def __predict__(args, params):
path = os.path.join(args.model_dir, "centroids_embeddings.npy")
centrois = np.load(path)
n_clusters = centrois.shape[1] # remember to get it before reshape
# print("centrois.shape=", centrois.shape)
centrois = centrois.reshape(-1, centrois.shape[2]) # flatten it for knn
# print("centrois.shape=", centrois.shape)
# Define the model
tf.logging.info("Creating the model...")
config = tf.estimator.RunConfig(
tf_random_seed=230,
model_dir=args.model_dir,
save_summary_steps=params.save_summary_steps)
estimator = tf.estimator.Estimator(model_fn, params=params, config=config)
# Compute embeddings on the test set
tf.logging.info("Predicting")
predictions = estimator.predict(
lambda: test_input_fn(args.data_dir, params))
embeddings = np.zeros((params.eval_size, params.embedding_size))
for i, p in enumerate(
predictions): # i:enumerate_id, p:{'embeddings':array(64)}
embeddings[i] = p['embeddings']
labels = np.zeros(shape=[params.num_labels * n_clusters], dtype=np.int)
for i in range(1, params.num_labels):
for j in range(n_clusters):
labels[n_clusters * i + j] = i
knn = KNeighborsClassifier(n_neighbors=3)
knn.fit(centrois, labels)
y_predicted = knn.predict(embeddings)
with tf.Session() as sess:
dataset = mnist_dataset.test(args.data_dir)
dataset = dataset.map(lambda img, lab: lab)
dataset = dataset.batch(params.eval_size)
labels_tensor = dataset.make_one_shot_iterator().get_next()
y_true = sess.run(labels_tensor)
print("Accuracy: " +
str(metrics.accuracy_score(y_true, y_predicted) * 100) + "%")
def test(params):
x, embeddings, labels, accuracy = model_fn(params, mode = 'test')
sess = tf.Session()
try:
tf.train.Saver().restore(sess , os.path.join(os.getcwd(), params.model_file))
except:
print("Please create a model before using it for prediction")
print("Run the following command-> python my_model.py train")
exit(1)
xdata, labeldata = test_input_fn()
print ("Model restored!")
start_time=time.time()
out, acc= sess.run([embeddings, accuracy], feed_dict={x:xdata, labels: labeldata})
test_time=time.time() - start_time
print("Time taken for prediction= ", test_time, "seconds")
print("Prediction accuracy", acc)
return out
parser.add_argument('--data_dir',
default='data/mnist',
help="Directory containing the dataset")
if __name__ == '__main__':
tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.INFO)
# Load the parameters
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Define the model
tf.logging.info("Creating the model...")
estimator = tf.estimator.Estimator(model_fn,
params=params,
model_dir=args.model_dir)
# Evaluate the model on the test set
tf.logging.info("Predict on the test set.")
print("dataset,", test_input_fn(args.data_dir, params))
res = estimator.predict(lambda: test_input_fn(args.data_dir, params))
print(next(res)['embeddings'].shape)
model_dir=args.model_dir,
save_summary_steps=params.save_summary_steps)
estimator = tf.estimator.Estimator(model_fn, params=params, config=config)
# Train the model
tf.logging.info("Starting training for {} epoch(s).".format(params.num_epochs))
estimator.train(lambda: train_input_fn(args.data_dir, params))
'''
path = args.model_save
try:
os.makedirs(path)
except OSError:
print ("Creation of the directory %s failed" % path)
else:
print ("Successfully created the directory %s " % path)
estimator.export_saved_model(path, serving_input_receiver_fn())
print("Model is SAVED !!")
'''
# Evaluate the model on the test set
tf.logging.info("Evaluation on test set.")
res = estimator.evaluate(lambda: test_input_fn(args.data_dir, params))
for key in res:
print("{}: {}".format(key, res[key]))
params = Params(json_path)
# Define the model
tf.logging.info("Creating the model...")
config = tf.estimator.RunConfig(
tf_random_seed=230,
model_dir=args.model_dir,
save_summary_steps=params.save_summary_steps)
estimator = tf.estimator.Estimator(model_fn, params=params, config=config)
# EMBEDDINGS VISUALIZATION
# Compute embeddings on the test set
tf.logging.info("Predicting")
predictions = estimator.predict(
lambda: test_input_fn(args.data_dir, params))
# TODO (@omoindrot): remove the hard-coded 10000
# embeddings = np.zeros((10000, params.embedding_size))
embeddings = np.zeros((params.eval_size, params.embedding_size))
for i, p in enumerate(
predictions): # i:enumerate_id, p:{'embeddings':array(64)}
embeddings[i] = p['embeddings']
tf.logging.info("Embeddings shape: {}".format(
embeddings.shape)) # (10000, 64)
# Visualize test embeddings
embedding_var = tf.Variable(embeddings, name='mnist_embedding')
eval_dir = os.path.join(args.model_dir, "eval")
default='experiments/base_model_v2',
help="Experiment directory containing params.json")
parser.add_argument('--data_dir',
default='data_for_model_resized_448*448/',
help="Directory containing the dataset")
if __name__ == '__main__':
tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.INFO)
# Load the parameters
args = parser.parse_args()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Define the model
tf.logging.info("Creating the model...")
estimator = tf.estimator.Estimator(model_fn,
params=params,
model_dir=args.model_dir)
# Evaluate the model on the test set
tf.logging.info("Evaluation on the test set.")
eval_dir = os.path.join(args.model_dir, "eval")
res = estimator.evaluate(
lambda: test_input_fn(args.data_dir, params, eval_dir))
for key in res:
print("{}: {}".format(key, res[key]))
params.vocab_fname, default_value='<unk>')
vocab_size = char_vocab.size()
params.pad_token_id = char_vocab.lookup(tf.constant(params.pad_token))
params.start_token_id = char_vocab.lookup(tf.constant(params.start_token))
params.end_token_id = char_vocab.lookup(tf.constant(params.end_token))
with tf.Session() as sess:
sess.run(tf.tables_initializer())
params.vocab_size_val = vocab_size.eval()
train_dataset = load_dataset_from_file(params.train_fname, char_vocab, params)
train_inputs = input_fn('train', train_dataset, params)
train_model_spec = model_fn('train', train_inputs, params, reuse=False)
test_inputs = test_input_fn('test', char_vocab, params)
test_model_spec = model_fn('test', test_inputs, params, reuse=True)
train_test(train_model_spec, test_model_spec, params, char_vocab_rev)
texts = ['ff', 'av']
preds, pred_logits = test_sess(texts,
test_model_spec,
params,
char_vocab_rev,
restore_from=os.path.join(
params.model_dir, 'last_weights'))
for text, t_preds, t_pred_logits in zip(texts, preds, pred_logits):
print('Input: {}'.format(text))
print('Top {} predictions:'.format(params.beam_width))
assert os.path.isfile(json_path), "No json configuration file found at {}".format(json_path)
params = Params(json_path)
# Define the model
tf.logging.info("Creating the model...")
config = tf.estimator.RunConfig(tf_random_seed=230,
model_dir=args.model_dir,
save_summary_steps=params.save_summary_steps)
estimator = tf.estimator.Estimator(model_fn, params=params, config=config)
# EMBEDDINGS VISUALIZATION
# Compute embeddings on the test set
tf.logging.info("Predicting")
predictions = estimator.predict(lambda: test_input_fn(args.data_dir, params))
# TODO (@omoindrot): remove the hard-coded 10000
embeddings = np.zeros((10000, params.embedding_size))
for i, p in enumerate(predictions):
embeddings[i] = p['embeddings']
tf.logging.info("Embeddings shape: {}".format(embeddings.shape))
# Visualize test embeddings
embedding_var = tf.Variable(embeddings, name='mnist_embedding')
eval_dir = os.path.join(args.model_dir, "eval")
summary_writer = tf.summary.FileWriter(eval_dir)
config = projector.ProjectorConfig()
