github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-22 06:23:20 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Did structural works for conversion

Browse source
This commit is contained in:
Laurent Olivier 2022-01-09 21:56:13 +01:00
commit 0572e6900e
1 changed files with 74 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

147
facelib/S3FDExtractor.py
View file

@ -3,13 +3,14 @@ from pathlib import Path
import cv2 import cv2
import numpy as np import numpy as np
import tensorflow
from core.leras import nn import torch
from torch import nn
from torch.nn import functional as F
class S3FDExtractor(object): class S3FDExtractor(object):
def __init__(self, place_model_on_cpu=False): def __init__(self, place_model_on_cpu=False):
nn.initialize(data_format="NHWC") # nn.initialize(data_format="NHWC")
tf = nn.tf
model_path = Path(__file__).parent / "S3FD.npy" model_path = Path(__file__).parent / "S3FD.npy"
if not model_path.exists(): if not model_path.exists():
@ -21,14 +22,14 @@ class S3FDExtractor(object):
super().__init__(**kwargs) super().__init__(**kwargs)
def build_weights(self): def build_weights(self):
self.weight = tf.get_variable ("weight", (1, 1, 1, self.n_channels), dtype=nn.floatx, initializer=tf.initializers.ones ) self.weight = torch.ones([1, 1, 1, self.n_channels], dtype=torch.float64)
def get_weights(self): def get_weights(self):
return [self.weight] return [self.weight]
def __call__(self, inputs): def __call__(self, inputs):
x = inputs x = inputs
x = x / (tf.sqrt( tf.reduce_sum( tf.pow(x, 2), axis=-1, keepdims=True ) ) + 1e-10) * self.weight x = x / (torch.sqrt(torch.sum(torch.pow(x, 2), axis=-1, keepdims=True ) ) + 1e-10) * self.weight
return x return x
class S3FD(nn.ModelBase): class S3FD(nn.ModelBase):
@ -36,96 +37,96 @@ class S3FDExtractor(object):
super().__init__(name='S3FD') super().__init__(name='S3FD')
def on_build(self): def on_build(self):
self.minus = tf.constant([104,117,123], dtype=nn.floatx ) self.minus = torch.Tensor([104,117,123])
self.conv1_1 = nn.Conv2D(3, 64, kernel_size=3, strides=1, padding='SAME') self.conv1_1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding='same')
self.conv1_2 = nn.Conv2D(64, 64, kernel_size=3, strides=1, padding='SAME') self.conv1_2 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding='same')
self.conv2_1 = nn.Conv2D(64, 128, kernel_size=3, strides=1, padding='SAME') self.conv2_1 = nn.Conv2d(64, 128, kernel_size=3, stride=1, padding='same')
self.conv2_2 = nn.Conv2D(128, 128, kernel_size=3, strides=1, padding='SAME') self.conv2_2 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding='same')
self.conv3_1 = nn.Conv2D(128, 256, kernel_size=3, strides=1, padding='SAME') self.conv3_1 = nn.Conv2d(128, 256, kernel_size=3, stride=1, padding='same')
self.conv3_2 = nn.Conv2D(256, 256, kernel_size=3, strides=1, padding='SAME') self.conv3_2 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding='same')
self.conv3_3 = nn.Conv2D(256, 256, kernel_size=3, strides=1, padding='SAME') self.conv3_3 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding='same')
self.conv4_1 = nn.Conv2D(256, 512, kernel_size=3, strides=1, padding='SAME') self.conv4_1 = nn.Conv2d(256, 512, kernel_size=3, stride=1, padding='same')
self.conv4_2 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME') self.conv4_2 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding='same')
self.conv4_3 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME') self.conv4_3 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding='same')
self.conv5_1 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME') self.conv5_1 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding='same')
self.conv5_2 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME') self.conv5_2 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding='same')
self.conv5_3 = nn.Conv2D(512, 512, kernel_size=3, strides=1, padding='SAME') self.conv5_3 = nn.Conv2d(512, 512, kernel_size=3, stride=1, padding='same')
self.fc6 = nn.Conv2D(512, 1024, kernel_size=3, strides=1, padding=3) self.fc6 = nn.Conv2d(512, 1024, kernel_size=3, stride=1, padding=3)
self.fc7 = nn.Conv2D(1024, 1024, kernel_size=1, strides=1, padding='SAME') self.fc7 = nn.Conv2d(1024, 1024, kernel_size=1, stride=1, padding='same')
self.conv6_1 = nn.Conv2D(1024, 256, kernel_size=1, strides=1, padding='SAME') self.conv6_1 = nn.Conv2d(1024, 256, kernel_size=1, stride=1, padding='same')
self.conv6_2 = nn.Conv2D(256, 512, kernel_size=3, strides=2, padding='SAME') self.conv6_2 = nn.Conv2d(256, 512, kernel_size=3, stride=2, padding='same')
self.conv7_1 = nn.Conv2D(512, 128, kernel_size=1, strides=1, padding='SAME') self.conv7_1 = nn.Conv2d(512, 128, kernel_size=1, stride=1, padding='same')
self.conv7_2 = nn.Conv2D(128, 256, kernel_size=3, strides=2, padding='SAME') self.conv7_2 = nn.Conv2d(128, 256, kernel_size=3, stride=2, padding='same')
self.conv3_3_norm = L2Norm(256) self.conv3_3_norm = L2Norm(256)
self.conv4_3_norm = L2Norm(512) self.conv4_3_norm = L2Norm(512)
self.conv5_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_conf = nn.Conv2d(256, 4, kernel_size=3, stride=1, padding='same')
self.conv3_3_norm_mbox_loc = nn.Conv2D(256, 4, kernel_size=3, strides=1, padding='SAME') self.conv3_3_norm_mbox_loc = nn.Conv2d(256, 4, kernel_size=3, stride=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_conf = nn.Conv2d(512, 2, kernel_size=3, stride=1, padding='same')
self.conv4_3_norm_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME') self.conv4_3_norm_mbox_loc = nn.Conv2d(512, 4, kernel_size=3, stride=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_conf = nn.Conv2d(512, 2, kernel_size=3, stride=1, padding='same')
self.conv5_3_norm_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME') self.conv5_3_norm_mbox_loc = nn.Conv2d(512, 4, kernel_size=3, stride=1, padding='same')
self.fc7_mbox_conf = nn.Conv2D(1024, 2, kernel_size=3, strides=1, padding='SAME') self.fc7_mbox_conf = nn.Conv2d(1024, 2, kernel_size=3, stride=1, padding='same')
self.fc7_mbox_loc = nn.Conv2D(1024, 4, kernel_size=3, strides=1, padding='SAME') self.fc7_mbox_loc = nn.Conv2d(1024, 4, kernel_size=3, stride=1, padding='same')
self.conv6_2_mbox_conf = nn.Conv2D(512, 2, kernel_size=3, strides=1, padding='SAME') self.conv6_2_mbox_conf = nn.Conv2d(512, 2, kernel_size=3, stride=1, padding='same')
self.conv6_2_mbox_loc = nn.Conv2D(512, 4, kernel_size=3, strides=1, padding='SAME') self.conv6_2_mbox_loc = nn.Conv2d(512, 4, kernel_size=3, stride=1, padding='same')
self.conv7_2_mbox_conf = nn.Conv2D(256, 2, kernel_size=3, strides=1, padding='SAME') self.conv7_2_mbox_conf = nn.Conv2d(256, 2, kernel_size=3, stride=1, padding='same')
self.conv7_2_mbox_loc = nn.Conv2D(256, 4, kernel_size=3, strides=1, padding='SAME') self.conv7_2_mbox_loc = nn.Conv2d(256, 4, kernel_size=3, stride=1, padding='same')
def forward(self, inp): def forward(self, inp):
x, = inp x, = inp
x = x - self.minus x = x - self.minus
x = tf.nn.relu(self.conv1_1(x)) x = nn.ReLU(self.conv1_1(x))
x = tf.nn.relu(self.conv1_2(x)) x = nn.ReLU(self.conv1_2(x))
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID") x = F.max_pool2d(x, kernel_size=[1,2,2,1], stride=[1,2,2,1], padding="valid")
x = tf.nn.relu(self.conv2_1(x)) x = nn.ReLU(self.conv2_1(x))
x = tf.nn.relu(self.conv2_2(x)) x = nn.ReLU(self.conv2_2(x))
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID") x = F.max_pool2d(x, kernel_size=[1,2,2,1], stride=[1,2,2,1], padding="valid")
x = tf.nn.relu(self.conv3_1(x)) x = nn.ReLU(self.conv3_1(x))
x = tf.nn.relu(self.conv3_2(x)) x = nn.ReLU(self.conv3_2(x))
x = tf.nn.relu(self.conv3_3(x)) x = nn.ReLU(self.conv3_3(x))
f3_3 = x f3_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID") x = F.max_pool2d(x, kernel_size=[1,2,2,1], stride=[1,2,2,1], padding="valid")
x = tf.nn.relu(self.conv4_1(x)) x = nn.ReLU(self.conv4_1(x))
x = tf.nn.relu(self.conv4_2(x)) x = nn.ReLU(self.conv4_2(x))
x = tf.nn.relu(self.conv4_3(x)) x = nn.ReLU(self.conv4_3(x))
f4_3 = x f4_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID") x = F.max_pool2d(x, kernel_size=[1,2,2,1], stride=[1,2,2,1], padding="valid")
x = tf.nn.relu(self.conv5_1(x)) x = nn.ReLU(self.conv5_1(x))
x = tf.nn.relu(self.conv5_2(x)) x = nn.ReLU(self.conv5_2(x))
x = tf.nn.relu(self.conv5_3(x)) x = nn.ReLU(self.conv5_3(x))
f5_3 = x f5_3 = x
x = tf.nn.max_pool(x, [1,2,2,1], [1,2,2,1], "VALID") x = F.max_pool2d(x, kernel_size=[1,2,2,1], stride=[1,2,2,1], padding="valid")
x = tf.nn.relu(self.fc6(x)) x = nn.ReLU(self.fc6(x))
x = tf.nn.relu(self.fc7(x)) x = nn.ReLU(self.fc7(x))
ffc7 = x ffc7 = x
x = tf.nn.relu(self.conv6_1(x)) x = nn.ReLU(self.conv6_1(x))
x = tf.nn.relu(self.conv6_2(x)) x = nn.ReLU(self.conv6_2(x))
f6_2 = x f6_2 = x
x = tf.nn.relu(self.conv7_1(x)) x = nn.ReLU(self.conv7_1(x))
x = tf.nn.relu(self.conv7_2(x)) x = nn.ReLU(self.conv7_2(x))
f7_2 = x f7_2 = x
f3_3 = self.conv3_3_norm(f3_3) f3_3 = self.conv3_3_norm(f3_3)
@ -135,39 +136,39 @@ class S3FDExtractor(object):
cls1 = self.conv3_3_norm_mbox_conf(f3_3) cls1 = self.conv3_3_norm_mbox_conf(f3_3)
reg1 = self.conv3_3_norm_mbox_loc(f3_3) reg1 = self.conv3_3_norm_mbox_loc(f3_3)
cls2 = tf.nn.softmax(self.conv4_3_norm_mbox_conf(f4_3)) cls2 = nn.Softmax(self.conv4_3_norm_mbox_conf(f4_3))
reg2 = self.conv4_3_norm_mbox_loc(f4_3) reg2 = self.conv4_3_norm_mbox_loc(f4_3)
cls3 = tf.nn.softmax(self.conv5_3_norm_mbox_conf(f5_3)) cls3 = nn.Softmax(self.conv5_3_norm_mbox_conf(f5_3))
reg3 = self.conv5_3_norm_mbox_loc(f5_3) reg3 = self.conv5_3_norm_mbox_loc(f5_3)
cls4 = tf.nn.softmax(self.fc7_mbox_conf(ffc7)) cls4 = nn.Softmax(self.fc7_mbox_conf(ffc7))
reg4 = self.fc7_mbox_loc(ffc7) reg4 = self.fc7_mbox_loc(ffc7)
cls5 = tf.nn.softmax(self.conv6_2_mbox_conf(f6_2)) cls5 = nn.Softmax(self.conv6_2_mbox_conf(f6_2))
reg5 = self.conv6_2_mbox_loc(f6_2) reg5 = self.conv6_2_mbox_loc(f6_2)
cls6 = tf.nn.softmax(self.conv7_2_mbox_conf(f7_2)) cls6 = nn.Softmax(self.conv7_2_mbox_conf(f7_2))
reg6 = self.conv7_2_mbox_loc(f7_2) reg6 = self.conv7_2_mbox_loc(f7_2)
# max-out background label # max-out background label
bmax = tf.maximum(tf.maximum(cls1[:,:,:,0:1], cls1[:,:,:,1:2]), cls1[:,:,:,2:3]) bmax = torch.maximum(torch.maximum(cls1[:,:,:,0:1], cls1[:,:,:,1:2]), cls1[:,:,:,2:3])
cls1 = tf.concat ([bmax, cls1[:,:,:,3:4] ], axis=-1) cls1 = torch.cat([bmax, cls1[:,:,:,3:4] ], axis=-1)
cls1 = tf.nn.softmax(cls1) cls1 = nn.Softmax(cls1)
return [cls1, reg1, cls2, reg2, cls3, reg3, cls4, reg4, cls5, reg5, cls6, reg6] return [cls1, reg1, cls2, reg2, cls3, reg3, cls4, reg4, cls5, reg5, cls6, reg6]
e = None e = None
if place_model_on_cpu: if place_model_on_cpu:
e = tf.device("/CPU:0") e = torch.device("/CPU:0")
if e is not None: e.__enter__() if e is not None: e.__enter__()
self.model = S3FD() self.model = S3FD()
self.model.load_weights (model_path) # self.model.load_weights(model_path)
if e is not None: e.__exit__(None,None,None) if e is not None: e.__exit__(None,None,None)
self.model.build_for_run ([ ( tf.float32, nn.get4Dshape (None,None,3) ) ]) self.model.build_for_run ([ ( torch.float32, nn.get4Dshape (None,None,3) ) ])
def __enter__(self): def __enter__(self):
return self return self