diff --git a/doc/manual_en_google_translated.docx b/doc/manual_en_google_translated.docx
index cd6c76d..f4575e1 100644
Binary files a/doc/manual_en_google_translated.docx and b/doc/manual_en_google_translated.docx differ
diff --git a/doc/manual_en_google_translated.pdf b/doc/manual_en_google_translated.pdf
index 828349d..e858506 100644
Binary files a/doc/manual_en_google_translated.pdf and b/doc/manual_en_google_translated.pdf differ
diff --git a/doc/manual_ru.pdf b/doc/manual_ru.pdf
index 6712983..892b04d 100644
Binary files a/doc/manual_ru.pdf and b/doc/manual_ru.pdf differ
diff --git a/doc/manual_ru_source.docx b/doc/manual_ru_source.docx
index d733115..d9543a6 100644
Binary files a/doc/manual_ru_source.docx and b/doc/manual_ru_source.docx differ
diff --git a/facelib/PoseEstimator.py b/facelib/PoseEstimator.py
index cc0f694..d74ed3e 100644
--- a/facelib/PoseEstimator.py
+++ b/facelib/PoseEstimator.py
@@ -23,7 +23,6 @@ class PoseEstimator(object):
         self.angles = [90, 45, 30, 10, 2]
         self.alpha_cat_losses = [7,5,3,1,1]
         self.class_nums = [ angle+1 for angle in self.angles ]
-        
         self.model = PoseEstimator.BuildModel(resolution, class_nums=self.class_nums)
         
 
@@ -57,7 +56,7 @@ class PoseEstimator(object):
         loss_pitch = []
         loss_yaw = []
         loss_roll = []
-        
+
         for i,class_num in enumerate(self.class_nums):
             a = self.alpha_cat_losses[i]
             loss_pitch += [ a*K.categorical_crossentropy( inp_bins_t[i*3+0], bins_t[i*3+0] ) ]
@@ -65,7 +64,12 @@ class PoseEstimator(object):
             loss_roll  += [ a*K.categorical_crossentropy( inp_bins_t[i*3+2], bins_t[i*3+2] ) ]
             
         idx_tensor =  K.constant( np.array([idx for idx in range(self.class_nums[0])], dtype=K.floatx() ) )
-        pitch_t, yaw_t, roll_t = K.sum ( bins_t[0] * idx_tensor, 1), K.sum ( bins_t[1] * idx_tensor, 1), K.sum ( bins_t[2] * idx_tensor, 1)
+        #pitch_t, yaw_t, roll_t = K.sum ( bins_t[0] * idx_tensor, 1), K.sum ( bins_t[1] * idx_tensor, 1), K.sum ( bins_t[2] * idx_tensor, 1)
+        
+        pitch_t, yaw_t, roll_t = nnlib.tf.reduce_sum ( bins_t[0] * idx_tensor, 1), nnlib.tf.reduce_sum ( bins_t[1] * idx_tensor, 1), nnlib.tf.reduce_sum ( bins_t[2] * idx_tensor, 1)
+        
+        
+        
         
         reg_alpha = 2
         reg_pitch_loss = reg_alpha * K.mean(K.square( inp_pitch_t - pitch_t), -1)        
@@ -75,7 +79,6 @@ class PoseEstimator(object):
         pitch_loss = reg_pitch_loss + sum(loss_pitch)
         yaw_loss   = reg_yaw_loss   + sum(loss_yaw)
         roll_loss  = reg_roll_loss  + sum(loss_roll)
-    
         opt = Adam(lr=0.000001)
         
         if training:
diff --git a/models/Model_SAE/Model.py b/models/Model_SAE/Model.py
index 067a3d8..760ed47 100644
--- a/models/Model_SAE/Model.py
+++ b/models/Model_SAE/Model.py
@@ -67,7 +67,7 @@ class SAEModel(ModelBase):
             self.options['d_ch_dims'] = np.clip ( io.input_int("Decoder dims per channel (10-85 ?:help skip:%d) : " % (default_d_ch_dims) , default_d_ch_dims, help_message="More decoder dims help to get better details, but require more VRAM. You can fine-tune model size to fit your GPU." ), 10, 85 )
             #self.options['remove_gray_border'] = io.input_bool ("Remove gray border? (y/n, ?:help skip:n) : ", False, help_message="Removes gray border of predicted face, but requires more computing resources.")
             self.options['multiscale_decoder'] = io.input_bool ("Use multiscale decoder? (y/n, ?:help skip:n) : ", False, help_message="Multiscale decoder helps to get better details.")
-            self.options['ca_weights'] = io.input_bool ("Use CA weights? (y/n, ?:help skip: %s ) : " % (yn_str[def_ca_weights]), def_ca_weights, help_message="Initialize network with 'Convolution Aware' weights. This may help to achieve a higher accuracy model, but consumes time at first run.")
+            self.options['ca_weights'] = io.input_bool ("Use CA weights? (y/n, ?:help skip: %s ) : " % (yn_str[def_ca_weights]), def_ca_weights, help_message="Initialize network with 'Convolution Aware' weights. This may help to achieve a higher accuracy model, but consumes a time at first run.")
         else:
             self.options['ae_dims'] = self.options.get('ae_dims', default_ae_dims)
             self.options['e_ch_dims'] = self.options.get('e_ch_dims', default_e_ch_dims)