def encoder(self):
""" The original Faceswap Encoder Network.
The encoder for the original model has it's weights shared between both the "A" and "B"
side of the model, so only one instance is created :func:`build_model`. However this same
instance is then used twice (once for A and once for B) meaning that the weights get
shared.
Returns
-------
:class:`keras.models.Model`
The Keras encoder model, for sharing between inputs from both sides.
"""
input_ = Input(shape=self.input_shape)
var_x = input_
var_x = Conv2DBlock(128, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(256, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(512, activation="leakyrelu")(var_x)
if not self.low_mem:
var_x = Conv2DBlock(1024, activation="leakyrelu")(var_x)
var_x = Dense(self.encoder_dim)(Flatten()(var_x))
var_x = Dense(4 * 4 * 1024)(var_x)
var_x = Reshape((4, 4, 1024))(var_x)
var_x = UpscaleBlock(512, activation="leakyrelu")(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" Unbalanced Encoder """
kwargs = dict(kernel_initializer=self.kernel_initializer)
encoder_complexity = 128 if self.low_mem else self.config["complexity_encoder"]
dense_dim = 384 if self.low_mem else 512
dense_shape = self.input_shape[0] // 16
input_ = Input(shape=self.input_shape)
var_x = input_
var_x = Conv2DBlock(encoder_complexity,
normalization="instance",
activation="leakyrelu",
**kwargs)(var_x)
var_x = Conv2DBlock(encoder_complexity * 2,
normalization="instance",
activation="leakyrelu",
**kwargs)(var_x)
var_x = Conv2DBlock(encoder_complexity * 4, **kwargs, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(encoder_complexity * 6, **kwargs, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(encoder_complexity * 8, **kwargs, activation="leakyrelu")(var_x)
var_x = Dense(self.encoder_dim,
kernel_initializer=self.kernel_initializer)(Flatten()(var_x))
var_x = Dense(dense_shape * dense_shape * dense_dim,
kernel_initializer=self.kernel_initializer)(var_x)
var_x = Reshape((dense_shape, dense_shape, dense_dim))(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" Encoder Network """
kwargs = dict(kernel_initializer=self.kernel_initializer)
input_ = Input(shape=self.input_shape)
in_conv_filters = self.input_shape[0]
if self.input_shape[0] > 128:
in_conv_filters = 128 + (self.input_shape[0] - 128) // 4
dense_shape = self.input_shape[0] // 16
var_x = Conv2DBlock(in_conv_filters, activation=None, **kwargs)(input_)
tmp_x = var_x
var_x = LeakyReLU(alpha=0.2)(var_x)
res_cycles = 8 if self.config.get("lowmem", False) else 16
for _ in range(res_cycles):
nn_x = ResidualBlock(in_conv_filters, **kwargs)(var_x)
var_x = nn_x
# consider adding scale before this layer to scale the residual chain
tmp_x = LeakyReLU(alpha=0.1)(tmp_x)
var_x = add([var_x, tmp_x])
var_x = Conv2DBlock(128, activation="leakyrelu", **kwargs)(var_x)
var_x = PixelShuffler()(var_x)
var_x = Conv2DBlock(128, activation="leakyrelu", **kwargs)(var_x)
var_x = PixelShuffler()(var_x)
var_x = Conv2DBlock(128, activation="leakyrelu", **kwargs)(var_x)
var_x = SeparableConv2DBlock(256, **kwargs)(var_x)
var_x = Conv2DBlock(512, activation="leakyrelu", **kwargs)(var_x)
if not self.config.get("lowmem", False):
var_x = SeparableConv2DBlock(1024, **kwargs)(var_x)
var_x = Dense(self.encoder_dim, **kwargs)(Flatten()(var_x))
var_x = Dense(dense_shape * dense_shape * 1024, **kwargs)(var_x)
var_x = Reshape((dense_shape, dense_shape, 1024))(var_x)
var_x = UpscaleBlock(512, activation="leakyrelu", **kwargs)(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder_liae(self):
""" DFL SAE LIAE Encoder Network """
input_ = Input(shape=self.input_shape)
dims = self.input_shape[-1] * self.encoder_dim
var_x = Conv2DBlock(dims, activation="leakyrelu")(input_)
var_x = Conv2DBlock(dims * 2, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(dims * 4, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(dims * 8, activation="leakyrelu")(var_x)
var_x = Flatten()(var_x)
return KerasModel(input_, var_x, name="encoder_liae")
def encoder(self):
""" Encoder Network """
input_ = Input(shape=self.input_shape)
var_x = input_
var_x = Conv2DBlock(128)(var_x)
var_x = Conv2DBlock(256)(var_x)
var_x = Conv2DBlock(512)(var_x)
var_x = Conv2DBlock(1024)(var_x)
var_x = Flatten()(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" Encoder Network """
input_ = Input(shape=self.input_shape)
var_x = input_
var_x = Conv2DBlock(128, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(256, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(512, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(1024, activation="leakyrelu")(var_x)
var_x = Flatten()(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" DFL H128 Encoder """
input_ = Input(shape=self.input_shape)
var_x = Conv2DBlock(128, activation="leakyrelu")(input_)
var_x = Conv2DBlock(256, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(512, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(1024, activation="leakyrelu")(var_x)
var_x = Dense(self.encoder_dim)(Flatten()(var_x))
var_x = Dense(8 * 8 * self.encoder_dim)(var_x)
var_x = Reshape((8, 8, self.encoder_dim))(var_x)
var_x = UpscaleBlock(self.encoder_dim, activation="leakyrelu")(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" Encoder Network """
input_ = Input(shape=self.input_shape)
var_x = input_
var_x = Conv2DBlock(128)(var_x)
var_x = Conv2DBlock(256)(var_x)
var_x = Conv2DBlock(512)(var_x)
var_x = Dense(self.encoder_dim)(Flatten()(var_x))
var_x = Dense(4 * 4 * 512)(var_x)
var_x = Reshape((4, 4, 512))(var_x)
var_x = UpscaleBlock(256)(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" DFL H128 Encoder """
input_ = Input(shape=self.input_shape)
var_x = Conv2DBlock(128)(input_)
var_x = Conv2DBlock(256)(var_x)
var_x = Conv2DBlock(512)(var_x)
var_x = Conv2DBlock(1024)(var_x)
var_x = Dense(self.encoder_dim)(Flatten()(var_x))
var_x = Dense(8 * 8 * self.encoder_dim)(var_x)
var_x = Reshape((8, 8, self.encoder_dim))(var_x)
var_x = UpscaleBlock(self.encoder_dim)(var_x)
return KerasModel(input_, var_x)
def encoder_df(self):
""" DFL SAE DF Encoder Network"""
input_ = Input(shape=self.input_shape)
dims = self.input_shape[-1] * self.encoder_dim
lowest_dense_res = self.input_shape[0] // 16
var_x = Conv2DBlock(dims, activation="leakyrelu")(input_)
var_x = Conv2DBlock(dims * 2, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(dims * 4, activation="leakyrelu")(var_x)
var_x = Conv2DBlock(dims * 8, activation="leakyrelu")(var_x)
var_x = Dense(self.ae_dims)(Flatten()(var_x))
var_x = Dense(lowest_dense_res * lowest_dense_res * self.ae_dims)(var_x)
var_x = Reshape((lowest_dense_res, lowest_dense_res, self.ae_dims))(var_x)
var_x = UpscaleBlock(self.ae_dims, activation="leakyrelu")(var_x)
return KerasModel(input_, var_x, name="encoder_df")
def encoder(self):
""" RealFace Encoder Network """
input_ = Input(shape=self.input_shape)
var_x = input_
encoder_complexity = self.config["complexity_encoder"]
for idx in range(self.downscalers_no - 1):
var_x = Conv2DBlock(encoder_complexity * 2**idx, activation=None)(var_x)
var_x = LeakyReLU(alpha=0.2)(var_x)
var_x = ResidualBlock(encoder_complexity * 2**idx, use_bias=True)(var_x)
var_x = ResidualBlock(encoder_complexity * 2**idx, use_bias=True)(var_x)
var_x = Conv2DBlock(encoder_complexity * 2**(idx + 1), activation="leakyrelu")(var_x)
return KerasModel(input_, var_x, name="encoder")
def encoder(self):
""" DeLight Encoder Network """
input_ = Input(shape=self.input_shape)
var_x = input_
var_x1 = Conv2DBlock(self.encoder_filters // 2,
activation="leakyrelu")(var_x)
var_x2 = AveragePooling2D()(var_x)
var_x2 = LeakyReLU(0.1)(var_x2)
var_x = Concatenate()([var_x1, var_x2])
var_x1 = Conv2DBlock(self.encoder_filters,
activation="leakyrelu")(var_x)
var_x2 = AveragePooling2D()(var_x)
var_x2 = LeakyReLU(0.1)(var_x2)
var_x = Concatenate()([var_x1, var_x2])
var_x1 = Conv2DBlock(self.encoder_filters * 2,
activation="leakyrelu")(var_x)
var_x2 = AveragePooling2D()(var_x)
var_x2 = LeakyReLU(0.1)(var_x2)
var_x = Concatenate()([var_x1, var_x2])
var_x1 = Conv2DBlock(self.encoder_filters * 4,
activation="leakyrelu")(var_x)
var_x2 = AveragePooling2D()(var_x)
var_x2 = LeakyReLU(0.1)(var_x2)
var_x = Concatenate()([var_x1, var_x2])
var_x1 = Conv2DBlock(self.encoder_filters * 8,
activation="leakyrelu")(var_x)
var_x2 = AveragePooling2D()(var_x)
var_x2 = LeakyReLU(0.1)(var_x2)
var_x = Concatenate()([var_x1, var_x2])
var_x = Dense(self.encoder_dim)(Flatten()(var_x))
var_x = Dropout(0.05)(var_x)
var_x = Dense(4 * 4 * 1024)(var_x)
var_x = Dropout(0.05)(var_x)
var_x = Reshape((4, 4, 1024))(var_x)
return KerasModel(input_, var_x, name="encoder")
def __call__(self, inputs):
""" Call the original Faceswap Encoder
Parameters
----------
inputs: tensor
The input tensor to the Faceswap Encoder
Returns
-------
tensor
The output tensor from the Faceswap Encoder
"""
var_x = inputs
filters = self._config["fs_original_min_filters"]
for i in range(self._depth):
var_x = Conv2DBlock(filters,
activation="leakyrelu",
name=f"fs_enc_convblk_{i}")(var_x)
filters = min(self._config["fs_original_max_filters"], filters * 2)
return var_x