I trained StarGAN model on my custom dataset. And I need to convert this model from .pth(Pytorch) to .pb for using on Android studio. I searched a lot and I found some ways for conversion. However all solutions don't work on my case.
I tried on small network that includes only one nn.Linear layer. On this network, solutions work very well!
I think, my network includes Conv2D layer and MaxPooling2D layer so conversion processing doesn't work.
First, this is my network(StarGAN).
import torch
import torch.nn as nn
import numpy as np
class ResidualBlock(nn.Module):
def __init__(self, dim_in, dim_out):
super(ResidualBlock, self).__init__()
self.main = nn.Sequential(
nn.Conv2d(dim_in, dim_out, kernel_size=3, stride=1, padding=1, bias=False),
nn.InstanceNorm2d(dim_out, affine=True, track_running_stats=True),
nn.ReLU(inplace=True),
nn.Conv2d(dim_out, dim_out, kernel_size=3, stride=1, padding=1, bias=False),
nn.InstanceNorm2d(dim_out, affine=True, track_running_stats=True))
def forward(self, x):
return x + self.main(x)
class Generator(nn.Module):
def __init__(self, conv_dim=64, c_dim=5, repeat_num=6):
super(Generator, self).__init__()
layers = []
layers.append(nn.Conv2d(3 + c_dim, conv_dim, kernel_size=7, stride=1, padding=3, bias=False))
layers.append(nn.InstanceNorm2d(conv_dim, affine=True, track_running_stats=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = conv_dim
for _ in range(2):
layers.append(nn.Conv2d(curr_dim, curr_dim * 2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim * 2, affine=True, track_running_stats=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim * 2
for _ in range(repeat_num):
layers.append(ResidualBlock(dim_in=curr_dim, dim_out=curr_dim))
for _ in range(2):
layers.append(nn.ConvTranspose2d(curr_dim, curr_dim // 2, kernel_size=4, stride=2, padding=1, bias=False))
layers.append(nn.InstanceNorm2d(curr_dim // 2, affine=True, track_running_stats=True))
layers.append(nn.ReLU(inplace=True))
curr_dim = curr_dim // 2
layers.append(nn.Conv2d(curr_dim, 3, kernel_size=7, stride=1, padding=3, bias=False))
layers.append(nn.Tanh())
self.main = nn.Sequential(*layers)
def forward(self, x, c):
c = c.view(c.size(0), c.size(1), 1, 1)
c = c.repeat(1, 1, x.size(2), x.size(3))
x = torch.cat([x, c], dim=1)
return self.main(x)
class Discriminator(nn.Module):
def __init__(self, image_size=128, conv_dim=64, c_dim=5, repeat_num=6):
super(Discriminator, self).__init__()
layers = []
layers.append(nn.Conv2d(3, conv_dim, kernel_size=4, stride=2, padding=1))
layers.append(nn.LeakyReLU(0.01))
curr_dim = conv_dim
for _ in range(1, repeat_num):
layers.append(nn.Conv2d(curr_dim, curr_dim * 2, kernel_size=4, stride=2, padding=1))
layers.append(nn.LeakyReLU(0.01))
curr_dim = curr_dim * 2
kernel_size = int(image_size / np.power(2, repeat_num))
self.main = nn.Sequential(*layers)
self.conv1 = nn.Conv2d(curr_dim, 1, kernel_size=3, stride=1, padding=1, bias=False)
self.conv2 = nn.Conv2d(curr_dim, c_dim, kernel_size=kernel_size, bias=False)
def forward(self, x):
h = self.main(x)
out_src = self.conv1(h)
out_cls = self.conv2(h)
return out_src, out_cls.view(out_cls.size(0), out_cls.size(1))
And this is the error message.
TypeError: object of type 'torch._C.Value' has no len() (occurred when translating repeat)
Is there any way for conversion? Help me.
