CalvinBackup/iperov-DeepFaceLab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upgraded to TF version 1.13.2

Browse Source 
Removed the wait at first launch for most graphics cards.

Increased speed of training by 10-20%, but you have to retrain all models from scratch.

SAEHD:

added option 'use float16'
	Experimental option. Reduces the model size by half.
	Increases the speed of training.
	Decreases the accuracy of the model.
	The model may collapse or not train.
	Model may not learn the mask in large resolutions.

true_face_training option is replaced by
"True face power". 0.0000 .. 1.0
Experimental option. Discriminates the result face to be more like the src face. Higher value - stronger discrimination.
Comparison - https://i.imgur.com/czScS9q.png
This commit is contained in:
Colombo
2020-01-25 21:58:19 +04:00
parent a3dfcb91b9
commit 76ca79216e
49 changed files with 1320 additions and 1297 deletions
Download Patch File Download Diff File Expand all files Collapse all files
facelib/S3FDExtractor.py
+53 -53
View File
@@ -8,9 +8,9 @@ from core.leras import nn
class S3FDExtractor(object):
def __init__(self, place_model_on_cpu=False):
nn.initialize()
nn.initialize(data_format="NHWC")
tf = nn.tf
model_path = Path(__file__).parent / "S3FD.npy"
if not model_path.exists():
raise Exception("Unable to load S3FD.npy")
@@ -19,143 +19,143 @@ class S3FDExtractor(object):
def __init__(self, n_channels, **kwargs):
self.n_channels = n_channels
super().__init__(**kwargs)
def build_weights(self):
self.weight = tf.get_variable ("weight", (1, 1, 1, self.n_channels), dtype=nn.tf_floatx, initializer=tf.initializers.ones )
def get_weights(self):
return [self.weight]
def __call__(self, inputs):
x = inputs
x = x / (tf.sqrt( tf.reduce_sum( tf.pow(x, 2), axis=-1, keepdims=True ) ) + 1e-10) * self.weight
return x
class S3FD(nn.ModelBase):
def __init__(self):
super().__init__(name='S3FD')
def on_build(self):
self.minus = tf.constant([104,117,123], dtype=nn.tf_floatx )
self.conv1_1 = nn.Conv2D(3, 64, kernel_size=3, strides=1, padding='SAME')
self.conv1_2 = nn.Conv2D(64, 64, kernel_size=3, strides=1, padding='SAME')
self.conv2_1 = nn.Conv2D(64, 128, kernel_size=3, strides=1, padding='SAME')
self.conv2_2 = nn.Conv2D(128, 128, kernel_size=3, strides=1, padding='SAME')
self.conv3_1 = nn.Conv2D(128, 256, kernel_size=3, strides=1, padding='SAME')
self.conv3_2 = nn.Conv2D(256, 256, kernel_size=3, strides=1, padding='SAME')
self.conv3_3 = nn.Conv2D(256, 256, kernel_size=3, strides=1, padding='SAME')
self.conv4_1 = nn.Conv2D(256, 512, kernel_size=3, strides=1, padding='SAME')
self.conv4_2 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME')
self.conv4_3 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME')
self.conv5_1 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME')
self.conv5_2 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME')
self.conv5_3 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME')
self.fc6 = nn.Conv2D(512, 1024, kernel_size=3, strides=1, padding=3)
self.fc7 = nn.Conv2D(1024, 1024, kernel_size=1, strides=1, padding='SAME')
self.conv6_1 = nn.Conv2D(1024, 256, kernel_size=1, strides=1, padding='SAME')
self.conv6_2 = nn.Conv2D(256, 512, kernel_size=3, strides=2, padding='SAME')
self.conv7_1 = nn.Conv2D(512, 128, kernel_size=1, strides=1, padding='SAME')
self.conv7_2 = nn.Conv2D(128, 256, kernel_size=3, strides=2, padding='SAME')
self.conv3_3_norm = L2Norm(256)
self.conv4_3_norm = L2Norm(512)
self.conv5_3_norm = L2Norm(512)
self.conv3_3_norm_mbox_conf = nn.Conv2D(256, 4, kernel_size=3, strides=1, padding='SAME')
self.conv3_3_norm_mbox_loc = nn.Conv2D(256, 4, kernel_size=3, strides=1, padding='SAME')
self.conv4_3_norm_mbox_conf = nn.Conv2D(512, 2, kernel_size=3, strides=1, padding='SAME')
self.conv4_3_norm_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME')
self.conv5_3_norm_mbox_conf = nn.Conv2D(512, 2, kernel_size=3, strides=1, padding='SAME')
self.conv5_3_norm_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME')
self.fc7_mbox_conf = nn.Conv2D(1024, 2, kernel_size=3, strides=1, padding='SAME')
self.fc7_mbox_loc = nn.Conv2D(1024, 4, kernel_size=3, strides=1, padding='SAME')
self.conv6_2_mbox_conf = nn.Conv2D(512, 2, kernel_size=3, strides=1, padding='SAME')
self.conv6_2_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME')
self.conv7_2_mbox_conf = nn.Conv2D(256, 2, kernel_size=3, strides=1, padding='SAME')
self.conv7_2_mbox_loc = nn.Conv2D(256, 4, kernel_size=3, strides=1, padding='SAME')
def forward(self, inp):
x, = inp
x = x - self.minus
x = tf.nn.relu(self.conv1_1(x))
x = tf.nn.relu(self.conv1_2(x))
x = tf.nn.relu(self.conv1_2(x))
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID")
x = tf.nn.relu(self.conv2_1(x))
x = tf.nn.relu(self.conv2_2(x))
x = tf.nn.relu(self.conv2_2(x))
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID")
x = tf.nn.relu(self.conv3_1(x))
x = tf.nn.relu(self.conv3_2(x))
x = tf.nn.relu(self.conv3_3(x))
f3_3 = x
x = tf.nn.relu(self.conv3_2(x))
x = tf.nn.relu(self.conv3_3(x))
f3_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID")
x = tf.nn.relu(self.conv4_1(x))
x = tf.nn.relu(self.conv4_2(x))
x = tf.nn.relu(self.conv4_3(x))
f4_3 = x
x = tf.nn.relu(self.conv4_2(x))
x = tf.nn.relu(self.conv4_3(x))
f4_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID")
x = tf.nn.relu(self.conv5_1(x))
x = tf.nn.relu(self.conv5_2(x))
x = tf.nn.relu(self.conv5_3(x))
f5_3 = x
x = tf.nn.relu(self.conv5_2(x))
x = tf.nn.relu(self.conv5_3(x))
f5_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID")
x = tf.nn.relu(self.fc6(x))
x = tf.nn.relu(self.fc7(x))
ffc7 = x
x = tf.nn.relu(self.conv6_1(x))
x = tf.nn.relu(self.conv6_2(x))
f6_2 = x
x = tf.nn.relu(self.conv7_1(x))
x = tf.nn.relu(self.conv7_2(x))
f7_2 = x
f3_3 = self.conv3_3_norm(f3_3)
f4_3 = self.conv4_3_norm(f4_3)
f5_3 = self.conv5_3_norm(f5_3)
cls1 = self.conv3_3_norm_mbox_conf(f3_3)
reg1 = self.conv3_3_norm_mbox_loc(f3_3)
cls2 = tf.nn.softmax(self.conv4_3_norm_mbox_conf(f4_3))
reg2 = self.conv4_3_norm_mbox_loc(f4_3)
cls3 = tf.nn.softmax(self.conv5_3_norm_mbox_conf(f5_3))
reg3 = self.conv5_3_norm_mbox_loc(f5_3)
cls4 = tf.nn.softmax(self.fc7_mbox_conf(ffc7))
reg4 = self.fc7_mbox_loc(ffc7)
cls5 = tf.nn.softmax(self.conv6_2_mbox_conf(f6_2))
reg5 = self.conv6_2_mbox_loc(f6_2)
cls6 = tf.nn.softmax(self.conv7_2_mbox_conf(f7_2))
reg6 = self.conv7_2_mbox_loc(f7_2)
# max-out background label
bmax = tf.maximum(tf.maximum(cls1[:,:,:,0:1], cls1[:,:,:,1:2]), cls1[:,:,:,2:3])
bmax = tf.maximum(tf.maximum(cls1[:,:,:,0:1], cls1[:,:,:,1:2]), cls1[:,:,:,2:3])
cls1 = tf.concat ([bmax, cls1[:,:,:,3:4] ], axis=-1)
cls1 = tf.nn.softmax(cls1)
return [cls1, reg1, cls2, reg2, cls3, reg3, cls4, reg4, cls5, reg5, cls6, reg6]
e = None
@@ -165,10 +165,10 @@ class S3FDExtractor(object):
if e is not None: e.__enter__()
self.model = S3FD()
self.model.load_weights (model_path)
if e is not None: e.__exit__(None,None,None)
self.model.build_for_run ([ ( tf.float32, (None,None,3) ) ])
if e is not None: e.__exit__(None,None,None)
self.model.build_for_run ([ ( tf.float32, nn.get4Dshape (None,None,3) ) ])
def __enter__(self):
return self
@@ -205,7 +205,7 @@ class S3FDExtractor(object):
detected_faces = [ [(l,t,r,b), (r-l)*(b-t) ] for (l,t,r,b) in detected_faces ]
detected_faces = sorted(detected_faces, key=operator.itemgetter(1), reverse=True )
detected_faces = [ x[0] for x in detected_faces]
if is_remove_intersects:
for i in range( len(detected_faces)-1, 0, -1):
l1,t1,r1,b1 = detected_faces[i]
@@ -214,8 +214,8 @@ class S3FDExtractor(object):
dx = min(r0, r1) - max(l0, l1)
dy = min(b0, b1) - max(t0, t1)
if (dx>=0) and (dy>=0):
detected_faces.pop(i)
detected_faces.pop(i)
return detected_faces
def refine(self, olist):