def training(n_epochs=40,
batch_size=256,
num_neg=4,
resample=True,
verbose=10):
args = parse_args()
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
data = Dataset(args.path)
idx_images, idx2item = data.item2image_u2a()
#idx_images, idx2item = data.item2image()
#idx_images = idx_images [:, -1:, :]
#print idx_images[0]
#exit(0)
users = data.train['UserId'].unique()
user2idx = pd.Series(data=np.arange(len(users)), index=users)
item2idx = pd.Series(data=np.arange(len(idx2item)), index=idx2item)
n_items, n_factors, embedding = idx_images.shape
print n_items, len(idx2item)
print "the shape of images is", idx_images.shape
model = Ourmodel(n_items, len(users), n_factors, idx_images, embedding,
0.01)
model.build_graph()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
print "initialized"
if args.pretrain == True:
print "load the pretrain model"
saver.restore(sess,
"./model2/music_GCNEncoder_model.ckpt") # usermap
#saver.restore(sess, "./model/usermap.ckpt")
eval(sess, model, data, item2idx, user2idx, idx2item, users, True)
#return
else:
start_time = time.time()
train_l, train_r = generate_input_fast(data.train, item2idx,
user2idx, num_neg)
print "generating data needed for 1 epoch", time.time(
) - start_time, 's'
print "training for learning usermape"
for epoch in range(n_epochs):
if resample == True:
#user_negs = data.neg_sample_pop(idx2item, pop, pop_items)
#user_negs = data.neg_sample(idx2item)
train_l, train_r = generate_input_fast(
data.train, item2idx, user2idx, num_neg)
losses, lrs, l2_losss = [], [], []
start = 0
while start < train_l.shape[0]:
feed_dict = dict()
feed_dict[model.user_input] = train_l[start:(start +
batch_size)]
feed_dict[model.item_input] = train_r[start:(start +
batch_size)]
feed_dict[model.global_step] = epoch
_, loss, lr, l2_loss = sess.run([
model.optimizer, model.loss, model.learning_rate,
model.l2_loss
], feed_dict)
start += batch_size
losses.append(loss)
lrs.append(lr)
l2_losss.append(l2_loss)
print "epoch", epoch, ", loss", np.array(losses).mean(
), np.array(lrs).mean(), np.array(l2_losss).mean()
#print lrs
#eval(sess, model, data, item2idx, user2idx, idx2item, users, False)
if (epoch + 1) % verbose == 0:
eval(sess, model, data, item2idx, user2idx, idx2item,
users)
#train_l, train_r = generate_input(data.train, item2idx, user2idx, num_neg)
#save(model.user_bias.eval(), 'user_bias.epoch' + str(epoch+1))
#saver.save(sess, "./model2/music_GCNEncoder_model.ckpt")
print "training for completion for itemmaps by using usermap"
## get usermap and complete the lossed ens of the items
# get usermap embedding and itemmap embedding
user_map_embedding = model.read_usermap_value().eval(
) # shape (n, k, d)
item_map_embedding = copy.copy(idx_images)
# get the item-user connection, idx
i_us = get_i_us(data.train, item2idx, user2idx)
# do completion
for iidx in range(item_map_embedding.shape[0]):
item_map = item_map_embedding[iidx]
item_flag = np.sum(item_map, axis=-1)
for k in range(item_flag.shape[0]):
if iidx in i_us and item_flag[k] <= 0.0:
item_map_embedding[iidx, k] = np.mean(
user_map_embedding[i_us[iidx], k], axis=0)
# updata the itemmap embedding
#print item_map_embedding[0,:3,]
sess.run(tf.assign(model.item_map_embedding, item_map_embedding))
for epoch in range(n_epochs):
if resample == True:
#user_negs = data.neg_sample_pop(idx2item, pop, pop_items)
#user_negs = data.neg_sample(idx2item)
train_l, train_r = generate_input_fast(data.train, item2idx,
user2idx, num_neg)
losses, lrs, l2_losss = [], [], []
start = 0
while start < train_l.shape[0]:
feed_dict = dict()
feed_dict[model.user_input] = train_l[start:(start +
batch_size)]
feed_dict[model.item_input] = train_r[start:(start +
batch_size)]
feed_dict[model.global_step] = epoch
_, loss, lr, l2_loss = sess.run([
model.optimizer, model.loss, model.learning_rate,
model.l2_loss
], feed_dict)
start += batch_size
losses.append(loss)
lrs.append(lr)
l2_losss.append(l2_loss)
print "epoch", epoch, ", loss", np.array(losses).mean(), np.array(
lrs).mean(), np.array(l2_losss).mean()
#print lrs
#eval(sess, model, data, item2idx, user2idx, idx2item, users, False)
if (epoch + 1) % verbose == 0:
eval(sess, model, data, item2idx, user2idx, idx2item, users)
def training(n_epochs=40,
batch_size=256,
num_neg=4,
resample=True,
verbose=10):
args = parse_args()
data = Dataset('../data/ml-1m/')
idx_images, idx2item = data.item2image_u2a()
#idx_images, idx2item = data.item2image()
#idx_images = idx_images [:, -1:, :]
#print idx_images[0]
users = data.train['UserId'].unique()
user2idx = pd.Series(data=np.arange(len(users)), index=users)
item2idx = pd.Series(data=np.arange(len(idx2item)), index=idx2item)
start_time = time.time()
train_l, train_r = generate_input_fast(data.train, item2idx, user2idx,
num_neg)
print "generating data needed for 1 epoch", time.time() - start_time, 's'
n_items, n_factors, embedding = idx_images.shape
print n_items, len(idx2item)
print "the shape of images is", idx_images.shape
model = Ourmodel(n_items, len(users), n_factors, idx_images, embedding,
0.01)
model.build_graph()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
print "initialized"
#initialize for training batches
#feed_dict[model.user_input] = train_l
#feed_dict[model.item_input] = train_r
#eval(sess, model, data, item2idx, user2idx, idx2item, users, False)
#save(model.user_bias.eval(), 'user_bias.epoch0')
#save_UI_simMap(sess, model, train_l, train_r, 'train_DT.pkl')
if args.pretrain == True:
print "load the pretrain model"
saver.restore(sess, "./model/model.ckpt")
#eval(sess, model, data, item2idx, user2idx, idx2item, users)
#save_UI_simMap(sess, model, train_l, train_r, 'train_DT.pkl')
eval(sess, model, data, item2idx, user2idx, idx2item, users, True)
return
for epoch in range(n_epochs):
if resample == True:
#user_negs = data.neg_sample_pop(idx2item, pop, pop_items)
#user_negs = data.neg_sample(idx2item)
train_l, train_r = generate_input_fast(data.train, item2idx,
user2idx, num_neg)
losses, lrs, l2_losss = [], [], []
start = 0
while start < train_l.shape[0]:
feed_dict = dict()
feed_dict[model.user_input] = train_l[start:(start +
batch_size)]
feed_dict[model.item_input] = train_r[start:(start +
batch_size)]
feed_dict[model.global_step] = epoch
'''print epoch, start, start+batch_size
print train_l[start:(start+batch_size)]
print train_r[start:(start+batch_size)]'''
_, loss, lr, l2_loss = sess.run([
model.optimizer, model.loss, model.learning_rate,
model.l2_loss
], feed_dict)
'''print loss'''
start += batch_size
losses.append(loss)
lrs.append(lr)
l2_losss.append(l2_loss)
print "epoch", epoch, ", loss", np.array(losses).mean(), np.array(
lrs).mean(), np.array(l2_losss).mean()
#print lrs
#eval(sess, model, data, item2idx, user2idx, idx2item, users, False)
if (epoch + 1) % verbose == 0:
eval(sess, model, data, item2idx, user2idx, idx2item, users)
#train_l, train_r = generate_input(data.train, item2idx, user2idx, num_neg)
#save(model.user_bias.eval(), 'user_bias.epoch' + str(epoch+1))
#save_UI_simMap(sess, model, train_l, train_r, 'train_DT.pkl')
#eval(sess, model, data, item2idx, user2idx, idx2item, users, True)
#eval(sess, model, data, item2idx, user2idx, idx2item, users)
saver.save(sess, "./model/usermap.ckpt")
