update == 04.20.2019 == (#242)

* superb improved fanseg

* _

* _

* added FANseg extractor for src and dst faces to use it in training

* -

* _

* _

* update to 'partial' func

* _

* trained FANSeg_256_full_face.h5,
new experimental models: AVATAR, RecycleGAN

* _

* _

* _

* fix for TCC mode cards(tesla), was conflict with plaidML initialization.

* _

* update manuals

* _

nnlib/device.py

@@ -274,28 +274,34 @@ has_nvml_cap = False
 #- CUDA build of DFL
 has_nvidia_device = os.environ.get("DFL_FORCE_HAS_NVIDIA_DEVICE", "0") == "1"
 
-plaidML_devices = []
-
-# Using plaidML OpenCL backend to determine system devices and has_nvidia_device
-try:
-    os.environ['PLAIDML_EXPERIMENTAL'] = 'false' #this enables work plaidML without run 'plaidml-setup'
-    import plaidml
-    ctx = plaidml.Context()
-    for d in plaidml.devices(ctx, return_all=True)[0]:
-        details = json.loads(d.details)
-        if details['type'] == 'CPU': #skipping opencl-CPU
-            continue
-        if 'nvidia' in details['vendor'].lower():
-            has_nvidia_device = True
-        plaidML_devices += [ {'id':d.id,
-                              'globalMemSize' : int(details['globalMemSize']),
-                              'description' : d.description.decode()
-                           }]
-    ctx.shutdown()
-except:
-    pass
-
-plaidML_devices_count = len(plaidML_devices)
+plaidML_devices = None
+def get_plaidML_devices():
+    global plaidML_devices
+    global has_nvidia_device
+    if plaidML_devices is None:
+        plaidML_devices = []
+        # Using plaidML OpenCL backend to determine system devices and has_nvidia_device
+        try:
+            os.environ['PLAIDML_EXPERIMENTAL'] = 'false' #this enables work plaidML without run 'plaidml-setup'
+            import plaidml
+            ctx = plaidml.Context()
+            for d in plaidml.devices(ctx, return_all=True)[0]:
+                details = json.loads(d.details)
+                if details['type'] == 'CPU': #skipping opencl-CPU
+                    continue
+                if 'nvidia' in details['vendor'].lower():
+                    has_nvidia_device = True
+                plaidML_devices += [ {'id':d.id,
+                                    'globalMemSize' : int(details['globalMemSize']),
+                                    'description' : d.description.decode()
+                                }]
+            ctx.shutdown()
+        except:
+            pass
+    return plaidML_devices
+ 
+if not has_nvidia_device:
+    get_plaidML_devices()    
 
 #choosing backend
 
@@ -324,7 +330,7 @@ if device.backend is None and not force_tf_cpu:
 
 if force_plaidML or (device.backend is None and not has_nvidia_device):
     #tensorflow backend was failed without has_nvidia_device , or forcing plaidML, trying to use plaidML backend
-    if plaidML_devices_count == 0:
+    if len(get_plaidML_devices()) == 0:
         #print ("plaidML: No capable OpenCL devices found. Falling back to tensorflow backend.")
         device.backend = None
     else:

nnlib/nnlib.py

@@ -52,7 +52,7 @@ Input = KL.Input
 
 Dense = KL.Dense
 Conv2D = nnlib.Conv2D
-Conv2DTranspose = KL.Conv2DTranspose
+Conv2DTranspose = nnlib.Conv2DTranspose
 SeparableConv2D = KL.SeparableConv2D
 MaxPooling2D = KL.MaxPooling2D
 UpSampling2D = KL.UpSampling2D
@@ -695,6 +695,26 @@ NLayerDiscriminator = nnlib.NLayerDiscriminator
                     x = ReflectionPadding2D( self.pad ) (x)
                 return self.func(x)
         nnlib.Conv2D = Conv2D
+        
+        class Conv2DTranspose():
+            def __init__ (self, *args, **kwargs):
+                self.reflect_pad = False
+                padding = kwargs.get('padding','')
+                if padding == 'zero':
+                    kwargs['padding'] = 'same'
+                if padding == 'reflect':
+                    kernel_size = kwargs['kernel_size']
+                    if (kernel_size % 2) == 1:
+                        self.pad = (kernel_size // 2,)*2
+                        kwargs['padding'] = 'valid'
+                        self.reflect_pad = True
+                self.func = keras.layers.Conv2DTranspose (*args, **kwargs)
+
+            def __call__(self,x):
+                if self.reflect_pad:
+                    x = ReflectionPadding2D( self.pad ) (x)
+                return self.func(x)
+        nnlib.Conv2DTranspose = Conv2DTranspose
 
     @staticmethod
     def import_keras_contrib(device_config):