diff --git a/GUI.py b/GUI.py
index 2ce3836..16e1f4d 100644
--- a/GUI.py
+++ b/GUI.py
@@ -5,7 +5,7 @@
 # Created Date: Wednesday December 22nd 2021
 # Author: Chen Xuanhong
 # Email: chenxuanhongzju@outlook.com
-# Last Modified:  Monday, 17th January 2022 12:45:32 am
+# Last Modified:  Thursday, 10th February 2022 12:14:47 am
 # Modified By: Chen Xuanhong
 # Copyright (c) 2021 Shanghai Jiao Tong University
 #############################################################
@@ -24,6 +24,13 @@ except:
     main(['install', 'paramiko'])
     import paramiko
 
+try:
+    import pyperclip
+except:
+    from pip._internal import main
+    main(['install', 'pyperclip'])
+    import pyperclip
+
 import threading
 import tkinter as tk
 import tkinter.ttk as ttk
@@ -390,13 +397,18 @@ class Application(tk.Frame):
         ssh_frame.pack(fill="both", padx=5,pady=5)
         ssh_frame.columnconfigure(0, weight=1)
         ssh_frame.columnconfigure(1, weight=1)
+        ssh_frame.columnconfigure(2, weight=1)
         ssh_button = tk.Button(ssh_frame, text = "Open SSH",
                             font=font_list, command = self.OpenSSH, bg='#990033', fg='#F5F5F5')
         ssh_button.grid(row=0,column=0,sticky=tk.EW)
 
+        ssh_button = tk.Button(ssh_frame, text = "Copy Passwd",
+                            font=font_list, command = self.CopyPasswd, bg='#990033', fg='#F5F5F5')
+        ssh_button.grid(row=0,column=1,sticky=tk.EW)
+
         ssh_button = tk.Button(ssh_frame, text = "Pull Log",
                             font=font_list, command = self.PullLog, bg='#990033', fg='#F5F5F5')
-        ssh_button.grid(row=0,column=1,sticky=tk.EW)
+        ssh_button.grid(row=0,column=2,sticky=tk.EW)
 
         #################################################################################################
         config_frame    = tk.Frame(self.master)
@@ -532,6 +544,16 @@ class Application(tk.Frame):
         self.test_com["value"] =all_files
         self.test_com.current(0)
     
+    def CopyPasswd(self):
+        def copy():
+            ip          = self.list_com.get()
+            cur_mac     = self.machine_dict[ip]
+            passwd      = cur_mac["passwd"]
+            pyperclip.copy(passwd)
+
+        thread_update = threading.Thread(target=copy)
+        thread_update.start()
+    
     def Test(self):
         def test_task():
             log         = self.log_com.get()
diff --git a/GUI/file_sync/filestate_machine0.json b/GUI/file_sync/filestate_machine0.json
index 80d4bd2..9656ee6 100644
--- a/GUI/file_sync/filestate_machine0.json
+++ b/GUI/file_sync/filestate_machine0.json
@@ -1,5 +1,5 @@
 {
-    "GUI.py": 1642351532.4558506,
+    "GUI.py": 1644423287.9844918,
     "test.py": 1643529962.5602193,
     "train.py": 1643397924.974299,
     "components\\Generator.py": 1642347735.351465,
@@ -60,7 +60,7 @@
     "face_crop.py": 1643789609.1834445,
     "face_crop_video.py": 1643815024.5516832,
     "similarity.py": 1643269705.1073737,
-    "train_multigpu.py": 1644331842.3490777,
+    "train_multigpu.py": 1644509438.008675,
     "components\\arcface_decoder.py": 1643396144.2575414,
     "components\\Generator_nobias.py": 1643179001.810856,
     "data_tools\\data_loader_VGGFace2HQ_multigpu.py": 1644330414.9587426,
@@ -83,9 +83,9 @@
     "torch_utils\\ops\\__init__.py": 1640773190.0,
     "train_scripts\\trainer_arcface_rec.py": 1643399647.0182135,
     "train_scripts\\trainer_multigpu_base.py": 1644131205.772292,
-    "train_scripts\\trainer_multi_gpu.py": 1644331738.7729652,
+    "train_scripts\\trainer_multi_gpu.py": 1644549528.075511,
     "train_yamls\\train_arcface_rec.yaml": 1643398807.3434353,
-    "train_yamls\\train_multigpu.yaml": 1644331809.0680442,
+    "train_yamls\\train_multigpu.yaml": 1644549590.0652373,
     "wandb\\run-20220129_032741-340btp9k\\files\\conda-environment.yaml": 1643398065.409959,
     "wandb\\run-20220129_032741-340btp9k\\files\\config.yaml": 1643398069.2392955,
     "wandb\\run-20220129_032939-2nmaozxq\\files\\conda-environment.yaml": 1643398182.647548,
@@ -104,5 +104,11 @@
     "dnnlib\\__init__.py": 1640773190.0,
     "components\\Generator_ori.py": 1644229508.0031855,
     "losses\\cos.py": 1644229583.4023254,
-    "data_tools\\data_loader_VGGFace2HQ_multigpu1.py": 1644297868.397411
+    "data_tools\\data_loader_VGGFace2HQ_multigpu1.py": 1644297868.397411,
+    "speed_test.py": 1644476745.605093,
+    "components\\DeConv_Invo.py": 1644426607.1588645,
+    "components\\Generator_reduce_up.py": 1644477248.9149294,
+    "components\\Generator_upsample.py": 1644426070.2325442,
+    "components\\misc\\Involution.py": 1644509321.5267963,
+    "train_yamls\\train_Invoup.yaml": 1644550037.4785244
 }
\ No newline at end of file
diff --git a/GUI/machines.json b/GUI/machines.json
index 30b51d2..68c43a2 100644
--- a/GUI/machines.json
+++ b/GUI/machines.json
@@ -7,5 +7,14 @@
         "path": "/home/ubuntu/CXH/simswap_plus",
         "ckp_path": "train_logs",
         "logfilename": "filestate_machine0.json"
+    },
+    {
+        "ip": "2001:da8:8000:6880:f284:d61c:3c76:f9cb",
+        "user": "ps",
+        "port": 22,
+        "passwd": "glass123456",
+        "path": "/data1/cxh/simswap_plus",
+        "ckp_path": "train_logs",
+        "logfilename": "filestate_machine1.json"
     }
 ]
\ No newline at end of file
diff --git a/README.md b/README.md
index fb4ee75..f2ea463 100644
--- a/README.md
+++ b/README.md
@@ -1,21 +1,20 @@
 # Simswap++
 
 ## Dependencies
-- python > 3.6
+- python >= 3.7
 - yaml (pip install pyyaml)
 - paramiko (For ssh file transportation)
-- pytorch > 1.8
-- tkinter (For GUI)
+- pytorch >= 1.9
 - pillow
 - torchvision
 - opencv
 - matplotlib
 - timm
+- cupy (for involution) you need to create a new env in anaconda (conda install pytorch==1.10.1 cudatoolkit==10.2.89 cupy==10.1.0 -c pytorch -c conda-forge)
 
 ## logger
 
-- tensorboard (pip install tensorboard)
-- tensorboardX (pip install tensorboardX)
+- wandb (pip install wandb)
 
 ***OR***
 
diff --git a/components/DeConv_Invo.py b/components/DeConv_Invo.py
new file mode 100644
index 0000000..03ae788
--- /dev/null
+++ b/components/DeConv_Invo.py
@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+#############################################################
+# File: DeConv copy.py
+# Created Date: Tuesday July 20th 2021
+# Author: Chen Xuanhong
+# Email: chenxuanhongzju@outlook.com
+# Last Modified:  Thursday, 10th February 2022 1:10:04 am
+# Modified By: Chen Xuanhong
+# Copyright (c) 2021 Shanghai Jiao Tong University
+#############################################################
+
+
+from components.misc.Involution import involution
+from torch import nn
+
+class DeConv(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size = 3, upsampl_scale = 2, padding="zero"):
+        super().__init__()
+        self.upsampling = nn.UpsamplingBilinear2d(scale_factor=upsampl_scale)
+        padding_size = int((kernel_size -1)/2)
+        self.conv1x1 = nn.Conv2d(in_channels = in_channels, out_channels = out_channels, kernel_size= 1)
+        # self.same_padding   = nn.ReflectionPad2d(padding_size)
+        if padding.lower() == "reflect":
+            
+            self.conv = involution(out_channels,kernel_size,1)
+            # self.conv = nn.Sequential(
+            #     nn.ReflectionPad2d(padding_size),
+            #     nn.Conv2d(in_channels = in_channels, out_channels = out_channels, kernel_size= kernel_size, bias= False))
+            # for layer in self.conv:
+            #     if isinstance(layer,nn.Conv2d):
+            #         nn.init.xavier_uniform_(layer.weight)
+        elif padding.lower() == "zero":
+            self.conv = involution(out_channels,kernel_size,1)
+            # nn.init.xavier_uniform_(self.conv.weight)
+    #     self.__weights_init__()
+
+    # def __weights_init__(self):
+    #     nn.init.xavier_uniform_(self.conv.weight)
+
+    def forward(self, input):
+        h   = self.conv1x1(input)
+        h   = self.upsampling(h)
+        h   = self.conv(h)
+        return h
\ No newline at end of file
diff --git a/components/Generator_reduce_up.py b/components/Generator_reduce_up.py
new file mode 100644
index 0000000..ef095f8
--- /dev/null
+++ b/components/Generator_reduce_up.py
@@ -0,0 +1,193 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+#############################################################
+# File: Generator.py
+# Created Date: Sunday January 16th 2022
+# Author: Chen Xuanhong
+# Email: chenxuanhongzju@outlook.com
+# Last Modified:  Thursday, 10th February 2022 3:14:08 pm
+# Modified By: Chen Xuanhong
+# Copyright (c) 2022 Shanghai Jiao Tong University
+#############################################################
+
+import torch
+from torch import nn
+from components.DeConv_Invo import DeConv
+
+class Demodule(nn.Module):
+    def __init__(self, epsilon=1e-8):
+        """
+            @notice: avoid in-place ops.
+            https://discuss.pytorch.org/t/encounter-the-runtimeerror-one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation/836/3
+        """
+        super(Demodule, self).__init__()
+        self.epsilon = epsilon
+
+    def forward(self, x):
+        tmp = torch.mul(x, x) # or x ** 2
+        tmp = torch.rsqrt(torch.mean(tmp, (2, 3), True) + self.epsilon)
+        return x * tmp
+
+class ApplyStyle(nn.Module):
+    """
+        @ref: https://github.com/lernapparat/lernapparat/blob/master/style_gan/pytorch_style_gan.ipynb
+    """
+    def __init__(self, latent_size, channels):
+        super(ApplyStyle, self).__init__()
+        self.linear = nn.Linear(latent_size, channels * 2)
+
+    def forward(self, x, latent):
+        style = self.linear(latent)  # style => [batch_size, n_channels*2]
+        shape = [-1, 2, x.size(1), 1, 1]
+        style = style.view(shape)    # [batch_size, 2, n_channels, ...]
+        #x = x * (style[:, 0] + 1.) + style[:, 1]
+        x = x * (style[:, 0] * 1 + 1.) + style[:, 1] * 1
+        return x
+
+class Modulation(nn.Module):
+    def __init__(self, latent_size, channels):
+        super(Modulation, self).__init__()
+        self.linear = nn.Linear(latent_size, channels)
+
+    def forward(self, x, latent):
+        style = self.linear(latent)  # style => [batch_size, n_channels*2]
+        shape = [-1, x.size(1), 1, 1]
+        style = style.view(shape)    # [batch_size, 2, n_channels, ...]
+        #x = x * (style[:, 0] + 1.) + style[:, 1]
+        x = x * style
+        return x
+
+class ResnetBlock_Modulation(nn.Module):
+    def __init__(self, dim, latent_size, padding_type, activation=nn.ReLU(True)):
+        super(ResnetBlock_Modulation, self).__init__()
+
+        p = 0
+        conv1 = []
+        if padding_type == 'reflect':
+            conv1 += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv1 += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+        conv1 += [nn.Conv2d(dim, dim, kernel_size=3, padding = p), Demodule()]
+        self.conv1 = nn.Sequential(*conv1)
+        self.style1 = Modulation(latent_size, dim)
+        self.act1 = activation
+
+        p = 0
+        conv2 = []
+        if padding_type == 'reflect':
+            conv2 += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv2 += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+        conv2 += [nn.Conv2d(dim, dim, kernel_size=3, padding=p), Demodule()]
+        self.conv2 = nn.Sequential(*conv2)
+        self.style2 = Modulation(latent_size, dim)
+
+
+    def forward(self, x, dlatents_in_slice):
+        y = self.conv1(x)
+        y = self.style1(y, dlatents_in_slice)
+        y = self.act1(y)
+        y = self.conv2(y)
+        y = self.style2(y, dlatents_in_slice)
+        out = x + y
+        return out
+
+class Generator(nn.Module):
+    def __init__(
+                self,
+                **kwargs
+                ):
+        super().__init__()
+
+        chn         = kwargs["g_conv_dim"]
+        k_size      = kwargs["g_kernel_size"]
+        res_num     = kwargs["res_num"]
+        
+        padding_size= int((k_size -1)/2)
+        padding_type= 'reflect'
+        
+        activation = nn.ReLU(True)
+
+        self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(3, 64, kernel_size=7, padding=0, bias=False),
+                                nn.BatchNorm2d(64), activation)
+        ### downsample
+        self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
+                                nn.BatchNorm2d(128), activation)
+                                
+        self.down2 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
+                                nn.BatchNorm2d(256), activation)
+
+        self.down3 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
+                                nn.BatchNorm2d(512), activation)
+
+        self.down4 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1),
+                                nn.BatchNorm2d(512), activation)
+
+        ### resnet blocks
+        BN = []
+        for i in range(res_num):
+            BN += [
+                ResnetBlock_Modulation(512, latent_size=chn, padding_type=padding_type, activation=activation)]
+        self.BottleNeck = nn.Sequential(*BN)
+
+        self.up4 = nn.Sequential(
+            DeConv(512,512,3),
+            nn.BatchNorm2d(512), activation
+        )
+        
+        self.up3 = nn.Sequential(
+            DeConv(512,256,3),
+            nn.BatchNorm2d(256), activation
+        )
+        
+        self.up2 = nn.Sequential(
+            DeConv(256,128,3),
+            nn.BatchNorm2d(128), activation
+        )
+
+        self.up1 = nn.Sequential(
+            DeConv(128,64,3),
+            nn.BatchNorm2d(64), activation
+        )
+        
+        self.last_layer = nn.Sequential(nn.ReflectionPad2d(3),
+                    nn.Conv2d(64, 3, kernel_size=7, padding=0))
+
+
+    #     self.__weights_init__()
+
+    # def __weights_init__(self):
+    #     for layer in self.encoder:
+    #         if isinstance(layer,nn.Conv2d):
+    #             nn.init.xavier_uniform_(layer.weight)
+
+    #     for layer in self.encoder2:
+    #         if isinstance(layer,nn.Conv2d):
+    #             nn.init.xavier_uniform_(layer.weight)
+
+    def forward(self, input, id):
+        x = input  # 3*224*224
+        skip1 = self.first_layer(x)
+        skip2 = self.down1(skip1)
+        skip3 = self.down2(skip2)
+        skip4 = self.down3(skip3)
+        res   = self.down4(skip4)
+
+        for i in range(len(self.BottleNeck)):
+            x = self.BottleNeck[i](res, id)
+
+        x = self.up4(x)
+        x = self.up3(x)
+        x = self.up2(x)
+        x = self.up1(x)
+        x = self.last_layer(x)
+
+        return x
diff --git a/components/Generator_upsample.py b/components/Generator_upsample.py
new file mode 100644
index 0000000..b2b5986
--- /dev/null
+++ b/components/Generator_upsample.py
@@ -0,0 +1,181 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+#############################################################
+# File: Generator.py
+# Created Date: Sunday January 16th 2022
+# Author: Chen Xuanhong
+# Email: chenxuanhongzju@outlook.com
+# Last Modified:  Thursday, 10th February 2022 1:01:09 am
+# Modified By: Chen Xuanhong
+# Copyright (c) 2022 Shanghai Jiao Tong University
+#############################################################
+
+import torch
+from torch import nn
+from components.DeConv_Invo import DeConv
+
+class InstanceNorm(nn.Module):
+    def __init__(self, epsilon=1e-8):
+        """
+            @notice: avoid in-place ops.
+            https://discuss.pytorch.org/t/encounter-the-runtimeerror-one-of-the-variables-needed-for-gradient-computation-has-been-modified-by-an-inplace-operation/836/3
+        """
+        super(InstanceNorm, self).__init__()
+        self.epsilon = epsilon
+
+    def forward(self, x):
+        x   = x - torch.mean(x, (2, 3), True)
+        tmp = torch.mul(x, x) # or x ** 2
+        tmp = torch.rsqrt(torch.mean(tmp, (2, 3), True) + self.epsilon)
+        return x * tmp
+
+class ApplyStyle(nn.Module):
+    """
+        @ref: https://github.com/lernapparat/lernapparat/blob/master/style_gan/pytorch_style_gan.ipynb
+    """
+    def __init__(self, latent_size, channels):
+        super(ApplyStyle, self).__init__()
+        self.linear = nn.Linear(latent_size, channels * 2)
+
+    def forward(self, x, latent):
+        style = self.linear(latent)  # style => [batch_size, n_channels*2]
+        shape = [-1, 2, x.size(1), 1, 1]
+        style = style.view(shape)    # [batch_size, 2, n_channels, ...]
+        #x = x * (style[:, 0] + 1.) + style[:, 1]
+        x = x * (style[:, 0] * 1 + 1.) + style[:, 1] * 1
+        return x
+
+class ResnetBlock_Adain(nn.Module):
+    def __init__(self, dim, latent_size, padding_type, activation=nn.ReLU(True)):
+        super(ResnetBlock_Adain, self).__init__()
+
+        p = 0
+        conv1 = []
+        if padding_type == 'reflect':
+            conv1 += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv1 += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+        conv1 += [nn.Conv2d(dim, dim, kernel_size=3, padding = p), InstanceNorm()]
+        self.conv1 = nn.Sequential(*conv1)
+        self.style1 = ApplyStyle(latent_size, dim)
+        self.act1 = activation
+
+        p = 0
+        conv2 = []
+        if padding_type == 'reflect':
+            conv2 += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv2 += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+        conv2 += [nn.Conv2d(dim, dim, kernel_size=3, padding=p), InstanceNorm()]
+        self.conv2 = nn.Sequential(*conv2)
+        self.style2 = ApplyStyle(latent_size, dim)
+
+
+    def forward(self, x, dlatents_in_slice):
+        y = self.conv1(x)
+        y = self.style1(y, dlatents_in_slice)
+        y = self.act1(y)
+        y = self.conv2(y)
+        y = self.style2(y, dlatents_in_slice)
+        out = x + y
+        return out
+
+
+class Generator(nn.Module):
+    def __init__(
+                self,
+                **kwargs
+                ):
+        super().__init__()
+
+        chn         = kwargs["g_conv_dim"]
+        k_size      = kwargs["g_kernel_size"]
+        res_num     = kwargs["res_num"]
+        
+        padding_size= int((k_size -1)/2)
+        padding_type= 'reflect'
+        
+        activation = nn.ReLU(True)
+
+        self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(3, 64, kernel_size=7, padding=0, bias=False),
+                                nn.BatchNorm2d(64), activation)
+        ### downsample
+        self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1, bias=False),
+                                nn.BatchNorm2d(128), activation)
+                                
+        self.down2 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1, bias=False),
+                                nn.BatchNorm2d(256), activation)
+
+        self.down3 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1, bias=False),
+                                nn.BatchNorm2d(512), activation)
+
+        self.down4 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1, bias=False),
+                                nn.BatchNorm2d(512), activation)
+
+        ### resnet blocks
+        BN = []
+        for i in range(res_num):
+            BN += [
+                ResnetBlock_Adain(512, latent_size=chn, padding_type=padding_type, activation=activation)]
+        self.BottleNeck = nn.Sequential(*BN)
+
+        self.up4 = nn.Sequential(
+            DeConv(512,512,3),
+            nn.BatchNorm2d(512), activation
+        )
+        
+        self.up3 = nn.Sequential(
+            DeConv(512,256,3),
+            nn.BatchNorm2d(256), activation
+        )
+        
+        self.up2 = nn.Sequential(
+            DeConv(256,128,3),
+            nn.BatchNorm2d(128), activation
+        )
+
+        self.up1 = nn.Sequential(
+            DeConv(128,64,3),
+            nn.BatchNorm2d(64), activation
+        )
+        
+        self.last_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(64, 3, kernel_size=7, padding=0))
+
+
+    #     self.__weights_init__()
+
+    # def __weights_init__(self):
+    #     for layer in self.encoder:
+    #         if isinstance(layer,nn.Conv2d):
+    #             nn.init.xavier_uniform_(layer.weight)
+
+    #     for layer in self.encoder2:
+    #         if isinstance(layer,nn.Conv2d):
+    #             nn.init.xavier_uniform_(layer.weight)
+
+    def forward(self, input, id):
+        x = input  # 3*224*224
+        skip1 = self.first_layer(x)
+        skip2 = self.down1(skip1)
+        skip3 = self.down2(skip2)
+        skip4 = self.down3(skip3)
+        res   = self.down4(skip4)
+
+        for i in range(len(self.BottleNeck)):
+            x = self.BottleNeck[i](res, id)
+
+        x = self.up4(x)
+        x = self.up3(x)
+        x = self.up2(x)
+        x = self.up1(x)
+        x = self.last_layer(x)
+
+        return x
diff --git a/components/misc/Involution.py b/components/misc/Involution.py
new file mode 100644
index 0000000..79a62cf
--- /dev/null
+++ b/components/misc/Involution.py
@@ -0,0 +1,302 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+#############################################################
+# File: Involution.py
+# Created Date: Tuesday July 20th 2021
+# Author: Chen Xuanhong
+# Email: chenxuanhongzju@outlook.com
+# Last Modified:  Friday, 11th February 2022 12:08:41 am
+# Modified By: Chen Xuanhong
+# Copyright (c) 2021 Shanghai Jiao Tong University
+#############################################################
+
+
+
+import torch
+import torch.nn as nn
+from torch.nn.modules.utils import _pair
+from torch.autograd import Function
+
+import cupy
+from string import Template
+from collections import namedtuple
+
+
+
+Stream = namedtuple('Stream', ['ptr'])
+
+
+def Dtype(t):
+    if isinstance(t, torch.cuda.FloatTensor):
+        return 'float'
+    elif isinstance(t, torch.cuda.DoubleTensor):
+        return 'double'
+
+
+@cupy._util.memoize(for_each_device=True)
+def load_kernel(kernel_name, code, **kwargs):
+    code = Template(code).substitute(**kwargs)
+    kernel_code = cupy.cuda.compile_with_cache(code)
+    return kernel_code.get_function(kernel_name)
+
+
+CUDA_NUM_THREADS = 1024
+
+kernel_loop = '''
+#define CUDA_KERNEL_LOOP(i, n)                        \
+  for (int i = blockIdx.x * blockDim.x + threadIdx.x; \
+      i < (n);                                       \
+      i += blockDim.x * gridDim.x)
+'''
+
+
+def GET_BLOCKS(N):
+    return (N + CUDA_NUM_THREADS - 1) // CUDA_NUM_THREADS
+
+
+_involution_kernel = kernel_loop + '''
+extern "C"
+__global__ void involution_forward_kernel(
+const ${Dtype}* bottom_data, const ${Dtype}* weight_data, ${Dtype}* top_data) {
+  CUDA_KERNEL_LOOP(index, ${nthreads}) {
+    const int n = index / ${channels} / ${top_height} / ${top_width};
+    const int c = (index / ${top_height} / ${top_width}) % ${channels};
+    const int h = (index / ${top_width}) % ${top_height};
+    const int w = index % ${top_width};
+    const int g = c / (${channels} / ${groups});
+    ${Dtype} value = 0;
+    #pragma unroll
+    for (int kh = 0; kh < ${kernel_h}; ++kh) {
+      #pragma unroll
+      for (int kw = 0; kw < ${kernel_w}; ++kw) {
+        const int h_in = -${pad_h} + h * ${stride_h} + kh * ${dilation_h};
+        const int w_in = -${pad_w} + w * ${stride_w} + kw * ${dilation_w};
+        if ((h_in >= 0) && (h_in < ${bottom_height})
+          && (w_in >= 0) && (w_in < ${bottom_width})) {
+          const int offset = ((n * ${channels} + c) * ${bottom_height} + h_in)
+            * ${bottom_width} + w_in;
+          const int offset_weight = ((((n * ${groups} + g) * ${kernel_h} + kh) * ${kernel_w} + kw) * ${top_height} + h)
+            * ${top_width} + w;
+          value += weight_data[offset_weight] * bottom_data[offset];
+        }
+      }
+    }
+    top_data[index] = value;
+  }
+}
+'''
+
+
+_involution_kernel_backward_grad_input = kernel_loop + '''
+extern "C"
+__global__ void involution_backward_grad_input_kernel(
+    const ${Dtype}* const top_diff, const ${Dtype}* const weight_data, ${Dtype}* const bottom_diff) {
+  CUDA_KERNEL_LOOP(index, ${nthreads}) {
+    const int n = index / ${channels} / ${bottom_height} / ${bottom_width};
+    const int c = (index / ${bottom_height} / ${bottom_width}) % ${channels};
+    const int h = (index / ${bottom_width}) % ${bottom_height};
+    const int w = index % ${bottom_width};
+    const int g = c / (${channels} / ${groups});
+    ${Dtype} value = 0;
+    #pragma unroll
+    for (int kh = 0; kh < ${kernel_h}; ++kh) {
+      #pragma unroll
+      for (int kw = 0; kw < ${kernel_w}; ++kw) {
+        const int h_out_s = h + ${pad_h} - kh * ${dilation_h};
+        const int w_out_s = w + ${pad_w} - kw * ${dilation_w};
+        if (((h_out_s % ${stride_h}) == 0) && ((w_out_s % ${stride_w}) == 0)) {
+          const int h_out = h_out_s / ${stride_h};
+          const int w_out = w_out_s / ${stride_w};
+          if ((h_out >= 0) && (h_out < ${top_height})
+                && (w_out >= 0) && (w_out < ${top_width})) {
+            const int offset = ((n * ${channels} + c) * ${top_height} + h_out)
+                  * ${top_width} + w_out;
+            const int offset_weight = ((((n * ${groups} + g) * ${kernel_h} + kh) * ${kernel_w} + kw) * ${top_height} + h_out)
+                  * ${top_width} + w_out;
+            value += weight_data[offset_weight] * top_diff[offset];
+          }
+        }
+      }
+    }
+    bottom_diff[index] = value;
+  }
+}
+'''
+
+
+_involution_kernel_backward_grad_weight = kernel_loop + '''
+extern "C"
+__global__ void involution_backward_grad_weight_kernel(
+    const ${Dtype}* const top_diff, const ${Dtype}* const bottom_data, ${Dtype}* const buffer_data) {
+  CUDA_KERNEL_LOOP(index, ${nthreads}) {
+    const int h = (index / ${top_width}) % ${top_height};
+    const int w = index % ${top_width};
+    const int kh = (index / ${kernel_w} / ${top_height} / ${top_width})
+          % ${kernel_h};
+    const int kw = (index / ${top_height} / ${top_width}) % ${kernel_w};
+    const int h_in = -${pad_h} + h * ${stride_h} + kh * ${dilation_h};
+    const int w_in = -${pad_w} + w * ${stride_w} + kw * ${dilation_w};
+    if ((h_in >= 0) && (h_in < ${bottom_height})
+          && (w_in >= 0) && (w_in < ${bottom_width})) {
+      const int g = (index / ${kernel_h} / ${kernel_w} / ${top_height} / ${top_width}) % ${groups};
+      const int n = (index / ${groups} / ${kernel_h} / ${kernel_w} / ${top_height} / ${top_width}) % ${num};
+      ${Dtype} value = 0;
+      #pragma unroll
+      for (int c = g * (${channels} / ${groups}); c < (g + 1) * (${channels} / ${groups}); ++c) {
+        const int top_offset = ((n * ${channels} + c) * ${top_height} + h)
+              * ${top_width} + w;
+        const int bottom_offset = ((n * ${channels} + c) * ${bottom_height} + h_in)
+              * ${bottom_width} + w_in;
+        value += top_diff[top_offset] * bottom_data[bottom_offset];
+      }
+      buffer_data[index] = value;
+    } else {
+      buffer_data[index] = 0;
+    }
+  }
+}
+'''
+
+
+class _involution(Function):
+    @staticmethod
+    def forward(ctx, input, weight, stride, padding, dilation):
+        assert input.dim() == 4 and input.is_cuda
+        assert weight.dim() == 6 and weight.is_cuda
+        batch_size, channels, height, width = input.size()
+        kernel_h, kernel_w = weight.size()[2:4]
+        output_h = int((height + 2 * padding[0] - (dilation[0] * (kernel_h - 1) + 1)) / stride[0] + 1)
+        output_w = int((width + 2 * padding[1] - (dilation[1] * (kernel_w - 1) + 1)) / stride[1] + 1)
+
+        output = input.new(batch_size, channels, output_h, output_w)
+        n = output.numel()
+
+        with torch.cuda.device_of(input):
+            f = load_kernel('involution_forward_kernel', _involution_kernel, Dtype=Dtype(input), nthreads=n,
+                            num=batch_size, channels=channels, groups=weight.size()[1],
+                            bottom_height=height, bottom_width=width,
+                            top_height=output_h, top_width=output_w,
+                            kernel_h=kernel_h, kernel_w=kernel_w,
+                            stride_h=stride[0], stride_w=stride[1],
+                            dilation_h=dilation[0], dilation_w=dilation[1],
+                            pad_h=padding[0], pad_w=padding[1])
+            f(block=(CUDA_NUM_THREADS,1,1),
+              grid=(GET_BLOCKS(n),1,1),
+              args=[input.data_ptr(), weight.data_ptr(), output.data_ptr()],
+              stream=Stream(ptr=torch.cuda.current_stream().cuda_stream))
+
+        ctx.save_for_backward(input, weight)
+        ctx.stride, ctx.padding, ctx.dilation = stride, padding, dilation
+        return output
+    
+    @staticmethod
+    def backward(ctx, grad_output):
+        assert grad_output.is_cuda and grad_output.is_contiguous()
+        input, weight = ctx.saved_tensors
+        stride, padding, dilation = ctx.stride, ctx.padding, ctx.dilation
+
+        batch_size, channels, height, width = input.size()
+        kernel_h, kernel_w = weight.size()[2:4]
+        output_h, output_w = grad_output.size()[2:]
+
+        grad_input, grad_weight = None, None
+
+        opt = dict(Dtype=Dtype(grad_output),
+                   num=batch_size, channels=channels, groups=weight.size()[1],
+                   bottom_height=height, bottom_width=width,
+                   top_height=output_h, top_width=output_w,
+                   kernel_h=kernel_h, kernel_w=kernel_w,
+                   stride_h=stride[0], stride_w=stride[1],
+                   dilation_h=dilation[0], dilation_w=dilation[1],
+                   pad_h=padding[0], pad_w=padding[1])
+
+        with torch.cuda.device_of(input):
+            if ctx.needs_input_grad[0]:
+                grad_input = input.new(input.size())
+
+                n = grad_input.numel()
+                opt['nthreads'] = n
+
+                f = load_kernel('involution_backward_grad_input_kernel',
+                                _involution_kernel_backward_grad_input, **opt)
+                f(block=(CUDA_NUM_THREADS,1,1),
+                  grid=(GET_BLOCKS(n),1,1),
+                  args=[grad_output.data_ptr(), weight.data_ptr(), grad_input.data_ptr()],
+                  stream=Stream(ptr=torch.cuda.current_stream().cuda_stream))
+
+            if ctx.needs_input_grad[1]:
+                grad_weight = weight.new(weight.size())
+
+                n = grad_weight.numel()
+                opt['nthreads'] = n
+
+                f = load_kernel('involution_backward_grad_weight_kernel',
+                                _involution_kernel_backward_grad_weight, **opt)
+                f(block=(CUDA_NUM_THREADS,1,1),
+                  grid=(GET_BLOCKS(n),1,1),
+                  args=[grad_output.data_ptr(), input.data_ptr(), grad_weight.data_ptr()],
+                  stream=Stream(ptr=torch.cuda.current_stream().cuda_stream))
+
+        return grad_input, grad_weight, None, None, None
+ 
+
+def _involution_cuda(input, weight, bias=None, stride=1, padding=0, dilation=1):
+    """ involution kernel
+    """
+    assert input.size(0) == weight.size(0)
+    assert input.size(-2)//stride == weight.size(-2)
+    assert input.size(-1)//stride == weight.size(-1)
+    if input.is_cuda:
+        out = _involution.apply(input, weight, _pair(stride), _pair(padding), _pair(dilation))
+        if bias is not None:
+            out += bias.view(1,-1,1,1)
+    else:
+        raise NotImplementedError
+    return out
+
+
+class involution(nn.Module):
+
+    def __init__(self,
+                 channels,
+                 kernel_size,
+                 stride):
+        super(involution, self).__init__()
+        self.kernel_size = kernel_size
+        self.stride = stride
+        self.channels = channels
+        reduction_ratio = 4
+        self.group_channels = 8
+        self.groups = self.channels // self.group_channels
+        self.seblock = nn.Sequential(
+            nn.Conv2d(in_channels = channels, out_channels = channels // reduction_ratio, kernel_size= 1),
+            # nn.BatchNorm2d(channels // reduction_ratio),
+            nn.ReLU(),
+            nn.Conv2d(in_channels = channels // reduction_ratio, out_channels = kernel_size**2 * self.groups, kernel_size= 1)
+        )
+
+        # self.conv1 = ConvModule(
+        #     in_channels=channels,
+        #     out_channels=channels // reduction_ratio,
+        #     kernel_size=1,
+        #     conv_cfg=None,
+        #     norm_cfg=dict(type='BN'),
+        #     act_cfg=dict(type='ReLU'))
+        # self.conv2 = ConvModule(
+        #     in_channels=channels // reduction_ratio,
+        #     out_channels=kernel_size**2 * self.groups,
+        #     kernel_size=1,
+        #     stride=1,
+        #     conv_cfg=None,
+        #     norm_cfg=None,
+        #     act_cfg=None)
+        if stride > 1:
+            self.avgpool = nn.AvgPool2d(stride, stride)
+
+    def forward(self, x):
+        # weight = self.conv2(self.conv1(x if self.stride == 1 else self.avgpool(x)))
+        weight = self.seblock(x)
+        b, c, h, w = weight.shape
+        weight = weight.view(b, self.groups, self.kernel_size, self.kernel_size, h, w)
+        out = _involution_cuda(x, weight, stride=self.stride, padding=(self.kernel_size-1)//2)
+        return out
diff --git a/env/env.json b/env/env.json
index 107f12a..942909d 100644
--- a/env/env.json
+++ b/env/env.json
@@ -12,6 +12,5 @@
         "train_scripts_path":"./train_scripts",
         "test_scripts_path":"./test_scripts",
         "config_json_name":"model_config.json"
-        
     }
 }
\ No newline at end of file
diff --git a/speed_test.py b/speed_test.py
new file mode 100644
index 0000000..2465f37
--- /dev/null
+++ b/speed_test.py
@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+#############################################################
+# File: speed_test.py
+# Created Date: Thursday February 10th 2022
+# Author: Chen Xuanhong
+# Email: chenxuanhongzju@outlook.com
+# Last Modified:  Thursday, 10th February 2022 3:05:44 pm
+# Modified By: Chen Xuanhong
+# Copyright (c) 2022 Shanghai Jiao Tong University
+#############################################################
+import os
+import time
+
+import torch
+
+
+
+if __name__ == '__main__':
+
+    script      = "Generator_reduce_up"
+    class_name  = "Generator"
+    arcface_ckpt= "arcface_ckpt/arcface_checkpoint.tar"
+    model_config={
+        "g_conv_dim": 512,
+        "g_kernel_size": 3,
+        "res_num": 9
+    }
+
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(0)
+    print("GPU used : ", os.environ['CUDA_VISIBLE_DEVICES'])
+
+    gscript_name     = "components." + script
+    
+    
+    package  = __import__(gscript_name, fromlist=True)
+    gen_class= getattr(package, class_name)
+    gen      = gen_class(**model_config)
+    model    = gen.cuda().eval().requires_grad_(False)
+    arcface1 = torch.load(arcface_ckpt, map_location=torch.device("cpu"))
+    arcface  = arcface1['model'].module
+    arcface  = arcface.cuda()
+    arcface.eval().requires_grad_(False)
+
+
+    id_img      = torch.rand((4,3,112,112)).cuda()
+    id_latent   = torch.rand((4,512)).cuda()
+    # cv2.imwrite(os.path.join("./swap_results", "id_%s.png"%(id_basename)),id_img_align_crop[0]
+
+    attr        = torch.rand((4,3,512,512)).cuda()
+    
+    import datetime
+    start_time  = time.time()
+    for i in range(100):
+        with torch.no_grad():
+
+            id_latent   = arcface(id_img)
+
+            results     = model(attr, id_latent)
+            elapsed = time.time() - start_time
+    elapsed = str(datetime.timedelta(seconds=elapsed))
+    information="Elapsed [{}]".format(elapsed)
+    print(information)
\ No newline at end of file
diff --git a/train_multigpu.py b/train_multigpu.py
index d5ba081..48354e2 100644
--- a/train_multigpu.py
+++ b/train_multigpu.py
@@ -5,7 +5,7 @@
 # Created Date: Tuesday April 28th 2020
 # Author: Chen Xuanhong
 # Email: chenxuanhongzju@outlook.com
-# Last Modified:  Tuesday, 8th February 2022 10:50:37 pm
+# Last Modified:  Friday, 11th February 2022 12:10:37 am
 # Modified By: Chen Xuanhong
 # Copyright (c) 2020 Shanghai Jiao Tong University
 #############################################################
@@ -31,9 +31,9 @@ def getParameters():
     
     parser = argparse.ArgumentParser()
     # general settings
-    parser.add_argument('-v', '--version', type=str, default='multigpu3',
+    parser.add_argument('-v', '--version', type=str, default='invoup1',
                                             help="version name for train, test, finetune")
-    parser.add_argument('-t', '--tag', type=str, default='multigpu',
+    parser.add_argument('-t', '--tag', type=str, default='invo_upsample',
                                             help="tag for current experiment")
 
     parser.add_argument('-p', '--phase', type=str, default="train",
@@ -46,9 +46,9 @@ def getParameters():
 
     # training
     parser.add_argument('--experiment_description', type=str,
-                                default="测试多GPU训练")
+                                default="使用involution作为上采样")
 
-    parser.add_argument('--train_yaml', type=str, default="train_multigpu.yaml")
+    parser.add_argument('--train_yaml', type=str, default="train_Invoup.yaml")
 
     # system logger
     parser.add_argument('--logger', type=str,
diff --git a/train_scripts/trainer_multi_gpu.py b/train_scripts/trainer_multi_gpu.py
index de56e85..1080b3b 100644
--- a/train_scripts/trainer_multi_gpu.py
+++ b/train_scripts/trainer_multi_gpu.py
@@ -5,7 +5,7 @@
 # Created Date: Sunday January 9th 2022
 # Author: Chen Xuanhong
 # Email: chenxuanhongzju@outlook.com
-# Last Modified:  Tuesday, 8th February 2022 10:48:58 pm
+# Last Modified:  Friday, 11th February 2022 11:18:47 am
 # Modified By: Chen Xuanhong
 # Copyright (c) 2022 Shanghai Jiao Tong University
 #############################################################
@@ -94,6 +94,7 @@ def init_framework(config, reporter, device, rank):
     # print and recorde model structure
     reporter.writeInfo("Discriminator structure:")
     reporter.writeModel(dis.__str__())
+    
     arcface1        = torch.load(config["arcface_ckpt"], map_location=torch.device("cpu"))
     arcface         = arcface1['model'].module
     
@@ -428,6 +429,9 @@ def train_loop(
         if rank == 0 and (step + 1) % log_freq == 0:
             elapsed = time.time() - start_time
             elapsed = str(datetime.timedelta(seconds=elapsed))
+            # print("ready to report losses")
+            # ID_Total= loss_G_ID
+            # torch.distributed.all_reduce(ID_Total)
             
             epochinformation="[{}], Elapsed [{}], Step [{}/{}], \
                     G_ID: {:.4f}, G_loss: {:.4f}, Rec_loss: {:.4f}, Fm_loss: {:.4f}, \
diff --git a/train_yamls/train_Invoup.yaml b/train_yamls/train_Invoup.yaml
new file mode 100644
index 0000000..2005f02
--- /dev/null
+++ b/train_yamls/train_Invoup.yaml
@@ -0,0 +1,63 @@
+# Related scripts
+train_script_name: multi_gpu
+
+# models' scripts
+model_configs:
+  g_model:
+    script: Generator_upsample
+    class_name: Generator
+    module_params:
+      g_conv_dim: 512
+      g_kernel_size: 3
+      res_num: 9
+
+  d_model:
+    script: projected_discriminator
+    class_name: ProjectedDiscriminator
+    module_params:
+      diffaug: False
+      interp224: False
+      backbone_kwargs: {}
+
+arcface_ckpt: arcface_ckpt/arcface_checkpoint.tar
+
+# Training information
+batch_size: 28
+
+# Dataset
+dataloader: VGGFace2HQ_multigpu
+dataset_name: vggface2_hq
+dataset_params:
+  random_seed: 1234
+  dataloader_workers: 4
+
+eval_dataloader: DIV2K_hdf5
+eval_dataset_name: DF2K_H5_Eval
+eval_batch_size: 2
+
+# Dataset
+
+# Optimizer
+optim_type: Adam
+g_optim_config:
+  lr:  0.0004
+  betas: [ 0, 0.99]
+  eps: !!float 1e-8
+
+d_optim_config:
+  lr:  0.0004
+  betas: [ 0, 0.99]
+  eps: !!float 1e-8
+
+id_weight: 20.0
+reconstruct_weight: 10.0
+feature_match_weight: 10.0
+
+# Log 
+log_step: 300
+model_save_step: 10000
+sample_step: 1000
+total_step: 1000000
+checkpoint_names:
+  generator_name: Generator
+  discriminator_name: Discriminator
\ No newline at end of file
diff --git a/train_yamls/train_multigpu.yaml b/train_yamls/train_multigpu.yaml
index daf0f97..b164fd7 100644
--- a/train_yamls/train_multigpu.yaml
+++ b/train_yamls/train_multigpu.yaml
@@ -22,7 +22,7 @@ model_configs:
 arcface_ckpt: arcface_ckpt/arcface_checkpoint.tar
 
 # Training information
-batch_size: 24
+batch_size: 28
 
 # Dataset
 dataloader: VGGFace2HQ_multigpu