def main(unused_argv):
# Load training and eval data
prepper = prep_hiragana.prepper('hiragana', 'hiragana.txt')
train_data = prepper.train_images() # Returns np.array
train_labels = np.asarray(prepper.train_labels(), dtype=np.int32)
eval_data = prepper.validate_images() # Returns np.array
eval_labels = np.asarray(prepper.validate_labels(), dtype=np.int32)
# Create the Estimator
hiragana_classifier = learn.Estimator(
model_fn=cnn_model_fn, model_dir="/tmp/hiragana_convnet_model2")
# Set up logging for predictions
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log,
every_n_iter=50)
# Train the model
hiragana_classifier.fit(x=train_data,
y=train_labels,
batch_size=50,
steps=1000,
monitors=[logging_hook])
# Configure the accuracy metric for evaluation
metrics = {
"accuracy":
learn.MetricSpec(metric_fn=tf.metrics.accuracy,
prediction_key="classes"),
}
# Evaluate the model and print results
eval_results = hiragana_classifier.evaluate(x=eval_data,
y=eval_labels,
metrics=metrics)
print(eval_results)
def main(_):
# Import data
# mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
prepper = prep_hiragana.prepper('hiragana', 'hiragana.txt')
training = prepper.train_images()
t_labels = np.asarray(prepper.train_labels(), dtype=np.int32)
validation = prepper.validate_images()
v_labels = np.asarray(prepper.validate_labels(), dtype=np.int32)
v_labels = onehot_labels(v_labels)
# Create the model
x = tf.placeholder(tf.float32, [None, 900])
W = tf.Variable(tf.zeros([900, 45]))
b = tf.Variable(tf.zeros([45]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 45])
# The raw formulation of cross-entropy,
#
# tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
# reduction_indices=[1]))
#
# can be numerically unstable.
#
# So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
# outputs of 'y', and then average across the batch.
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
# Test trained model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# Train
for i in range(1000):
a = i * 50 % len(training)
batchx = training[a:a + 50]
batchy = t_labels[a:a + 50]
batchy = onehot_labels(batchy)
sess.run(train_step, feed_dict={x: batchx, y_: batchy})
if i % 100 == 0:
print(sess.run(accuracy, feed_dict={x: validation, y_: v_labels}))
print(sess.run(accuracy, feed_dict={x: validation, y_: v_labels}))
def main(_):
# Hyper-parameters
width, height = 32, 32
classes = 90
batch_size = 50
steps = 1000
save_location = "/tmp/kana_cnn"
# Import data
prepper = prep_hiragana.prepper('kana', 'kana.txt')
training = prepper.train_images()
t_labels = np.asarray(prepper.train_labels(), dtype=np.int32)
validation = prepper.validate_images()
v_labels = np.asarray(prepper.validate_labels(), dtype=np.int32)
v_labels = onehot_labels(v_labels, classes)
# Create the model
x = tf.placeholder(tf.float32, [None, width * height])
W = tf.Variable(tf.zeros([width * height, classes]))
b = tf.Variable(tf.zeros([classes]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, classes])
# adding in the convolutional layer
W_conv1 = weight_variable([5, 5, 1, 32], "w1")
b_conv1 = bias_variable([32], "b1")
x_image = tf.reshape(x, [-1, width, height, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# adding the second convolutional layer
W_conv2 = weight_variable([5, 5, 32, 64], "w2")
b_conv2 = bias_variable([64], "b2")
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# adding the third convolutional layer
W_conv3 = weight_variable([5, 5, 64, 128], "w3")
b_conv3 = bias_variable([128], "b3")
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)
#adding the final layer
W_fc1 = weight_variable([4 * 4 * 128, 1024], "w_flat")
b_fc1 = bias_variable([1024], "b_flat")
h_pool3_flat = tf.reshape(h_pool3, [-1, 4 * 4 * 128])
h_fc1 = tf.nn.relu(tf.matmul(h_pool3_flat, W_fc1) + b_fc1)
# adding the dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# adding the readout layer
W_fc2 = weight_variable([1024, classes], "w_read")
b_fc2 = bias_variable([classes], "b_read")
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# The raw formulation of cross-entropy,
#
# tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
# reduction_indices=[1]))
#
# can be numerically unstable.
#
# So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
# outputs of 'y', and then average across the batch.
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
if os.path.exists(os.path.join(save_location)):
saver.restore(sess, save_location + "/model.ckpt")
# Test trained model
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# Train
for i in range(steps):
a = i * batch_size % len(training)
batchx = training[a:a + batch_size]
batchy = t_labels[a:a + batch_size]
batchy = onehot_labels(batchy, classes)
train_step.run(feed_dict={x: batchx, y_: batchy, keep_prob: 0.5})
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batchx,
y_: batchy,
keep_prob: 1.0
})
print("step %d, training accuracy %g" % (i, train_accuracy))
print("test accuracy %g" % accuracy.eval(feed_dict={
x: validation,
y_: v_labels,
keep_prob: 1.0
}))
if i % 300 == 0:
# Save the variables to disk.
save_path = saver.save(sess, save_location + "/model.ckpt")
# print("Model saved in file: %s" % save_path)
print("test accuracy %g" % accuracy.eval(feed_dict={
x: validation,
y_: v_labels,
keep_prob: 1.0
}))
save_path = saver.save(sess, save_location + "/model.ckpt")