diff --git a/deepface/basemodels/Boosting.py b/deepface/basemodels/Boosting.py
index fe73ae65e..d8cb732d2 100644
--- a/deepface/basemodels/Boosting.py
+++ b/deepface/basemodels/Boosting.py
@@ -4,8 +4,6 @@
 from os import path
 from pathlib import Path
 import numpy as np
-import lightgbm as lgb #lightgbm==2.3.1
-
 from deepface.commons import functions, distance as dst
 
 def loadModel():
@@ -35,10 +33,16 @@ def validate_model(model):
 		#print("Ensemble learning will be applied for ", found_models," models")
 		valid = True
 	else:
-		raise ValueError("You would like to apply ensemble learning and pass pre-built models but models must contain [VGG-Face, Facenet, OpenFace, DeepFace] but you passed "+found_models)
+		
+		missing_ones = set(['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace']) - set(found_models)
+		
+		raise ValueError("You'd like to apply ensemble method and pass pre-built models but models must contain [VGG-Face, Facenet, OpenFace, DeepFace] but you passed "+str(found_models)+". So, you need to pass "+str(missing_ones)+" models as well.")
 
 def build_gbm():
 	
+	#this is not a must dependency
+	import lightgbm as lgb #lightgbm==2.3.1
+	
 	home = str(Path.home())
 	
 	if os.path.isfile(home+'/.deepface/weights/face-recognition-ensemble-model.txt') != True:
diff --git a/deepface/basemodels/DlibResNet.py b/deepface/basemodels/DlibResNet.py
index 1a859db57..f4cba3a37 100644
--- a/deepface/basemodels/DlibResNet.py
+++ b/deepface/basemodels/DlibResNet.py
@@ -1,4 +1,3 @@
-import dlib #19.20.0
 import os
 import zipfile
 import bz2
@@ -9,6 +8,9 @@
 class DlibResNet:
 	
 	def __init__(self):
+		
+		#this is not a must dependency
+		import dlib #19.20.0
 	
 		self.layers = [DlibMetaData()]