removing trailing spaces

facelib/FaceType.py

@@ -31,4 +31,3 @@ to_string_list = [ 'half_face',
                    'avatar',
                    'mark_only'
                     ]
-                        

mainscripts/VideoEd.py

@@ -194,4 +194,3 @@ def video_from_sequence( input_dir, output_file, reference_file=None, ext=None,
         job = job.run()
     except:
         io.log_err ("ffmpeg fail, job commandline:" + str(job.compile()) )
-           

models/Model_SAE/Model.py

@@ -124,25 +124,26 @@ class SAEModel(ModelBase):
         target_dst_ar  = [ Input ( ( bgr_shape[0] // (2**i) ,)*2 + (bgr_shape[-1],) ) for i in range(ms_count-1, -1, -1)]
         target_dstm_ar = [ Input ( ( mask_shape[0] // (2**i) ,)*2 + (mask_shape[-1],) ) for i in range(ms_count-1, -1, -1)]
 
+        use_bn = True
 
         models_list = []
         weights_to_load = []
         if self.options['archi'] == 'liae':
-            self.encoder = modelify(SAEModel.LIAEEncFlow(resolution, self.options['lighter_encoder'], ed_ch_dims=ed_ch_dims)  ) (Input(bgr_shape))
+            self.encoder = modelify(SAEModel.LIAEEncFlow(resolution, self.options['lighter_encoder'], ed_ch_dims=ed_ch_dims, use_bn=use_bn)  ) (Input(bgr_shape))
 
             enc_output_Inputs = [ Input(K.int_shape(x)[1:]) for x in self.encoder.outputs ]
 
-            self.inter_B = modelify(SAEModel.LIAEInterFlow(resolution, ae_dims=ae_dims)) (enc_output_Inputs)
-            self.inter_AB = modelify(SAEModel.LIAEInterFlow(resolution, ae_dims=ae_dims)) (enc_output_Inputs)
+            self.inter_B = modelify(SAEModel.LIAEInterFlow(resolution, ae_dims=ae_dims, use_bn=use_bn)) (enc_output_Inputs)
+            self.inter_AB = modelify(SAEModel.LIAEInterFlow(resolution, ae_dims=ae_dims, use_bn=use_bn)) (enc_output_Inputs)
 
             inter_output_Inputs = [ Input( np.array(K.int_shape(x)[1:])*(1,1,2) ) for x in self.inter_B.outputs ]
 
-            self.decoder = modelify(SAEModel.LIAEDecFlow (bgr_shape[2],ed_ch_dims=ed_ch_dims//2, multiscale_count=self.ms_count )) (inter_output_Inputs)
+            self.decoder = modelify(SAEModel.LIAEDecFlow (bgr_shape[2],ed_ch_dims=ed_ch_dims//2, multiscale_count=self.ms_count, use_bn=use_bn )) (inter_output_Inputs)
 
             models_list += [self.encoder, self.inter_B, self.inter_AB, self.decoder]
 
             if self.options['learn_mask']:
-                self.decoderm = modelify(SAEModel.LIAEDecFlow (mask_shape[2],ed_ch_dims=int(ed_ch_dims/1.5) )) (inter_output_Inputs)
+                self.decoderm = modelify(SAEModel.LIAEDecFlow (mask_shape[2],ed_ch_dims=int(ed_ch_dims/1.5), use_bn=use_bn )) (inter_output_Inputs)
                 models_list += [self.decoderm]
 
             if not self.is_first_run():
@@ -495,6 +496,10 @@ class SAEModel(ModelBase):
     def initialize_nn_functions():
         exec (nnlib.import_all(), locals(), globals())
 
+        def BatchNorm():
+            return BatchNormalization(axis=-1,  gamma_initializer=RandomNormal(1., 0.02) )
+
+
         class ResidualBlock(object):
             def __init__(self, filters, kernel_size=3, padding='same', use_reflection_padding=False):
                 self.filters = filters
@@ -521,21 +526,30 @@ class SAEModel(ModelBase):
                 return var_x
         SAEModel.ResidualBlock = ResidualBlock
 
-        def downscale (dim):
+        def downscale (dim, use_bn=False):
             def func(x):
-                return LeakyReLU(0.1)(Conv2D(dim, kernel_size=5, strides=2, padding='same', kernel_initializer=RandomNormal(0, 0.02))(x))
+                if use_bn:
+                    return LeakyReLU(0.1)(BatchNorm()(Conv2D(dim, kernel_size=5, strides=2, padding='same', kernel_initializer=RandomNormal(0, 0.02), use_bias=False)(x)))
+                else:
+                    return LeakyReLU(0.1)(Conv2D(dim, kernel_size=5, strides=2, padding='same', kernel_initializer=RandomNormal(0, 0.02))(x))
             return func
         SAEModel.downscale = downscale
 
-        def downscale_sep (dim):
+        def downscale_sep (dim, use_bn=False):
             def func(x):
-                return LeakyReLU(0.1)(SeparableConv2D(dim, kernel_size=5, strides=2, padding='same', depthwise_initializer=RandomNormal(0, 0.02), pointwise_initializer=RandomNormal(0, 0.02) )(x))
+                if use_bn:
+                    return LeakyReLU(0.1)(BatchNorm()(SeparableConv2D(dim, kernel_size=5, strides=2, padding='same', depthwise_initializer=RandomNormal(0, 0.02), pointwise_initializer=RandomNormal(0, 0.02), use_bias=False )(x)))
+                else:
+                    return LeakyReLU(0.1)(SeparableConv2D(dim, kernel_size=5, strides=2, padding='same', depthwise_initializer=RandomNormal(0, 0.02), pointwise_initializer=RandomNormal(0, 0.02) )(x))
             return func
         SAEModel.downscale_sep = downscale_sep
 
-        def upscale (dim):
+        def upscale (dim, use_bn=False):
             def func(x):
-                return SubpixelUpscaler()(LeakyReLU(0.1)(Conv2D(dim * 4, kernel_size=3, strides=1, padding='same', kernel_initializer=RandomNormal(0, 0.02) )(x)))
+                if use_bn:
+                    return SubpixelUpscaler()(LeakyReLU(0.1)(BatchNorm()(Conv2D(dim * 4, kernel_size=3, strides=1, padding='same', kernel_initializer=RandomNormal(0,0.02), use_bias=False )(x))))
+                else:
+                    return SubpixelUpscaler()(LeakyReLU(0.1)(Conv2D(dim * 4, kernel_size=3, strides=1, padding='same', kernel_initializer=RandomNormal(0, 0.02) )(x)))
             return func
         SAEModel.upscale = upscale
 
@@ -547,7 +561,7 @@ class SAEModel(ModelBase):
 
 
     @staticmethod
-    def LIAEEncFlow(resolution, light_enc, ed_ch_dims=42):
+    def LIAEEncFlow(resolution, light_enc, ed_ch_dims=42, use_bn=False):
         exec (nnlib.import_all(), locals(), globals())
         upscale = SAEModel.upscale
         downscale = SAEModel.downscale
@@ -559,20 +573,20 @@ class SAEModel(ModelBase):
             x = input
             x = downscale(ed_dims)(x)
             if not light_enc:
-                x = downscale(ed_dims*2)(x)
-                x = downscale(ed_dims*4)(x)
-                x = downscale(ed_dims*8)(x)
+                x = downscale(ed_dims*2, use_bn=use_bn)(x)
+                x = downscale(ed_dims*4, use_bn=use_bn)(x)
+                x = downscale(ed_dims*8, use_bn=use_bn)(x)
             else:
-                x = downscale_sep(ed_dims*2)(x)
-                x = downscale(ed_dims*4)(x)
-                x = downscale_sep(ed_dims*8)(x)
+                x = downscale_sep(ed_dims*2, use_bn=use_bn)(x)
+                x = downscale(ed_dims*4, use_bn=use_bn)(x)
+                x = downscale_sep(ed_dims*8, use_bn=use_bn)(x)
 
             x = Flatten()(x)
             return x
         return func
 
     @staticmethod
-    def LIAEInterFlow(resolution, ae_dims=256):
+    def LIAEInterFlow(resolution, ae_dims=256, use_bn=False):
         exec (nnlib.import_all(), locals(), globals())
         upscale = SAEModel.upscale
         lowest_dense_res=resolution // 16
@@ -582,12 +596,12 @@ class SAEModel(ModelBase):
             x = Dense(ae_dims)(x)
             x = Dense(lowest_dense_res * lowest_dense_res * ae_dims*2)(x)
             x = Reshape((lowest_dense_res, lowest_dense_res, ae_dims*2))(x)
-            x = upscale(ae_dims*2)(x)
+            x = upscale(ae_dims*2, use_bn=use_bn)(x)
             return x
         return func
 
     @staticmethod
-    def LIAEDecFlow(output_nc,ed_ch_dims=21, multiscale_count=1):
+    def LIAEDecFlow(output_nc,ed_ch_dims=21, multiscale_count=1, use_bn=False):
         exec (nnlib.import_all(), locals(), globals())
         upscale = SAEModel.upscale
         to_bgr = SAEModel.to_bgr
@@ -597,17 +611,17 @@ class SAEModel(ModelBase):
             x = input[0]
 
             outputs = []
-            x1     = upscale(ed_dims*8)( x )       
+            x1     = upscale(ed_dims*8, use_bn=use_bn)( x )
 
             if multiscale_count >= 3:
                 outputs += [ to_bgr(output_nc) ( x1 ) ]
 
-            x2     = upscale(ed_dims*4)( x1 )    
+            x2     = upscale(ed_dims*4, use_bn=use_bn)( x1 )
 
             if multiscale_count >= 2:
                 outputs += [ to_bgr(output_nc) ( x2 ) ]
 
-            x3     = upscale(ed_dims*2)( x2 )
+            x3     = upscale(ed_dims*2, use_bn=use_bn)( x2 )
 
             outputs += [ to_bgr(output_nc) ( x3 ) ]
 

nnlib/device.py

@@ -348,4 +348,3 @@ if device.backend is None:
         else:
             #has NVSMI, no capable CUDA-devices, also plaidML was failed, then CPU only
             device.backend = "tensorflow-cpu"
-

nnlib/nnlib.py

@@ -541,7 +541,6 @@ NLayerDiscriminator = nnlib.NLayerDiscriminator
             result = CAInitializerMPSubprocessor ( [ (i, K.int_shape(conv_weights)) for i, conv_weights in enumerate(conv_weights_list) ], K.floatx(), K.image_data_format() ).run()
             for idx, weights in result:
                 K.set_value ( conv_weights_list[idx], weights )
-            
         nnlib.CAInitializerMP = CAInitializerMP
             
       

samples/SampleGeneratorBase.py

@@ -22,4 +22,3 @@ class SampleGeneratorBase(object):
     def __next__(self):
         #implement your own iterator
         return None
-    

utils/image_utils.py

@@ -422,4 +422,3 @@ def reduce_colors (img_bgr, n_colors):
     img_bgr = cv2.cvtColor( np.array(img_rgb_p, dtype=np.float32) / 255.0, cv2.COLOR_RGB2BGR )
 
     return img_bgr
-  

utils/struct_utils.py

@@ -3,4 +3,3 @@ import struct
 def struct_unpack(data, counter, fmt):
     fmt_size = struct.calcsize(fmt)
     return (counter+fmt_size,) + struct.unpack (fmt, data[counter:counter+fmt_size])
-