def inference():
dicPath = "C:\\wuwei\\work\\github\\data\\imdb.dict.pkl"
inferenceFile = "C:\\wuwei\\work\\github\\dl\\sentiment\\inferencedata\\pos1.txt"
dic = loadDic(dicPath)
inference_data = preProcessData.preProcess_inference_data(
inferenceFile, dic)
print(inference_data)
inference_data = dataload.load_inference_data(inference_data)
print(inference_data)
graph = tf.Graph()
with graph.as_default():
encoder_inputs = tf.placeholder(shape=(batchSize, None),
dtype=tf.int32,
name='encoder_inputs')
embeddings_inputs = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
logist = model.inference2(encoder_inputs,
embeddings_inputs,
classNum,
isTrainModel=False)
inputs_batch_major = np.zeros(
shape=[batchSize, len(inference_data[0])], dtype=np.int32)
for i in range(len(inference_data[0])):
inputs_batch_major[0, i] = inference_data[0][i]
saver = tf.train.Saver()
with tf.Session(graph=graph) as sess:
saver.restore(sess, ckpt_dir)
# sess.run(tf.global_variables_initializer())
feed = {encoder_inputs: inputs_batch_major}
logist_val = sess.run([logist], feed_dict=feed)
results = np.squeeze(logist_val)
top_1 = results.argsort()[-1:][::-1]
print("The logist val is: ", results)
print("The predict class is: {}".format(top_1[0]))
def validate2():
val_tfrecords = TFRECORDS_PATH + 'test5.tfrecords'
val_image_batch, val_label_batch = input_data.get_batch(val_tfrecords,
BATCH_SIZE,
num_epochs=1)
x = tf.placeholder(tf.float32, [BATCH_SIZE, WIDTH, HEIGHT, CHANNEL],
name='x-input')
y_ = tf.placeholder(tf.float32, [BATCH_SIZE, NUM_CLASSES], name='y-input')
y = model.inference2(x, NUM_CLASSES, evaluate=False)
predict_y = tf.argmax(y, 1)
val_loss = tools.loss(logits=y, labels=y_)
val_acc = tools.accuracy(logits=y, labels=y_)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run([
tf.global_variables_initializer(),
tf.local_variables_initializer()
])
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
ckpt = tf.train.get_checkpoint_state(MODEL2_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
global_score = 0.
num_step = 0
try:
for i in range(TRAINING_STEPS):
if coord.should_stop():
break
val_xs, val_ys = sess.run(
[val_image_batch, val_label_batch])
yy, loss_value, acc_value = sess.run(
[predict_y, val_loss, val_acc],
feed_dict={
x: val_xs,
y_: val_ys
})
global_score += acc_value
num_step += 1
if i % 5 == 0:
print(
"in the %dth batch: After %s training step(s), validation accuracy = %g"
% (i, global_step, acc_value))
# plot_images(val_xs, val_ys)
except tf.errors.OutOfRangeError:
print("global accuracy = %g" % (global_score / num_step))
print('Done testing -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
def train2():
ckpt = tf.train.get_checkpoint_state(MODEL2_SAVE_PATH)
train_tfrecords = TFRECORDS_PATH + 'train2.tfrecords'
val_tfrecords = TFRECORDS_PATH + 'val.tfrecords'
train_image_batch, train_label_batch = input_data.get_batch(
train_tfrecords, BATCH_SIZE)
val_image_batch, val_label_batch = input_data.get_batch(
val_tfrecords, BATCH_SIZE)
x = tf.placeholder(tf.float32, [BATCH_SIZE, WIDTH, HEIGHT, CHANNEL],
name='x-input')
y_ = tf.placeholder(tf.float32, [BATCH_SIZE, NUM_CLASSES], name='y-input')
if ckpt and ckpt.model_checkpoint_path:
num_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
num_step = int(num_step)
print(num_step)
global_step = tf.Variable(num_step, trainable=False)
else:
global_step = tf.Variable(0, trainable=False)
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
y = model.inference2(x, NUM_CLASSES, regularizer=regularizer)
train_loss = tools.loss(logits=y, labels=y_)
train_acc = tools.accuracy(logits=y, labels=y_)
train_op = tools.optimizer(train_loss,
LEARNING_RATE,
global_step=global_step)
saver = tf.train.Saver()
with tf.Session() as sess:
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
tf.global_variables_initializer().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
summary_op = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(LOG2_TRAIN_PATH, sess.graph)
val_writer = tf.summary.FileWriter(LOG2_VAL_PATH, sess.graph)
try:
for i in range(TRAINING_STEPS):
if coord.should_stop():
break
xs, ys = sess.run([train_image_batch, train_label_batch])
_, loss_value, acc_value, step = sess.run(
[train_op, train_loss, train_acc, global_step],
feed_dict={
x: xs,
y_: ys
})
if i % 1 == 0:
print(
"After %d training step(s), loss on training batch is %g, accuracy is %g"
% (step, loss_value, acc_value))
if i % 1 == 0:
summary_str = sess.run(summary_op,
feed_dict={
x: xs,
y_: ys
})
train_writer.add_summary(summary_str, step)
if i % 5 == 0:
val_xs, val_ys = sess.run(
[val_image_batch, val_label_batch])
val_loss_value, val_acc_value = sess.run(
[train_loss, train_acc],
feed_dict={
x: val_xs,
y_: val_ys
})
print(
"After %d training step(s), valuation loss is %g, accuracy is %g"
% (step, val_loss_value, val_acc_value))
summary_str = sess.run(summary_op,
feed_dict={
x: val_xs,
y_: val_ys
})
val_writer.add_summary(summary_str, step)
if i % 10 == 0 or step + 1 == TRAINING_STEPS:
saver.save(sess,
os.path.join(MODEL2_SAVE_PATH, MODEL_NAME),
global_step=global_step)
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)