prova_gen_unet.py

import torch
from torch import nn
from torchvision import transforms
import functools
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

import cv2


from PaletteGen import palette_extractor
from Downsampling import pixxelate


path = './Pictures/venz.JPG'


input_img= cv2.imread(path, cv2.IMREAD_COLOR)
input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)


class UnetGenerator(nn.Module):
    """Create a Unet-based generator"""

    def __init__(self, input_nc, output_nc, num_downs, ngf=64, norm_layer=nn.BatchNorm2d, use_dropout=False):
        """Construct a Unet generator
        Parameters:
            input_nc (int)  -- the number of channels in input images
            output_nc (int) -- the number of channels in output images
            num_downs (int) -- the number of downsamplings in UNet. For example, # if |num_downs| == 7,
                                image of size 128x128 will become of size 1x1 # at the bottleneck
            ngf (int)       -- the number of filters in the last conv layer
            norm_layer      -- normalization layer

        We construct the U-Net from the innermost layer to the outermost layer.
        It is a recursive process.
        """
        super(UnetGenerator, self).__init__()
        # construct unet structure
        unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=None, norm_layer=norm_layer, innermost=True)  # add the innermost layer
        for i in range(num_downs - 5):          # add intermediate layers with ngf * 8 filters
            unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer, use_dropout=use_dropout)
        # gradually reduce the number of filters from ngf * 8 to ngf
        unet_block = UnetSkipConnectionBlock(ngf * 4, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        unet_block = UnetSkipConnectionBlock(ngf * 2, ngf * 4, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        unet_block = UnetSkipConnectionBlock(ngf, ngf * 2, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        self.model = UnetSkipConnectionBlock(output_nc, ngf, input_nc=input_nc, submodule=unet_block, outermost=True, norm_layer=norm_layer)  # add the outermost layer

    def forward(self, input):
        """Standard forward"""
        return self.model(input)

###############################################################################

class UnetSkipConnectionBlock(nn.Module):
    """Defines the Unet submodule with skip connection.
        X -------------------identity----------------------
        |-- downsampling -- |submodule| -- upsampling --|
    """

    def __init__(self, outer_nc, inner_nc, input_nc=None,
                 submodule=None, outermost=False, innermost=False, norm_layer=nn.BatchNorm2d, use_dropout=False):
        """Construct a Unet submodule with skip connections.

        Parameters:
            outer_nc (int) -- the number of filters in the outer conv layer
            inner_nc (int) -- the number of filters in the inner conv layer
            input_nc (int) -- the number of channels in input images/features
            submodule (UnetSkipConnectionBlock) -- previously defined submodules
            outermost (bool)    -- if this module is the outermost module
            innermost (bool)    -- if this module is the innermost module
            norm_layer          -- normalization layer
            use_dropout (bool)  -- if use dropout layers.
        """
        super(UnetSkipConnectionBlock, self).__init__()
        self.outermost = outermost
        if type(norm_layer) == functools.partial:
            use_bias = norm_layer.func == nn.InstanceNorm2d
        else:
            use_bias = norm_layer == nn.InstanceNorm2d
        if input_nc is None:
            input_nc = outer_nc
        downconv = nn.Conv2d(input_nc, inner_nc, kernel_size=4,
                             stride=2, padding=1, bias=use_bias)
        downrelu = nn.LeakyReLU(0.2, True)
        downnorm = norm_layer(inner_nc)
        uprelu = nn.ReLU(True)
        upnorm = norm_layer(outer_nc)

        if outermost:
            upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1)
            down = [downconv]
            up = [uprelu, upconv, nn.Tanh()]
            model = down + [submodule] + up
        elif innermost:
            upconv = nn.ConvTranspose2d(inner_nc, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1, bias=use_bias)
            down = [downrelu, downconv]
            up = [uprelu, upconv, upnorm]
            model = down + up
        else:
            upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1, bias=use_bias)
            down = [downrelu, downconv, downnorm]
            up = [uprelu, upconv, upnorm]

            if use_dropout:
                model = down + [submodule] + up + [nn.Dropout(0.5)]
            else:
                model = down + [submodule] + up

        self.model = nn.Sequential(*model)

    def forward(self, x):
        if self.outermost:
            return self.model(x)
        else:   # add skip connections
            return torch.cat([x, self.model(x)], 1)

################################################################################

def get_norm_layer(norm_type='instance'):
    """Return a normalization layer
    Parameters:
        norm_type (str) -- the name of the normalization layer: batch | instance | none
    For BatchNorm, we use learnable affine parameters and track running statistics (mean/stddev).
    For InstanceNorm, we do not use learnable affine parameters. We do not track running statistics.
    """
    if norm_type == 'batch':
        norm_layer = functools.partial(nn.BatchNorm2d, affine=True, track_running_stats=True)
    elif norm_type == 'instance':
        norm_layer = functools.partial(nn.InstanceNorm2d, affine=False, track_running_stats=False)
    elif norm_type == 'none':
        def norm_layer(x): return Identity()
    else:
        raise NotImplementedError('normalization layer [%s] is not found' % norm_type)
    return norm_layer

###############################################################################

norm_layer = get_norm_layer(norm_type='instance')
net = UnetGenerator(input_nc=3, output_nc=3, num_downs=8, ngf=64, norm_layer=norm_layer, use_dropout=False)

device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
gpu_ids = [0] if torch.cuda.is_available() else []

state_dict = torch.load('./unet-256-cartoon(150).pth', map_location=device)

if len(gpu_ids) > 0:
    assert(torch.cuda.is_available())
    net.to(gpu_ids[0])
    net = torch.nn.DataParallel(net, gpu_ids)  # multi-GPUs

if isinstance(net, torch.nn.DataParallel):
    net = net.module

net.load_state_dict(state_dict)

transform_A = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

#Effettuo un resize altrimenti l'input della rete non è compatibile
input_img = cv2.resize(input_img, (256,256), interpolation = cv2.INTER_AREA)

A_img = transform_A(input_img)
A_img = A_img.unsqueeze(0).to(device)


fake_img_tensor1 = net(A_img)


def tensor2im(input_image, imtype=np.uint8):
    """"Converts a Tensor array into a numpy image array.
    Parameters:
        input_image (tensor) --  the input image tensor array
        imtype (type)        --  the desired type of the converted numpy array
    """
    if not isinstance(input_image, np.ndarray):
        if isinstance(input_image, torch.Tensor):  # get the data from a variable
            image_tensor = input_image.data
        else:
            return input_image
        image_numpy = image_tensor[0].cpu().float().numpy()  # convert it into a numpy array
        if image_numpy.shape[0] == 1:  # grayscale to RGB
            image_numpy = np.tile(image_numpy, (3, 1, 1))
        image_numpy = (np.transpose(image_numpy, (1, 2, 0)) + 1) / 2.0 * 255.0  # post-processing: tranpose and scaling
    else:  # if it is a numpy array, do nothing
        image_numpy = input_image
    return image_numpy.astype(imtype)

out_nn = tensor2im(fake_img_tensor1)

save_path1 = './output_nn_unet.png'

save_path2 = './output_nn_unet_post_processed.png'

palette = palette_extractor(out_nn)
out_final = pixxelate(out_nn, 128, palette)


plt.imshow(np.array(out_final))
plt.show()

out_nn_save = cv2.cvtColor(out_nn, cv2.COLOR_RGB2BGR)
out_nn_save2 = cv2.cvtColor(out_final, cv2.COLOR_RGB2BGR)

cv2.imwrite(save_path1, out_nn_save)
cv2.imwrite(save_path2, out_nn_save2)