def like_or_dislike_users(self, users):
# automatically like or dislike users based on your previously trained
# model on your historical preference.
# facenet settings from export_embeddings....
model_dir = '20170512-110547'
data_dir = 'temp_images_aligned'
embeddings_name = 'temp_embeddings.npy'
labels_name = 'temp_labels.npy'
labels_strings_name = 'temp_label_strings.npy'
is_aligned = True
image_size = 160
margin = 44
gpu_memory_fraction = 1.0
image_batch = 1000
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the facenet model
facenet.load_model(model_dir)
for user in users:
clean_temp_images()
urls = user.get_photos(width='640')
image_list = download_url_photos(urls,
user.id,
is_temp=True)
# align the database
tindetheus_align.main(input_dir='temp_images',
output_dir='temp_images_aligned')
# export the embeddinggs from the aligned database
train_set = facenet.get_dataset(data_dir)
image_list_temp, label_list = facenet.get_image_paths_and_labels(
train_set)
label_strings = [
name
for name in os.listdir(os.path.expanduser(data_dir))
if os.path.isdir(
os.path.join(os.path.expanduser(data_dir), name))
]
# Get input and output tensors
images_placeholder = tf.get_default_graph(
).get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Run forward pass to calculate embeddings
nrof_images = len(image_list_temp)
print('Number of images: ', nrof_images)
batch_size = image_batch
if nrof_images % batch_size == 0:
nrof_batches = nrof_images // batch_size
else:
nrof_batches = (nrof_images // batch_size) + 1
print('Number of batches: ', nrof_batches)
embedding_size = embeddings.get_shape()[1]
emb_array = np.zeros((nrof_images, embedding_size))
start_time = time.time()
for i in range(nrof_batches):
if i == nrof_batches - 1:
n = nrof_images
else:
n = i * batch_size + batch_size
# Get images for the batch
if is_aligned is True:
images = facenet.load_data(
image_list_temp[i * batch_size:n], False,
False, image_size)
else:
images = load_and_align_data(
image_list_temp[i * batch_size:n], image_size,
margin, gpu_memory_fraction)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
# Use the facenet model to calcualte embeddings
embed = sess.run(embeddings, feed_dict=feed_dict)
emb_array[i * batch_size:n, :] = embed
print('Completed batch', i + 1, 'of', nrof_batches)
run_time = time.time() - start_time
print('Run time: ', run_time)
# export emedings and labels
label_list = np.array(label_list)
np.save(embeddings_name, emb_array)
if emb_array.size > 0:
# calculate the 128 average embedding per profiles
X = calc_avg_emb_temp(emb_array)
# ealuate on the model
yhat = self.model.predict(X)
if yhat[0] == 1:
didILike = 'Like'
else:
didILike = 'Dislike'
else:
# there were no faces in this profile
didILike = 'Dislike'
print(
'********************************************************'
)
print(user.name, user.age, didILike)
print(
'********************************************************'
)
dbase_names = move_images_temp(image_list, user.id)
if didILike == 'Like':
print(user.like())
self.likes_left -= 1
else:
print(user.dislike())
userList = [
user.id, user.name, user.age, user.bio,
user.distance_km, user.jobs, user.schools,
user.get_photos(width='640'), dbase_names, didILike
]
self.al_database.append(userList)
np.save('al_database.npy', self.al_database)
clean_temp_images_aligned()
def main(model_dir='20170512-110547',
data_dir='database_aligned',
is_aligned=True,
image_size=160,
margin=44,
gpu_memory_fraction=1.0,
image_batch=1000,
embeddings_name='embeddings.npy',
labels_name='labels.npy',
labels_strings_name='label_strings.npy',
return_image_list=False):
train_set = facenet.get_dataset(data_dir)
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
# fetch the classes (labels as strings) exactly as it's done in get_dataset
path_exp = os.path.expanduser(data_dir)
classes = [
path for path in os.listdir(path_exp)
if os.path.isdir(os.path.join(path_exp, path))
]
# get the label strings
label_strings = [
name for name in classes if os.path.isdir(os.path.join(path_exp, name))
]
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
facenet.load_model(model_dir)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0") # noqa: E501
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0") # noqa: E501
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0") # noqa: E501
# Run forward pass to calculate embeddings
nrof_images = len(image_list)
print('Number of images: ', nrof_images)
batch_size = image_batch
if nrof_images % batch_size == 0:
nrof_batches = nrof_images // batch_size
else:
nrof_batches = (nrof_images // batch_size) + 1
print('Number of batches: ', nrof_batches)
embedding_size = embeddings.get_shape()[1]
emb_array = np.zeros((nrof_images, embedding_size))
start_time = time.time()
for i in range(nrof_batches):
if i == nrof_batches - 1:
n = nrof_images
else:
n = i * batch_size + batch_size
# Get images for the batch
if is_aligned is True:
images = facenet.load_data(image_list[i * batch_size:n],
False, False, image_size)
else:
images = load_and_align_data(image_list[i * batch_size:n],
image_size, margin,
gpu_memory_fraction)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
# Use the facenet model to calculate embeddings
embed = sess.run(embeddings, feed_dict=feed_dict)
emb_array[i * batch_size:n, :] = embed
print('Completed batch', i + 1, 'of', nrof_batches)
run_time = time.time() - start_time
print('Run time: ', run_time)
# export embeddings and labels
label_list = np.array(label_list)
np.save(embeddings_name, emb_array)
if emb_array.size > 0:
labels_final = (label_list) - np.min(label_list)
np.save(labels_name, labels_final)
label_strings = np.array(label_strings)
np.save(labels_strings_name, label_strings[labels_final])
np.save('image_list.npy', image_list)
if return_image_list:
np.save('validation_image_list.npy', image_list)
return image_list, emb_array
def main(args, facebook_token):
# There are three function choices: browse, build, like
# browse: review new tinder profiles and store them in your database
# train: use machine learning to create a new model that likes and dislikes
# profiles based on your historical preference
# like: use your machine leanring model to like new tinder profiles
if args.function == 'browse':
my_sess = client(facebook_token, args.distance, args.model_dir,
likes_left=args.likes)
my_sess.browse()
elif args.function == 'train':
# align the database
tindetheus_align.main()
# export the embeddings from the aligned database
export_embeddings.main(model_dir=args.model_dir,
image_batch=args.image_batch)
# calculate the n average embedding per profiles
X, y = calc_avg_emb()
# fit and save a logistic regression model to the database
fit_log_reg(X, y)
elif args.function == 'validate':
print('\n\nAttempting to validate the dataset...\n\n')
valdir = 'validation'
# align the validation dataset
tindetheus_align.main(input_dir=valdir,
output_dir=valdir+'_aligned')
# export embeddings
# y is the image list, X is the embedding_array
image_list, emb_array = export_embeddings.main(model_dir=args.model_dir, # noqa: E501
data_dir=valdir+'_aligned',
image_batch=args.image_batch,
embeddings_name='val_embeddings.npy',
labels_name='val_labels.npy',
labels_strings_name='val_label_strings.npy', # noqa: E501
return_image_list=True)
# print(image_list)
# convert the image list to a numpy array to take advantage of
# numpy array slicing
image_list = np.array(image_list)
print('\n\nEvaluating trained model\n \n')
model = joblib.load('log_reg_model.pkl')
yhat = model.predict(emb_array)
# print(yhat)
# 0 should be dislike, and 1 should be like
# if this is backwards, there is probablly a bug...
dislikes = yhat == 0
likes = yhat == 1
show_images(image_list[dislikes], holdon=True, title='Dislike')
print('\n\nGenerating plots...\n\n')
plt.title('Dislike')
show_images(image_list[likes], holdon=True, title='Like')
plt.title('Like')
cols = ['Image name', 'Model prediction (0=Dislike, 1=Like)']
results = np.array((image_list, yhat)).T
print('\n\nSaving results to validation.csv\n\n')
my_results_DF = pd.DataFrame(results, columns=cols)
my_results_DF.to_csv('validation.csv')
plt.show()
elif args.function == 'like':
print('... Loading the facenet model ...')
print('... be patient this may take some time ...')
with tf.Graph().as_default():
with tf.Session() as sess:
# pass the tf session into client object
my_sess = client(facebook_token, args.distance, args.model_dir,
likes_left=args.likes, tfsess=sess)
# Load the facenet model
facenet.load_model(my_sess.model_dir)
print('Facenet model loaded successfully!!!')
# automatically like users
my_sess.like()
else:
text = '''You must specify a function. Your choices are either
tindetheus browse
tindetheus train
tindetheus like
tindetheus validate'''
print(text)