add demo + inference files

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+from huggingface_hub import hf_hub_download
+
+import torch
+from networks import define_G
+from torchvision import transforms
+
+REPO_ID = "Launchpad/ditto"
+FILENAME = "model.pth"
+
+# model_dict = torch.load("model.pth")
+model_dict = torch.load(
+        hf_hub_download(repo_id=REPO_ID, filename=FILENAME)
+        )
+generator = define_G(input_nc=3, output_nc=3, ngf=64, netG="resnet_9blocks", norm="instance")
+generator.load_state_dict(model_dict)
+generator.eval()
+
+# set up transforms for model
+encode = transforms.Compose([
+    transforms.ToTensor(),
+    transforms.Resize((256, 256))
+])
+transform = transforms.ToPILImage()
+
+def generate_pokemon(pet_img):
+    # encode image
+    encoded_img = encode(pet_img)
+
+    # evaluate model on pet image
+    with torch.no_grad():
+        generated_img = generator(encoded_img)
+        
+    # transform to PIL image
+    return transform(generated_img)
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Image("https://www.ocf.berkeley.edu/~launchpad/media/uploads/project_logos/Ditto.png", elem_id="logo-img", show_label=False, show_share_button=False, show_download_button=False)
+            
+        with gr.Column(scale=3):
+          gr.Markdown("""Ditto is a [Launchpad](https://launchpad.studentorg.berkeley.edu/) project (Fall 2022) that transfers styles of Pokemon sprites onto pet images using GANs and contrastive learning.
+                      <br/><br/>
+                      **Model**: [ditto](https://huggingface.co/Launchpad/ditto)
+                      <br/>
+                      **Developed by**: Kiran Suresh, Annie Lee, Chloe Wong, Tony Xin, Sebastian Zhao
+                      """
+                      )
+    with gr.Row():  
+        gr.Interface(generate_pokemon, gr.Image(), "image")
+
+if __name__ == '__main__':
+    demo.launch()

networks.py

@@ -0,0 +1,366 @@
+import torch
+import torch.nn as nn
+from torch.nn import init
+import functools
+from torch.optim import lr_scheduler
+
+
+###############################################################################
+# Helper Functions
+###############################################################################
+
+
+class Identity(nn.Module):
+    def forward(self, x):
+        return x
+
+
+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
+
+
+def get_scheduler(optimizer, opt):
+    """Return a learning rate scheduler
+    Parameters:
+        optimizer          -- the optimizer of the network
+        opt (option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions．　
+                              opt.lr_policy is the name of learning rate policy: linear | step | plateau | cosine
+    For 'linear', we keep the same learning rate for the first <opt.n_epochs> epochs
+    and linearly decay the rate to zero over the next <opt.n_epochs_decay> epochs.
+    For other schedulers (step, plateau, and cosine), we use the default PyTorch schedulers.
+    See https://pytorch.org/docs/stable/optim.html for more details.
+    """
+    if opt.lr_policy == 'linear':
+        def lambda_rule(epoch):
+            lr_l = 1.0 - max(0, epoch + opt.epoch_count - opt.n_epochs) / float(opt.n_epochs_decay + 1)
+            return lr_l
+        scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda_rule)
+    elif opt.lr_policy == 'step':
+        scheduler = lr_scheduler.StepLR(optimizer, step_size=opt.lr_decay_iters, gamma=0.1)
+    elif opt.lr_policy == 'plateau':
+        scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.2, threshold=0.01, patience=5)
+    elif opt.lr_policy == 'cosine':
+        scheduler = lr_scheduler.CosineAnnealingLR(optimizer, T_max=opt.n_epochs, eta_min=0)
+    else:
+        return NotImplementedError('learning rate policy [%s] is not implemented', opt.lr_policy)
+    return scheduler
+
+
+def init_weights(net, init_type='normal', init_gain=0.02):
+    """Initialize network weights.
+    Parameters:
+        net (network)   -- network to be initialized
+        init_type (str) -- the name of an initialization method: normal | xavier | kaiming | orthogonal
+        init_gain (float)    -- scaling factor for normal, xavier and orthogonal.
+    We use 'normal' in the original pix2pix and CycleGAN paper. But xavier and kaiming might
+    work better for some applications. Feel free to try yourself.
+    """
+    def init_func(m):  # define the initialization function
+        classname = m.__class__.__name__
+        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
+            if init_type == 'normal':
+                init.normal_(m.weight.data, 0.0, init_gain)
+            elif init_type == 'xavier':
+                init.xavier_normal_(m.weight.data, gain=init_gain)
+            elif init_type == 'kaiming':
+                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
+            elif init_type == 'orthogonal':
+                init.orthogonal_(m.weight.data, gain=init_gain)
+            else:
+                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
+            if hasattr(m, 'bias') and m.bias is not None:
+                init.constant_(m.bias.data, 0.0)
+        elif classname.find('BatchNorm2d') != -1:  # BatchNorm Layer's weight is not a matrix; only normal distribution applies.
+            init.normal_(m.weight.data, 1.0, init_gain)
+            init.constant_(m.bias.data, 0.0)
+
+    print('initialize network with %s' % init_type)
+    net.apply(init_func)  # apply the initialization function <init_func>
+
+
+def init_net(net, init_type='normal', init_gain=0.02, gpu_ids=[]):
+    """Initialize a network: 1. register CPU/GPU device (with multi-GPU support); 2. initialize the network weights
+    Parameters:
+        net (network)      -- the network to be initialized
+        init_type (str)    -- the name of an initialization method: normal | xavier | kaiming | orthogonal
+        gain (float)       -- scaling factor for normal, xavier and orthogonal.
+        gpu_ids (int list) -- which GPUs the network runs on: e.g., 0,1,2
+    Return an initialized network.
+    """
+    if len(gpu_ids) > 0:
+        assert(torch.cuda.is_available())
+        net.to(gpu_ids[0])
+        net = torch.nn.DataParallel(net, gpu_ids)  # multi-GPUs
+    init_weights(net, init_type, init_gain=init_gain)
+    return net
+
+
+def define_G(input_nc, output_nc, ngf, netG, norm='batch', use_dropout=False, init_type='normal', init_gain=0.02, gpu_ids=[]):
+    """Create a generator
+    Parameters:
+        input_nc (int) -- the number of channels in input images
+        output_nc (int) -- the number of channels in output images
+        ngf (int) -- the number of filters in the last conv layer
+        netG (str) -- the architecture's name: resnet_9blocks | resnet_6blocks | unet_256 | unet_128
+        norm (str) -- the name of normalization layers used in the network: batch | instance | none
+        use_dropout (bool) -- if use dropout layers.
+        init_type (str)    -- the name of our initialization method.
+        init_gain (float)  -- scaling factor for normal, xavier and orthogonal.
+        gpu_ids (int list) -- which GPUs the network runs on: e.g., 0,1,2
+    Returns a generator
+    Our current implementation provides two types of generators:
+        U-Net: [unet_128] (for 128x128 input images) and [unet_256] (for 256x256 input images)
+        The original U-Net paper: https://arxiv.org/abs/1505.04597
+        Resnet-based generator: [resnet_6blocks] (with 6 Resnet blocks) and [resnet_9blocks] (with 9 Resnet blocks)
+        Resnet-based generator consists of several Resnet blocks between a few downsampling/upsampling operations.
+        We adapt Torch code from Justin Johnson's neural style transfer project (https://github.com/jcjohnson/fast-neural-style).
+    The generator has been initialized by <init_net>. It uses RELU for non-linearity.
+    """
+    net = None
+    norm_layer = get_norm_layer(norm_type=norm)
+
+    if netG == 'resnet_9blocks':
+        net = ResnetGenerator(input_nc, output_nc, ngf, norm_layer=norm_layer, use_dropout=use_dropout, n_blocks=9)
+    elif netG == 'resnet_6blocks':
+        net = ResnetGenerator(input_nc, output_nc, ngf, norm_layer=norm_layer, use_dropout=use_dropout, n_blocks=6)
+    elif netG == 'unet_128':
+        net = UnetGenerator(input_nc, output_nc, 7, ngf, norm_layer=norm_layer, use_dropout=use_dropout)
+    elif netG == 'unet_256':
+        net = UnetGenerator(input_nc, output_nc, 8, ngf, norm_layer=norm_layer, use_dropout=use_dropout)
+    else:
+        raise NotImplementedError('Generator model name [%s] is not recognized' % netG)
+    return init_net(net, init_type, init_gain, gpu_ids)
+
+##############################################################################
+# Classes
+##############################################################################
+
+class ResnetGenerator(nn.Module):
+    """Resnet-based generator that consists of Resnet blocks between a few downsampling/upsampling operations.
+    We adapt Torch code and idea from Justin Johnson's neural style transfer project(https://github.com/jcjohnson/fast-neural-style)
+    """
+
+    def __init__(self, input_nc, output_nc, ngf=64, norm_layer=nn.BatchNorm2d, use_dropout=False, n_blocks=6, padding_type='reflect'):
+        """Construct a Resnet-based generator
+        Parameters:
+            input_nc (int)      -- the number of channels in input images
+            output_nc (int)     -- the number of channels in output images
+            ngf (int)           -- the number of filters in the last conv layer
+            norm_layer          -- normalization layer
+            use_dropout (bool)  -- if use dropout layers
+            n_blocks (int)      -- the number of ResNet blocks
+            padding_type (str)  -- the name of padding layer in conv layers: reflect | replicate | zero
+        """
+        assert(n_blocks >= 0)
+        super(ResnetGenerator, self).__init__()
+        if type(norm_layer) == functools.partial:
+            use_bias = norm_layer.func == nn.InstanceNorm2d
+        else:
+            use_bias = norm_layer == nn.InstanceNorm2d
+
+        model = [nn.ReflectionPad2d(3),
+                 nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0, bias=use_bias),
+                 norm_layer(ngf),
+                 nn.ReLU(True)]
+
+        n_downsampling = 2
+        for i in range(n_downsampling):  # add downsampling layers
+            mult = 2 ** i
+            model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1, bias=use_bias),
+                      norm_layer(ngf * mult * 2),
+                      nn.ReLU(True)]
+
+        mult = 2 ** n_downsampling
+        for i in range(n_blocks):       # add ResNet blocks
+
+            model += [ResnetBlock(ngf * mult, padding_type=padding_type, norm_layer=norm_layer, use_dropout=use_dropout, use_bias=use_bias)]
+
+        for i in range(n_downsampling):  # add upsampling layers
+            mult = 2 ** (n_downsampling - i)
+            model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2),
+                                         kernel_size=3, stride=2,
+                                         padding=1, output_padding=1,
+                                         bias=use_bias),
+                      norm_layer(int(ngf * mult / 2)),
+                      nn.ReLU(True)]
+        model += [nn.ReflectionPad2d(3)]
+        model += [nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0)]
+        model += [nn.Tanh()]
+
+        self.model = nn.Sequential(*model)
+
+    def forward(self, input):
+        """Standard forward"""
+        return self.model(input)
+
+
+class ResnetBlock(nn.Module):
+    """Define a Resnet block"""
+
+    def __init__(self, dim, padding_type, norm_layer, use_dropout, use_bias):
+        """Initialize the Resnet block
+        A resnet block is a conv block with skip connections
+        We construct a conv block with build_conv_block function,
+        and implement skip connections in <forward> function.
+        Original Resnet paper: https://arxiv.org/pdf/1512.03385.pdf
+        """
+        super(ResnetBlock, self).__init__()
+        self.conv_block = self.build_conv_block(dim, padding_type, norm_layer, use_dropout, use_bias)
+
+    def build_conv_block(self, dim, padding_type, norm_layer, use_dropout, use_bias):
+        """Construct a convolutional block.
+        Parameters:
+            dim (int)           -- the number of channels in the conv layer.
+            padding_type (str)  -- the name of padding layer: reflect | replicate | zero
+            norm_layer          -- normalization layer
+            use_dropout (bool)  -- if use dropout layers.
+            use_bias (bool)     -- if the conv layer uses bias or not
+        Returns a conv block (with a conv layer, a normalization layer, and a non-linearity layer (ReLU))
+        """
+        conv_block = []
+        p = 0
+        if padding_type == 'reflect':
+            conv_block += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv_block += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+
+        conv_block += [nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias), norm_layer(dim), nn.ReLU(True)]
+        if use_dropout:
+            conv_block += [nn.Dropout(0.5)]
+
+        p = 0
+        if padding_type == 'reflect':
+            conv_block += [nn.ReflectionPad2d(1)]
+        elif padding_type == 'replicate':
+            conv_block += [nn.ReplicationPad2d(1)]
+        elif padding_type == 'zero':
+            p = 1
+        else:
+            raise NotImplementedError('padding [%s] is not implemented' % padding_type)
+        conv_block += [nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias), norm_layer(dim)]
+
+        return nn.Sequential(*conv_block)
+
+    def forward(self, x):
+        """Forward function (with skip connections)"""
+        out = x + self.conv_block(x)  # add skip connections
+        return out
+
+
+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)

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.13.0
+torchvision==0.14.0
+gradio==4.26.0