From a148db410ce7989351542f907569db7b921a41f7 Mon Sep 17 00:00:00 2001 From: chenxuanhong Date: Sun, 13 Feb 2022 14:20:26 +0800 Subject: [PATCH] fix bug --- GUI/file_sync/filestate_machine0.json | 13 +-- README.md | 2 +- components/Generator.py | 30 +++---- ...enerator_nobias.py => Generator_config.py} | 86 +++++++++---------- ...educe_up.py => Generator_modulation_up.py} | 39 +++++---- components/Generator_ori.py | 29 +++---- components/Generator_reduce.py | 39 ++++----- components/Generator_upsample.py | 40 +++++---- flops.py | 56 ++++++++++++ speed_test.py | 5 +- train_multigpu.py | 6 +- 11 files changed, 200 insertions(+), 145 deletions(-) rename components/{Generator_nobias.py => Generator_config.py} (62%) rename components/{Generator_reduce_up.py => Generator_modulation_up.py} (86%) create mode 100644 flops.py diff --git a/GUI/file_sync/filestate_machine0.json b/GUI/file_sync/filestate_machine0.json index 9656ee6..c944866 100644 --- a/GUI/file_sync/filestate_machine0.json +++ b/GUI/file_sync/filestate_machine0.json @@ -2,7 +2,7 @@ "GUI.py": 1644423287.9844918, "test.py": 1643529962.5602193, "train.py": 1643397924.974299, - "components\\Generator.py": 1642347735.351465, + "components\\Generator.py": 1644689001.9005148, "components\\projected_discriminator.py": 1642348101.4661522, "components\\pg_modules\\blocks.py": 1640773190.0, "components\\pg_modules\\diffaug.py": 1640773190.0, @@ -60,7 +60,7 @@ "face_crop.py": 1643789609.1834445, "face_crop_video.py": 1643815024.5516832, "similarity.py": 1643269705.1073737, - "train_multigpu.py": 1644509438.008675, + "train_multigpu.py": 1644689820.5085416, "components\\arcface_decoder.py": 1643396144.2575414, "components\\Generator_nobias.py": 1643179001.810856, "data_tools\\data_loader_VGGFace2HQ_multigpu.py": 1644330414.9587426, @@ -102,13 +102,14 @@ "wandb\\run-20220129_035624-3hmwgcgw\\files\\config.yaml": 1643426465.6088357, "dnnlib\\util.py": 1640773190.0, "dnnlib\\__init__.py": 1640773190.0, - "components\\Generator_ori.py": 1644229508.0031855, + "components\\Generator_ori.py": 1644689174.414655, "losses\\cos.py": 1644229583.4023254, "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\\Generator_reduce_up.py": 1644688655.2096283, + "components\\Generator_upsample.py": 1644689723.8293872, "components\\misc\\Involution.py": 1644509321.5267963, - "train_yamls\\train_Invoup.yaml": 1644550037.4785244 + "train_yamls\\train_Invoup.yaml": 1644689981.9794765, + "flops.py": 1644689428.618648 } \ No newline at end of file diff --git a/README.md b/README.md index f2ea463..fde62be 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ ***OR*** -- wandb (pip install wandb) +- Do not need to install tensorboard and tensorboardX any more. ***Logger is an option setting, which can be adjust with train.py --logger [wandb, tensorbaord, None]*** diff --git a/components/Generator.py b/components/Generator.py index 56552d2..083404a 100644 --- a/components/Generator.py +++ b/components/Generator.py @@ -5,7 +5,7 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Sunday, 16th January 2022 11:42:14 pm +# Last Modified: Sunday, 13th February 2022 2:03:21 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -166,21 +166,21 @@ class Generator(nn.Module): # 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) + def forward(self, img, id): + # x = input # 3*224*224 + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/components/Generator_nobias.py b/components/Generator_config.py similarity index 62% rename from components/Generator_nobias.py rename to components/Generator_config.py index 832211c..b8fea6d 100644 --- a/components/Generator_nobias.py +++ b/components/Generator_config.py @@ -5,16 +5,14 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Wednesday, 26th January 2022 2:36:41 pm +# Last Modified: Sunday, 13th February 2022 3:03:05 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# -from audioop import bias import torch from torch import nn -from torch.nn import init -from torch.nn import functional as F +from components.DeConv_Invo import DeConv class InstanceNorm(nn.Module): def __init__(self, epsilon=1e-8): @@ -61,7 +59,7 @@ class ResnetBlock_Adain(nn.Module): p = 1 else: raise NotImplementedError('padding [%s] is not implemented' % padding_type) - conv1 += [nn.Conv2d(dim, dim, kernel_size=3, padding = p, bias=False), InstanceNorm()] + 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 @@ -76,7 +74,7 @@ class ResnetBlock_Adain(nn.Module): p = 1 else: raise NotImplementedError('padding [%s] is not implemented' % padding_type) - conv2 += [nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=False), InstanceNorm()] + conv2 += [nn.Conv2d(dim, dim, kernel_size=3, padding=p), InstanceNorm()] self.conv2 = nn.Sequential(*conv2) self.style2 = ApplyStyle(latent_size, dim) @@ -101,59 +99,57 @@ class Generator(nn.Module): chn = kwargs["g_conv_dim"] k_size = kwargs["g_kernel_size"] res_num = kwargs["res_num"] + in_channel = kwargs["in_channel"] padding_size= int((k_size -1)/2) padding_type= 'reflect' activation = nn.ReLU(True) - self.first_layer = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False), - nn.BatchNorm2d(64), activation) + self.first_layer = nn.Sequential(nn.Conv2d(3, in_channel, kernel_size=3, padding=1, bias=False), + nn.BatchNorm2d(in_channel), activation) ### downsample - self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1, bias=False), - nn.BatchNorm2d(128), activation) + self.down1 = nn.Sequential(nn.Conv2d(in_channel, in_channel*2, kernel_size=3, stride=2, padding=1, bias=False), + nn.BatchNorm2d(in_channel*2), activation) - self.down2 = nn.Sequential(nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1, bias=False), - nn.BatchNorm2d(256), activation) + self.down2 = nn.Sequential(nn.Conv2d(in_channel*2, in_channel*4, kernel_size=3, stride=2, padding=1, bias=False), + nn.BatchNorm2d(in_channel*4), activation) - self.down3 = nn.Sequential(nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1, bias=False), - nn.BatchNorm2d(512), activation) + self.down3 = nn.Sequential(nn.Conv2d(in_channel*4, in_channel*8, kernel_size=3, stride=2, padding=1, bias=False), + nn.BatchNorm2d(in_channel*8), activation) - self.down4 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1, bias=False), - nn.BatchNorm2d(512), activation) + self.down4 = nn.Sequential(nn.Conv2d(in_channel*8, in_channel*8, kernel_size=3, stride=2, padding=1, bias=False), + nn.BatchNorm2d(in_channel*8), activation) ### resnet blocks BN = [] - for i in range(res_num): + for _ in range(res_num): BN += [ - ResnetBlock_Adain(512, latent_size=chn, padding_type=padding_type, activation=activation)] + ResnetBlock_Adain(in_channel*8, latent_size=chn, + padding_type=padding_type, activation=activation)] self.BottleNeck = nn.Sequential(*BN) self.up4 = nn.Sequential( - nn.Upsample(scale_factor=2, mode='bilinear'), - nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False), - nn.BatchNorm2d(512), activation + DeConv(in_channel*8,in_channel*8,3), + nn.BatchNorm2d(in_channel*8), activation ) self.up3 = nn.Sequential( - nn.Upsample(scale_factor=2, mode='bilinear'), - nn.Conv2d(512, 256, kernel_size=3, stride=1, padding=1, bias=False), - nn.BatchNorm2d(256), activation + DeConv(in_channel*8,in_channel*4,3), + nn.BatchNorm2d(in_channel*4), activation ) self.up2 = nn.Sequential( - nn.Upsample(scale_factor=2, mode='bilinear'), - nn.Conv2d(256, 128, kernel_size=3, stride=1, padding=1, bias=False), - nn.BatchNorm2d(128), activation + DeConv(in_channel*4,in_channel*2,3), + nn.BatchNorm2d(in_channel*2), activation ) self.up1 = nn.Sequential( - nn.Upsample(scale_factor=2, mode='bilinear'), - nn.Conv2d(128, 64, kernel_size=3, stride=1, padding=1, bias=False), - nn.BatchNorm2d(64), activation + DeConv(in_channel*2,in_channel,3), + nn.BatchNorm2d(in_channel), activation ) - self.last_layer = nn.Sequential(nn.Conv2d(64, 3, kernel_size=3, padding=1, bias=False)) + self.last_layer = nn.Sequential(nn.Conv2d(in_channel, 3, kernel_size=3, padding=1)) # self.__weights_init__() @@ -167,21 +163,21 @@ class Generator(nn.Module): # 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) + def forward(self, img, id): + # x = input # 3*224*224 + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/components/Generator_reduce_up.py b/components/Generator_modulation_up.py similarity index 86% rename from components/Generator_reduce_up.py rename to components/Generator_modulation_up.py index ef095f8..ef370a0 100644 --- a/components/Generator_reduce_up.py +++ b/components/Generator_modulation_up.py @@ -5,7 +5,7 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Thursday, 10th February 2022 3:14:08 pm +# Last Modified: Sunday, 13th February 2022 1:35:21 pm # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -116,7 +116,9 @@ class Generator(nn.Module): activation = nn.ReLU(True) - self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(3, 64, kernel_size=7, padding=0, bias=False), + # self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(3, 64, kernel_size=7, padding=0, bias=False), + # nn.BatchNorm2d(64), activation) + self.first_layer = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(64), activation) ### downsample self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1), @@ -157,9 +159,9 @@ class Generator(nn.Module): 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.last_layer = nn.Sequential(nn.Conv2d(64, 3, kernel_size=3, padding=1)) + # self.last_layer = nn.Sequential(nn.ReflectionPad2d(3), + # nn.Conv2d(64, 3, kernel_size=7, padding=0)) # self.__weights_init__() @@ -173,21 +175,20 @@ class Generator(nn.Module): # 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) + def forward(self, img, id): + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/components/Generator_ori.py b/components/Generator_ori.py index c611e08..d48ab2b 100644 --- a/components/Generator_ori.py +++ b/components/Generator_ori.py @@ -5,7 +5,7 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Monday, 7th February 2022 6:25:07 pm +# Last Modified: Sunday, 13th February 2022 2:06:14 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -167,21 +167,20 @@ class Generator(nn.Module): # 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) + def forward(self, img, id): + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/components/Generator_reduce.py b/components/Generator_reduce.py index 881a0cb..1537040 100644 --- a/components/Generator_reduce.py +++ b/components/Generator_reduce.py @@ -5,7 +5,7 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Monday, 24th January 2022 6:47:22 pm +# Last Modified: Sunday, 13th February 2022 3:47:59 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -117,19 +117,19 @@ class Generator(nn.Module): activation = nn.ReLU(True) - self.stem = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1), + self.first_layer = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(64), activation) ### downsample - self.down1 = nn.Sequential(nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1), + 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), + 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), + 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), + self.down4 = nn.Sequential(nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1, bias=False), nn.BatchNorm2d(512), activation) ### resnet blocks @@ -177,21 +177,20 @@ class Generator(nn.Module): # if isinstance(layer,nn.Conv2d): # nn.init.xavier_uniform_(layer.weight) - def forward(self, input, id): - x = input # 3*224*224 - skip1 = self.stem(x) - skip2 = self.down1(skip1) - skip3 = self.down2(skip2) - skip4 = self.down3(skip3) - res = self.down4(skip4) + def forward(self, img, id): + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/components/Generator_upsample.py b/components/Generator_upsample.py index b2b5986..d0ccfbc 100644 --- a/components/Generator_upsample.py +++ b/components/Generator_upsample.py @@ -5,7 +5,7 @@ # Created Date: Sunday January 16th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Thursday, 10th February 2022 1:01:09 am +# Last Modified: Sunday, 13th February 2022 2:15:23 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -104,9 +104,11 @@ class Generator(nn.Module): 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), + + self.first_layer = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(64), activation) + # self.first_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(3, 64, kernel_size=3, 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) @@ -146,8 +148,9 @@ class Generator(nn.Module): 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.last_layer = nn.Sequential(nn.Conv2d(64, 3, kernel_size=3, padding=1)) + # self.last_layer = nn.Sequential(nn.ReflectionPad2d(3), nn.Conv2d(64, 3, kernel_size=3, padding=0)) + # self.__weights_init__() @@ -161,21 +164,20 @@ class Generator(nn.Module): # 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) + def forward(self, img, id): + res = self.first_layer(img) + res = self.down1(res) + res = self.down2(res) + res = self.down3(res) + res = self.down4(res) for i in range(len(self.BottleNeck)): - x = self.BottleNeck[i](res, id) + res = 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) + res = self.up4(res) + res = self.up3(res) + res = self.up2(res) + res = self.up1(res) + res = self.last_layer(res) - return x + return res diff --git a/flops.py b/flops.py new file mode 100644 index 0000000..f5e8eb3 --- /dev/null +++ b/flops.py @@ -0,0 +1,56 @@ +#!/usr/bin/env python3 +# -*- coding:utf-8 -*- +############################################################# +# File: flops.py +# Created Date: Sunday February 13th 2022 +# Author: Chen Xuanhong +# Email: chenxuanhongzju@outlook.com +# Last Modified: Sunday, 13th February 2022 1:37:15 pm +# Modified By: Chen Xuanhong +# Copyright (c) 2022 Shanghai Jiao Tong University +############################################################# + + +import os + +import torch +from thop import profile +from thop import clever_format + + + +if __name__ == '__main__': + + script = "Generator_config" + class_name = "Generator" + arcface_ckpt= "arcface_ckpt/arcface_checkpoint.tar" + model_config={ + "g_conv_dim": 512, + "g_kernel_size": 3, + "in_channel":64, + "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) + + attr_img = torch.rand((1,3,512,512)).cuda() + id_img = torch.rand((1,3,112,112)).cuda() + id_latent = torch.rand((1,512)).cuda() + + macs, params = profile(model, inputs=(attr_img, id_latent)) + macs, params = clever_format([macs, params], "%.3f") + print(macs) + print(params) \ No newline at end of file diff --git a/speed_test.py b/speed_test.py index 2465f37..691a6e5 100644 --- a/speed_test.py +++ b/speed_test.py @@ -5,7 +5,7 @@ # Created Date: Thursday February 10th 2022 # Author: Chen Xuanhong # Email: chenxuanhongzju@outlook.com -# Last Modified: Thursday, 10th February 2022 3:05:44 pm +# Last Modified: Sunday, 13th February 2022 3:04:07 am # Modified By: Chen Xuanhong # Copyright (c) 2022 Shanghai Jiao Tong University ############################################################# @@ -18,12 +18,13 @@ import torch if __name__ == '__main__': - script = "Generator_reduce_up" + script = "Generator_config" class_name = "Generator" arcface_ckpt= "arcface_ckpt/arcface_checkpoint.tar" model_config={ "g_conv_dim": 512, "g_kernel_size": 3, + "in_channel":16, "res_num": 9 } diff --git a/train_multigpu.py b/train_multigpu.py index 48354e2..fcd9f95 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: Friday, 11th February 2022 12:10:37 am +# Last Modified: Sunday, 13th February 2022 2:16:50 am # Modified By: Chen Xuanhong # Copyright (c) 2020 Shanghai Jiao Tong University ############################################################# @@ -31,7 +31,7 @@ def getParameters(): parser = argparse.ArgumentParser() # general settings - parser.add_argument('-v', '--version', type=str, default='invoup1', + parser.add_argument('-v', '--version', type=str, default='invoup2', help="version name for train, test, finetune") parser.add_argument('-t', '--tag', type=str, default='invo_upsample', help="tag for current experiment") @@ -46,7 +46,7 @@ def getParameters(): # training parser.add_argument('--experiment_description', type=str, - default="使用involution作为上采样") + default="generator网络前向部分残差的赋值错误，现纠正，重新训练网络") parser.add_argument('--train_yaml', type=str, default="train_Invoup.yaml")