StarMirror/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2024-03-22 13:10:55 +08:00
Code Issues Projects Releases Wiki Activity

AMP, SAEHD: reverted GAN to december version.

Browse Source
This commit is contained in:
iperov 2021-07-07 21:45:43 +04:00
parent b4b72d056f
commit ee1bc83a14
3 changed files with 5 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
core/leras/models/PatchDiscriminator.py
View File

@ -146,11 +146,7 @@ class UNetPatchDiscriminator(nn.ModelBase):
prev_ch = in_ch
self.convs = []
self.res1 = []
self.res2 = []
self.upconvs = []
self.upres1 = []
self.upres2 = []
layers = self.find_archi(patch_size)
level_chs = { i-1:v for i,v in enumerate([ min( base_ch * (2**i), 512 ) for i in range(len(layers)+1)]) }
@ -160,14 +156,8 @@ class UNetPatchDiscriminator(nn.ModelBase):
for i, (kernel_size, strides) in enumerate(layers):
self.convs.append ( nn.Conv2D( level_chs[i-1], level_chs[i], kernel_size=kernel_size, strides=strides, padding='SAME') )
self.res1.append ( ResidualBlock(level_chs[i]) )
self.res2.append ( ResidualBlock(level_chs[i]) )
self.upconvs.insert (0, nn.Conv2DTranspose( level_chs[i]*(2 if i != len(layers)-1 else 1), level_chs[i-1], kernel_size=kernel_size, strides=strides, padding='SAME') )
self.upres1.insert (0, ResidualBlock(level_chs[i-1]*2) )
self.upres2.insert (0, ResidualBlock(level_chs[i-1]*2) )
self.out_conv = nn.Conv2D( level_chs[-1]*2, 1, kernel_size=1, padding='VALID')
self.center_out = nn.Conv2D( level_chs[len(layers)-1], 1, kernel_size=1, padding='VALID')
@ -178,19 +168,15 @@ class UNetPatchDiscriminator(nn.ModelBase):
x = tf.nn.leaky_relu( self.in_conv(x), 0.2 )
encs = []
for conv, res1,res2 in zip(self.convs, self.res1, self.res2):
for conv in self.convs:
encs.insert(0, x)
x = tf.nn.leaky_relu( conv(x), 0.2 )
x = res1(x)
x = res2(x)
center_out, x = self.center_out(x), tf.nn.leaky_relu( self.center_conv(x), 0.2 )
for i, (upconv, enc, upres1, upres2 ) in enumerate(zip(self.upconvs, encs, self.upres1, self.upres2)):
for i, (upconv, enc) in enumerate(zip(self.upconvs, encs)):
x = tf.nn.leaky_relu( upconv(x), 0.2 )
x = tf.concat( [enc, x], axis=nn.conv2d_ch_axis)
x = upres1(x)
x = upres2(x)
return center_out, self.out_conv(x)

2
models/Model_AMP/Model.py
View File

@ -123,7 +123,7 @@ class AMPModel(ModelBase):
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
self.options['gan_patch_size'] = gan_patch_size
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-64", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 64 )
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-512", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 512 )
self.options['gan_dims'] = gan_dims
self.options['ct_mode'] = io.input_str (f"Color transfer for src faceset", default_ct_mode, ['none','rct','lct','mkl','idt','sot'], help_message="Change color distribution of src samples close to dst samples. Try all modes to find the best.")

4
models/Model_SAEHD/Model.py
View File

@ -156,7 +156,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
gan_patch_size = np.clip ( io.input_int("GAN patch size", default_gan_patch_size, add_info="3-640", help_message="The higher patch size, the higher the quality, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is resolution / 8." ), 3, 640 )
self.options['gan_patch_size'] = gan_patch_size
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-64", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 64 )
gan_dims = np.clip ( io.input_int("GAN dimensions", default_gan_dims, add_info="4-512", help_message="The dimensions of the GAN network. The higher dimensions, the more VRAM is required. You can get sharper edges even at the lowest setting. Typical fine value is 16." ), 4, 512 )
self.options['gan_dims'] = gan_dims
if 'df' in self.options['archi']:
@ -467,7 +467,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
gpu_G_loss += self.options['true_face_power']*DLoss(gpu_src_code_d_ones, gpu_src_code_d)
gpu_D_code_loss = (DLoss(gpu_src_code_d_ones , gpu_dst_code_d) + \
gpu_D_code_loss = (DLoss(gpu_dst_code_d_ones , gpu_dst_code_d) + \
DLoss(gpu_src_code_d_zeros, gpu_src_code_d) ) * 0.5
gpu_D_code_loss_gvs += [ nn.gradients (gpu_D_code_loss, self.code_discriminator.get_weights() ) ]