset_url = "http://download.tensorflow.org/data/iris_training.csv"
train_dataset_fp = tf.keras.utils.get_file(fname=os.path.basename(train_dataset_url),
origin=train_dataset_url)
print("Local copy of the dataset file: {}".format(train_dataset_fp))
# Parse the dataset
def parse_csv(line):
example_defaults = [[0.], [0.], [0.], [0.], [0]]
parsed_line = tf.decode_csv(line, example_defaults)
features = tf.reshape(parsed_line[:-1], shape=(4,))
label = tf.reshape(parsed_line[-1], shape=())
return features, label
# Create the training tf.data.Dataset
train_dataset = tf.data.TextLineDataset(train_dataset_fp)
train_dataset = train_dataset.skip(1)
train_dataset = train_dataset.map(parse_csv)
train_dataset = train_dataset.shuffle(buffer_size=1000)
train_dataset = train_dataset.batch(32)
features, label = iter(train_dataset).next()
print("example features:", features[0])
print("example label:", label[0])
# Create a model using Keras
model = tf.keras.Sequential([
tf.keras.layers.Dense(10, activation="relu", input_shape=(4,)),
tf.keras.layers.Dense(10, activation="relu"),
tf.keras.layers.Dense(3)
])
# Define the loss and gradient function
def loss(model, x, y):
y_ = model(x)
return tf.losses.sparse_softmax_cross_entropy(labels=y, logits=y_)
def grad(model, inputs, targets):
with tf.GradientTape() as tape:
loss_value = loss(model, inputs, targets)
return tape.gradient(loss_value, model.variables)
# Create an optimizer
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
# Training loop
train_loss_results = []
train_accuracy_results = []
num_epochs = 201
for epoch in range(num_epochs):
epoch_loss_avg = tfe.metrics.Mean()
epoch_accuracy = tfe.metrics.Accuracy()
for x, y in train_dataset:
grads = grad(model, x, y)
optimizer.apply_gradients(zip(grads, model.variables), global_step=tf.train.get_or_create_global_step())
epoch_loss_avg(loss(model, x, y))
epoch_accuracy(tf.argmax(model(x), axis=1, output_type=tf.int32), y)
train_loss_results.append(epoch_loss_avg.result())
train_accuracy_results.append(epoch_accuracy.result())
if epoch % 50 == 0:
print("Epoch {:03d}: Loss: {:.3f}, Accuracy: {:.3%}".format(epoch, epoch_loss_avg.result(), epoch_accuracy.result()))
# Visualize the loss function over time
"""
fig, axes = plt.subplots(2, sharex=True, figsize=(12, 8))
fig.suptitle("Training Metrics")
axes[0].set_ylabel("Loss", fontsize=14)
axes[0].plot(train_loss_results)
axes[1].set_ylabel("Accuracy", fontsize=14)
axes[1].set_xlabel("Epoch", fontsize=14)
axes[1].plot(train_accuracy_results)
plt.show()
"""
# Setup the test dataset
test_url = "http://download.tensorflow.org/data/iris_test.csv"
test_fp = tf.keras.utils.get_file(fname=os.path.basename(test_url), origin=test_url)
test_dataset = tf.data.TextLineDataset(test_fp)
test_dataset = test_dataset.skip(1)
test_dataset = test_dataset.map(parse_csv)
test_dataset = test_dataset.shuffle(1000)
test_dataset = test_dataset.batch(32)
# Evaluate the model on the test dataset
test_accuracy = tfe.metrics.Accuracy()
for (x, y) in test_dataset:
prediction = tf.argmax(model(x), axis=1, output_type=tf.int32)
test_accuracy(prediction, y)
print("Test set accuracy: {:.3%}".format(test_accuracy.result()))
# Use the trained model to make predictions
class_ids = ["Iris setosa", "Iris versicolor", "Iris virginica"]
predict_dataset = tf.convert_to_tensor([
[5.1, 3.3, 1.7, 0.5,],
[5.9, 3.0, 4.2, 1.5,],
[6.9, 3.1, 5.4, 2.1]
])
predictions = model(predict_dataset)
for i, logits in enumerate(predictions):
class_idx = tf.argmax(logits).numpy()
name = class_ids[class_idx]
print("Example {} prediction: {}".format(i, name))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment