print('Loading data...')
testset = np.loadtxt(DATA_DIR + '/ORIGINAL_SOUNDS_THREE_LABEL_DATA')
print('Load successful')
x_data = testset[50000:, 2:-4] #Use frequency 100Hz~8000Hz
print(x_data.shape)
y_data = testset[50000:, 0]
y_data = np.reshape(y_data, [-1, 1])
print(y_data.shape)
X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)
with tf.Session() as sess:
modelmaker = model.NetworkModel()
_, Hypothesis_prob_load, _, saver = modelmaker.get_model(
sess, './P2_LOADED', X, Y)
prob_load = sess.run([Hypothesis_prob_load], feed_dict={X: x_data})
g = tf.Graph()
with g.as_default():
X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)
modelmaker = model.NetworkModel()
with tf.Session(graph=g) as sess:
_, Hypothesis_prob_unload, _, _ = modelmaker.get_model(
sess, './P2_UNLOADED', X, Y)
prob_unload = sess.run([Hypothesis_prob_unload], feed_dict={X: x_data})
def main(argv=None):
margin = 0.75
BATCH_SIZE = 40
ITERATION = 200000
data_num = 16813
train_anchor_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
train_positive_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
train_negative_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
labels_anchor = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
labels_positive = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
labels_negative = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
keep_prob = tf.placeholder(tf.float32, shape=[], name='keep_probability')
train_data = tf.concat(
[train_anchor_data, train_positive_data, train_negative_data], axis=0)
# vgg_train_anchor = model.NetworkModel(train_anchor_data, keep_prob=keep_prob)
# vgg_train_positive = model.NetworkModel(train_positive_data, keep_prob=keep_prob, reuse=True)
# vgg_train_negative = model.NetworkModel(train_negative_data, keep_prob=keep_prob, reuse=True)
pre_logits = model.NetworkModel(train_data, keep_prob=keep_prob)
logits = tf.nn.l2_normalize(pre_logits, 1, 1e-10, name='embeddings')
# print(logits.get_shape().as_list())
vgg_train_anchor, vgg_train_positive, vgg_train_negative = tf.unstack(
tf.reshape(logits, [-1, 3, 1024]), 3, 1)
# print(vgg_train_anchor.get_shape().as_list())
# print(vgg_train_positive.get_shape().as_list())
# print(vgg_train_negative.get_shape().as_list())
loss, positives, negatives = utils.compute_triplet_loss(
vgg_train_anchor, vgg_train_positive, vgg_train_negative, margin)
batch = tf.Variable(0)
learning_rate = tf.train.exponential_decay(0.001, batch * BATCH_SIZE,
data_num, 0.95)
optimizer_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(
loss)
Saver = tf.train.Saver()
tf.summary.scalar('loss', loss)
tf.summary.scalar('positives', positives)
tf.summary.scalar('negatives', negatives)
merged = tf.summary.merge_all()
data, labels = data_process.input_data()
print(data.shape)
print(labels.shape)
dataShufflu = DataShuffle(data, labels)
with tf.Session() as sess:
train_write = tf.summary.FileWriter('./logs_tensorboard_3/',
sess.graph)
# test_write = tf.summary.FileWriter('./logs_tensorboard/triple/test/', sess.graph)
sess.run(tf.global_variables_initializer())
for step in range(ITERATION):
batch_anchor, batch_positive, batch_negative, batch_labels_anchor, batch_labels_positive,\
batch_labels_negative = dataShufflu.get_triplet(n_labels=30, n_triplet=BATCH_SIZE)
# print(batch_anchor, batch_positive, batch_negative, batch_labels_anchor, batch_labels_positive, batch_labels_negative)
feed_dict = {
train_anchor_data: batch_anchor,
train_positive_data: batch_positive,
train_negative_data: batch_negative,
labels_anchor: batch_labels_anchor,
labels_positive: batch_labels_positive,
labels_negative: batch_labels_negative,
keep_prob: 0.80
}
_, l, ls, summary = sess.run(
[optimizer_op, loss, learning_rate, merged],
feed_dict=feed_dict)
print("%d the %s train reslut" % (step, datetime.datetime.now()))
print('the triplet loss %g' % l)
train_write.add_summary(summary, step)
if step % 100 == 0:
Saver.save(sess, './logs_tensorboard_3/')
train_write.close()
def main(data, iter_num, labels, train=True):
BATCH_SIZE = 2
ITERATION = iter_num
embedding_size = 1024
CLASS_NUM = 30
train_anchor_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
labels_anchor = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
keep_prob = tf.placeholder(tf.float32, shape=[], name='keep_probability')
pre_logits = model.NetworkModel(train_anchor_data, keep_prob=keep_prob)
logits = tf.nn.l2_normalize(pre_logits, 1, 1e-12, name='embeddings')
# print(logits.get_shape().as_list())
data_train, train_labels = data, labels
# data_train = data
print(data.shape)
print(labels.shape)
Saver = tf.train.Saver()
with tf.Session() as sess:
# test_write = tf.summary.FileWriter('./logs_tensorboard/triple/test/', sess.graph)
sess.run(tf.global_variables_initializer())
Saver.restore(sess, './logs_tensorboard2/')
emb_array = np.zeros(
(ITERATION // BATCH_SIZE * BATCH_SIZE, embedding_size))
print(np.shape(emb_array))
for step in range(ITERATION // BATCH_SIZE):
batch_anchor, batch_labels = data_train[step * BATCH_SIZE:(step + 1) * BATCH_SIZE], \
train_labels[step * BATCH_SIZE:(step + 1) * BATCH_SIZE]
# batch_anchor = data_train[step * BATCH_SIZE:(step + 1) * BATCH_SIZE]
feed_dict = {
train_anchor_data: batch_anchor,
labels_anchor: batch_labels,
keep_prob: 1.0
}
Logits = sess.run(logits, feed_dict=feed_dict)
emb_array[step * BATCH_SIZE:(step + 1) * BATCH_SIZE, :] = Logits
print('the triplet loss %g' % step)
np.savetxt('valid_feature.txt', emb_array)
if train:
print('Training classifier')
class_name = ['%2d' % (i) for i in range(CLASS_NUM)]
print(class_name)
# SVMmodel = SVC(kernel='rbf', probability=True)
knn = KNeighborsClassifier(n_neighbors=30)
print("fit !!!")
# SVMmodel.fit(emb_array, labels[:ITERATION // BATCH_SIZE * BATCH_SIZE])
knn.fit(emb_array, labels[:ITERATION // BATCH_SIZE * BATCH_SIZE])
with open('train_model_pickle30', 'wb') as outfile:
pickle.dump((knn, class_name), outfile)
# pickle.dump((SVMmodel, class_name), outfile)
print('Saved classifier model to file train_model_pickle')
else:
print('Testing classifier30')
with open('train_model_pickle30', 'rb') as infile:
(knn, class_name) = pickle.load(infile)
print('Loaded classifier model from file train_model_pickle')
predictions = knn.predict_proba(emb_array)
np.savetxt('test_k_30_image_result.csv', predictions, fmt='%g')
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s %0.3f' % (i, class_name[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print("Accuracy %.3f" % accuracy)
def main(argv=None):
with tf.Graph().as_default() as graph:
Margin = 0.25
BATCH_SIZE = 40
ITERATION = 2000000
data_num = 16640
train_anchor_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
train_positive_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
train_negative_data = tf.placeholder(tf.float32,
shape=[BATCH_SIZE, 224, 224, 3],
name='anchor')
# labels_anchor = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
# labels_positive = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
# labels_negative = tf.placeholder(tf.float32, shape=[BATCH_SIZE])
tf.summary.image('input_image', train_anchor_data, 10)
train_data = tf.concat(
[train_anchor_data, train_positive_data, train_negative_data],
axis=0)
pre_logits1 = model.NetworkModel(train_data, keep_prob=0.80)
# pre_logits2 = model.NetworkModel(train_positive_data, keep_prob=0.80, reuse=True)
# pre_logits3 = model.NetworkModel(train_negative_data, keep_prob=0.80, reuse=True)
pre_logits1 = tf.nn.l2_normalize(pre_logits1,
1,
1e-10,
name='embeddings')
# pre_logits2 = tf.nn.l2_normalize(pre_logits2, 1, 1e-10, name='embeddings')
# pre_logits3 = tf.nn.l2_normalize(pre_logits3, 1, 1e-10, name='embeddings')
# print(logits.get_shape().as_list())
vgg_train_anchor, vgg_train_positive, vgg_train_negative = tf.unstack(
tf.reshape(pre_logits1, [-1, 3, 256]), 3, 1)
loss, positives, negatives = utils.compute_triplet_loss(
vgg_train_anchor, vgg_train_positive, vgg_train_negative, Margin)
regularizer_losses = tf.add_n(tf.get_collection("losses"))
total_loss = loss + regularizer_losses
# print(total_loss)
# num_batches_per_epoch = int(data_num / BATCH_SIZE * 3)
# num_steps_per_epoch = num_batches_per_epoch # Because one step is one batch processed
# decay_steps = int(2 * num_steps_per_epoch)
global_step = tf.Variable(tf.constant(0, dtype=tf.int64))
lr = tf.train.exponential_decay(learning_rate=0.001,
global_step=global_step,
decay_steps=data_num // BATCH_SIZE,
decay_rate=0.96,
staircase=True)
train_op = tf.train.GradientDescentOptimizer(
learning_rate=lr).minimize(total_loss, global_step=global_step)
Saver = tf.train.Saver()
tf.summary.scalar('total_loss', total_loss)
tf.summary.scalar('loss', loss)
tf.summary.scalar('learning_rate', lr)
tf.summary.scalar('positives', positives)
tf.summary.scalar('negatives', negatives)
# tf.summary.scalar('pos', pos)
# tf.summary.scalar('neg', neg)
merged = tf.summary.merge_all()
data, labels = data_process.input_data()
print(data.shape)
print(labels.shape)
dataShufflu = DataShuffle(data, labels)
with tf.Session() as sess:
train_write = tf.summary.FileWriter(
'/home/lenovo/yql/pig_data/triplet_model/logs_tensorboard2/',
sess.graph)
sess.run(tf.global_variables_initializer())
# Saver.restore(sess, '/home/lenovo/yql/pig_data/triplet_model/logs_tensorboard2/')
for step in range(ITERATION):
batch_anchor, batch_positive, batch_negative, batch_labels_anchor, batch_labels_positive,\
batch_labels_negative = dataShufflu.get_triplet(n_labels=30, n_triplet=BATCH_SIZE)
feed_dict = {
train_anchor_data: batch_anchor,
train_positive_data: batch_positive,
train_negative_data: batch_negative
# labels_anchor: batch_labels_anchor,
# labels_positive: batch_labels_positive,
# labels_negative: batch_labels_negative
}
_, l, summary, Loss = sess.run(
[train_op, total_loss, merged, loss], feed_dict=feed_dict)
print("%d the %s train reslut" %
(step, datetime.datetime.now()))
print('the triplet loss %g' % Loss)
# print('the triplet total loss %g' % l)
train_write.add_summary(summary, step)
if step % 200 == 0:
Saver.save(
sess,
'/home/lenovo/yql/pig_data/triplet_model/logs_tensorboard2/'
)
train_write.close()