def infer(train_data, test_data, user_size, item_size):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
############################### CREATE MODEL #############################
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
model = NCF.NCF(FLAGS.embedding_size, user_size, item_size, FLAGS.lr,
FLAGS.optim, FLAGS.initializer, FLAGS.loss_func, FLAGS.activation,
FLAGS.regularizer, iterator, FLAGS.topK, FLAGS.dropout, is_training=True)
model.build()
# train_init_op = iterator.make_initializer(train_data)
ckpt = tf.train.get_checkpoint_state(FLAGS.model_dir)
if ckpt:
print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
model.saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("model files do not exist")
exit(1)
############################### Training ####################################
total_time = 0
count = 0
for epoch in range(FLAGS.epochs):
################################ EVALUATION ##################################
sess.run(model.iterator.make_initializer(test_data))
model.is_training = False
HR, MRR, NDCG = [], [], []
start_time = time.time()
try:
while True:
prediction, label = model.step(sess, None)
count = count + 1
label = int(label[0])
HR.append(metrics.hit(label, prediction))
MRR.append(metrics.mrr(label, prediction))
NDCG.append(metrics.ndcg(label, prediction))
except tf.errors.OutOfRangeError:
hr = np.array(HR).mean()
mrr = np.array(MRR).mean()
ndcg = np.array(NDCG).mean()
print("Epoch %d testing " %epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
print("HR is %.3f, MRR is %.3f, NDCG is %.3f" %(hr, mrr, ndcg))
total_time += time.time() - start_time
print("Total Epochs: %d on inference " %(epoch+1))
print("Total recommendations: %d" % (count * FLAGS.batch_size))
print("Approximate accelerator time in seconds is: %.2f" % total_time)
print("Approximate accelerator performance in recommendations/second is: %.2f" % (float(count * FLAGS.batch_size)/float(total_time)))
def test(model, sess, test_data, all_items_idx, user_bought):
model.is_training = False
model.test_first = True
all_items_embed = []
HR, MRR, NDCG = [], [], []
########################## GET ALL ITEM EMBEDDING ONCE ######################
for sample in test_data.get_all_test():
item_embed = model.step(sess, sample, None, None)
all_items_embed.append(item_embed[0][0])
model.test_first = False
all_items_embed = np.array(all_items_embed)
########################## TEST FOR EACH USER QUERY PAIR #####################
for sample in test_data.get_instance():
item_indices = model.step(sess, sample, all_items_embed, None)[0]
itemID = sample[3]
reviewerID = sample[4]
ranking_list = all_items_idx[item_indices].tolist()
top_idx = []
u_bought = user_bought[reviewerID] if reviewerID in user_bought else []
while len(
top_idx
) < FLAGS.topK: # delete those items already bought by the user
candidate_item = ranking_list.pop()
if candidate_item not in u_bought or candidate_item == itemID:
top_idx.append(candidate_item)
top_idx = np.array(top_idx)
HR.append(metrics.hit(itemID, top_idx))
MRR.append(metrics.mrr(itemID, top_idx))
NDCG.append(metrics.ndcg(itemID, top_idx))
hr = np.array(HR).mean()
mrr = np.array(MRR).mean()
ndcg = np.array(NDCG).mean()
print("HR is %.3f, MRR is %.3f, NDCG is %.3f" % (hr, mrr, ndcg))
def train(train_data, test_data, n_user, n_item):
with tf.Session() as sess:
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
model = NCF.NCF(FLAGS.embedding_size, n_user, n_item, FLAGS.lr,
FLAGS.optim, FLAGS.initializer, FLAGS.loss_func, FLAGS.activation,
FLAGS.regularizer, iterator, FLAGS.topK, FLAGS.dropout, is_training=True)
model.build()
# 有参数就读取, 没有就重新训练
ckpt = tf.train.get_checkpoint_state(FLAGS.model_dir)
if ckpt and ckpt.model_checkpoint_path:
print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
# 加载模型参数
model.saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("Creating model with fresh parameters.")
sess.run(tf.global_variables_initializer())
count = 0
# 在训练集上训练epochs轮
for epoch in range(FLAGS.epochs):
# 训练集的迭代器
sess.run(model.iterator.make_initializer(train_data))
model.is_training = True
model.get_data()
start_time = time.time()
try:
while True: # 直到生成器没数据, 也就是所有训练数据遍历一次
model.step(sess, count)
count += 1
except tf.errors.OutOfRangeError:
# 打印训练一轮的时间
print("Epoch %d training " % epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
# 测试集的迭代器
sess.run(model.iterator.make_initializer(test_data))
model.is_training = False
model.get_data()
start_time = time.time()
HR, MRR, NDCG = [], [], []
pred_item, gt_item = model.step(sess, None)
try:
while True: # 直到生成器没数据, 也就是所有测试数据遍历一次
pred_item, gt_item = model.step(sess, None)
# 对于测试集每同一批量数据的item都一样, 所以只取一个
gt_item = int(gt_item[0])
HR.append(metrics.hit(gt_item, pred_item))
MRR.append(metrics.mrr(gt_item, pred_item))
NDCG.append(metrics.ndcg(gt_item, pred_item))
# 评估值取均值
except tf.errors.OutOfRangeError:
hr = np.array(HR).mean()
mrr = np.array(MRR).mean()
ndcg = np.array(NDCG).mean()
print("Epoch %d testing " % epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
print("HR is %.3f, MRR is %.3f, NDCG is %.3f" % (hr, mrr, ndcg))
# 保存模型参数
checkpoint_path = os.path.join(FLAGS.model_dir, "NCF.ckpt")
model.saver.save(sess, checkpoint_path)
def train(train_data, test_data, user_size, item_size):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
############################### CREATE MODEL #############################
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
model = NCF.NCF(FLAGS.embedding_size, user_size, item_size, FLAGS.lr,
FLAGS.optim, FLAGS.initializer, FLAGS.loss_func, FLAGS.activation,
FLAGS.regularizer, iterator, FLAGS.topK, FLAGS.dropout, is_training=True)
model.build()
# train_init_op = iterator.make_initializer(train_data)
ckpt = tf.train.get_checkpoint_state(FLAGS.model_dir)
if ckpt:
print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
model.saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("Creating model with fresh parameters.")
sess.run(tf.global_variables_initializer())
############################### Training ####################################
count = 0
for epoch in range(FLAGS.epochs):
sess.run(model.iterator.make_initializer(train_data))
model.is_training = True
start_time = time.time()
try:
while True:
model.step(sess, count)
count += 1
except tf.errors.OutOfRangeError:
print("Epoch %d training " %epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
################################ EVALUATION ##################################
sess.run(model.iterator.make_initializer(test_data))
model.is_training = False
start_time = time.time()
HR, MRR, NDCG = [], [], []
try:
while True:
prediction, label = model.step(sess, None)
label = int(label[0])
HR.append(metrics.hit(label, prediction))
MRR.append(metrics.mrr(label, prediction))
NDCG.append(metrics.ndcg(label, prediction))
except tf.errors.OutOfRangeError:
hr = np.array(HR).mean()
mrr = np.array(MRR).mean()
ndcg = np.array(NDCG).mean()
print("Epoch %d testing " %epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
print("HR is %.3f, MRR is %.3f, NDCG is %.3f" %(hr, mrr, ndcg))
################################## SAVE MODEL ################################
checkpoint_path = os.path.join(FLAGS.model_dir, "NCF.ckpt")
model.saver.save(sess, checkpoint_path)
def train(train_data,test_data,user_size,item_size):
with tf.Session() as sess:
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
model = NCF.NCF(FLAGS.embedding_size, user_size, item_size, FLAGS.lr,
FLAGS.optim, FLAGS.initializer, FLAGS.loss_func, FLAGS.activation,
FLAGS.regularizer, iterator, FLAGS.topK, FLAGS.dropout, is_training=True)
model.build()
ckpt = tf.train.get_checkpoint_state(FLAGS.model_dir)
if ckpt:
print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
model.saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("Creating model with fresh parameters.")
sess.run(tf.global_variables_initializer())
count = 0
for epoch in range(FLAGS.epochs):
sess.run(model.iterator.make_initializer(train_data))
model.is_training = True
model.get_data()
start_time = time.time()
try:
while True:
model.step(sess, count)
count += 1
except tf.errors.OutOfRangeError:
print("Epoch %d training " % epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
sess.run(model.iterator.make_initializer(test_data))
model.is_training = False
model.get_data()
start_time = time.time()
HR,MRR,NDCG = [],[],[]
prediction, label = model.step(sess, None)
try:
while True:
prediction, label = model.step(sess, None)
label = int(label[0])
HR.append(metrics.hit(label, prediction))
MRR.append(metrics.mrr(label, prediction))
NDCG.append(metrics.ndcg(label, prediction))
except tf.errors.OutOfRangeError:
hr = np.array(HR).mean()
mrr = np.array(MRR).mean()
ndcg = np.array(NDCG).mean()
print("Epoch %d testing " % epoch + "Took: " + time.strftime("%H: %M: %S",
time.gmtime(time.time() - start_time)))
print("HR is %.3f, MRR is %.3f, NDCG is %.3f" % (hr, mrr, ndcg))
################################## SAVE MODEL ################################
checkpoint_path = os.path.join(FLAGS.model_dir, "NCF.ckpt")
model.saver.save(sess, checkpoint_path)
