add app

.gitignore

@@ -0,0 +1 @@
+model_bk*

.vscode/sftp.json

@@ -0,0 +1,24 @@
+{
+    "name": "wzhoux",
+    "host": "9.134.229.18",
+    "protocol": "sftp",
+    "port": 36000,
+    "username": "root",
+    "remotePath": "/group/30042/zhouxiawang/project/gradio/RestoreFormerPlusPlus",
+    "uploadOnSave": true,
+    "password": "Beagirl12#",
+    "ignore": [
+        ".vscode",
+        ".git",
+        ".DS_Store",
+        ".conda",
+        "./models",
+        "./logs",
+        "outputs",
+        "eggs",
+        ".eggs",
+        "logs",
+        "experiments",
+        "./results"
+    ]
+}

RestoreFormer.py

@@ -0,0 +1,117 @@
+import os
+
+import cv2
+import torch
+from basicsr.utils import img2tensor, tensor2img
+from basicsr.utils.download_util import load_file_from_url
+from facexlib.utils.face_restoration_helper import FaceRestoreHelper
+from torchvision.transforms.functional import normalize
+
+from RestoreFormer_arch import VQVAEGANMultiHeadTransformer
+
+ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+class RestoreFormer():
+    """Helper for restoration with RestoreFormer.
+
+    It will detect and crop faces, and then resize the faces to 512x512.
+    RestoreFormer is used to restored the resized faces.
+    The background is upsampled with the bg_upsampler.
+    Finally, the faces will be pasted back to the upsample background image.
+
+    Args:
+        model_path (str): The path to the GFPGAN model. It can be urls (will first download it automatically).
+        upscale (float): The upscale of the final output. Default: 2.
+        arch (str): The RestoreFormer architecture. Option: RestoreFormer | RestoreFormer++. Default: RestoreFormer++.
+        bg_upsampler (nn.Module): The upsampler for the background. Default: None.
+    """
+
+    def __init__(self, model_path, upscale=2, arch='RestoreFromerPlusPlus', bg_upsampler=None, device=None):
+        self.upscale = upscale
+        self.bg_upsampler = bg_upsampler
+        self.arch = arch
+        
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if device is None else device
+
+        if arch == 'RestoreFormer':
+            self.RF = VQVAEGANMultiHeadTransformer(head_size = 8, ex_multi_scale_num = 0)
+        elif arch == 'RestoreFormer++':
+            self.RF = VQVAEGANMultiHeadTransformer(head_size = 4, ex_multi_scale_num = 1)
+        else:
+            raise NotImplementedError(f'Not support arch: {arch}.')
+        
+        # initialize face helper
+        self.face_helper = FaceRestoreHelper(
+            upscale,
+            face_size=512,
+            crop_ratio=(1, 1),
+            det_model='retinaface_resnet50',
+            save_ext='png',
+            use_parse=True,
+            device=self.device,
+            model_rootpath=None)
+        
+        if model_path.startswith('https://'):
+            model_path = load_file_from_url(
+                url=model_path, model_dir=os.path.join(ROOT_DIR, 'experiments/weights'), progress=True, file_name=None)
+        loadnet = torch.load(model_path)
+        
+        strict=False
+        weights = loadnet['state_dict']
+        new_weights = {}
+        for k, v in weights.items():
+            if k.startswith('vqvae.'):
+                k = k.replace('vqvae.', '')
+            new_weights[k] = v
+        self.RF.load_state_dict(new_weights, strict=strict)
+        
+        self.RF.eval()
+        self.RF = self.RF.to(self.device)
+
+    @torch.no_grad()
+    def enhance(self, img, has_aligned=False, only_center_face=False, paste_back=True):
+        self.face_helper.clean_all()
+
+        if has_aligned:  # the inputs are already aligned
+            img = cv2.resize(img, (512, 512))
+            self.face_helper.cropped_faces = [img]
+        else:
+            self.face_helper.read_image(img)
+            self.face_helper.get_face_landmarks_5(only_center_face=only_center_face, eye_dist_threshold=5)
+            # eye_dist_threshold=5: skip faces whose eye distance is smaller than 5 pixels
+            # TODO: even with eye_dist_threshold, it will still introduce wrong detections and restorations.
+            # align and warp each face
+            self.face_helper.align_warp_face()
+
+        # face restoration
+        for cropped_face in self.face_helper.cropped_faces:
+            # prepare data
+            cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
+            normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
+            cropped_face_t = cropped_face_t.unsqueeze(0).to(self.device)
+
+            try:
+                output = self.RF(cropped_face_t)[0]
+                restored_face = tensor2img(output.squeeze(0), rgb2bgr=True, min_max=(-1, 1))
+            except RuntimeError as error:
+                print(f'\tFailed inference for RestoreFormer: {error}.')
+                restored_face = cropped_face
+
+            restored_face = restored_face.astype('uint8')
+            self.face_helper.add_restored_face(restored_face)
+
+        if not has_aligned and paste_back:
+            # upsample the background
+            if self.bg_upsampler is not None:
+                # Now only support RealESRGAN for upsampling background
+                bg_img = self.bg_upsampler.enhance(img, outscale=self.upscale)[0]
+            else:
+                bg_img = None
+
+            self.face_helper.get_inverse_affine(None)
+            # paste each restored face to the input image
+            restored_img = self.face_helper.paste_faces_to_input_image(upsample_img=bg_img)
+            return self.face_helper.cropped_faces, self.face_helper.restored_faces, restored_img
+        else:
+            return self.face_helper.cropped_faces, self.face_helper.restored_faces, None

RestoreFormer_arch.py

@@ -0,0 +1,742 @@
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class VectorQuantizer(nn.Module):
+    """
+    see https://github.com/MishaLaskin/vqvae/blob/d761a999e2267766400dc646d82d3ac3657771d4/models/quantizer.py
+    ____________________________________________
+    Discretization bottleneck part of the VQ-VAE.
+    Inputs:
+    - n_e : number of embeddings
+    - e_dim : dimension of embedding
+    - beta : commitment cost used in loss term, beta * ||z_e(x)-sg[e]||^2
+    _____________________________________________
+    """
+
+    def __init__(self, n_e, e_dim, beta):
+        super(VectorQuantizer, self).__init__()
+        self.n_e = n_e
+        self.e_dim = e_dim
+        self.beta = beta
+
+        self.embedding = nn.Embedding(self.n_e, self.e_dim)
+        self.embedding.weight.data.uniform_(-1.0 / self.n_e, 1.0 / self.n_e)
+
+    def forward(self, z):
+        """
+        Inputs the output of the encoder network z and maps it to a discrete
+        one-hot vector that is the index of the closest embedding vector e_j
+        z (continuous) -> z_q (discrete)
+        z.shape = (batch, channel, height, width)
+        quantization pipeline:
+            1. get encoder input (B,C,H,W)
+            2. flatten input to (B*H*W,C)
+        """
+        # reshape z -> (batch, height, width, channel) and flatten
+        z = z.permute(0, 2, 3, 1).contiguous()
+        z_flattened = z.view(-1, self.e_dim)
+        # distances from z to embeddings e_j (z - e)^2 = z^2 + e^2 - 2 e * z
+
+        d = torch.sum(z_flattened ** 2, dim=1, keepdim=True) + \
+            torch.sum(self.embedding.weight**2, dim=1) - 2 * \
+            torch.matmul(z_flattened, self.embedding.weight.t())
+
+        ## could possible replace this here
+        # #\start...
+        # find closest encodings
+
+        min_value, min_encoding_indices = torch.min(d, dim=1)
+
+        min_encoding_indices = min_encoding_indices.unsqueeze(1)
+
+        min_encodings = torch.zeros(
+            min_encoding_indices.shape[0], self.n_e).to(z)
+        min_encodings.scatter_(1, min_encoding_indices, 1)
+
+        # dtype min encodings: torch.float32
+        # min_encodings shape: torch.Size([2048, 512])
+        # min_encoding_indices.shape: torch.Size([2048, 1])
+
+        # get quantized latent vectors
+        z_q = torch.matmul(min_encodings, self.embedding.weight).view(z.shape)
+        #.........\end
+
+        # with:
+        # .........\start
+        #min_encoding_indices = torch.argmin(d, dim=1)
+        #z_q = self.embedding(min_encoding_indices)
+        # ......\end......... (TODO)
+
+        # compute loss for embedding
+        loss = torch.mean((z_q.detach()-z)**2) + self.beta * \
+            torch.mean((z_q - z.detach()) ** 2)
+
+        # preserve gradients
+        z_q = z + (z_q - z).detach()
+
+        # perplexity
+        
+        e_mean = torch.mean(min_encodings, dim=0)
+        perplexity = torch.exp(-torch.sum(e_mean * torch.log(e_mean + 1e-10)))
+
+        # reshape back to match original input shape
+        z_q = z_q.permute(0, 3, 1, 2).contiguous()
+
+        return z_q, loss, (perplexity, min_encodings, min_encoding_indices, d)
+
+    def get_codebook_entry(self, indices, shape):
+        # shape specifying (batch, height, width, channel)
+        # TODO: check for more easy handling with nn.Embedding
+        min_encodings = torch.zeros(indices.shape[0], self.n_e).to(indices)
+        min_encodings.scatter_(1, indices[:,None], 1)
+
+        # get quantized latent vectors
+        z_q = torch.matmul(min_encodings.float(), self.embedding.weight)
+
+        if shape is not None:
+            z_q = z_q.view(shape)
+
+            # reshape back to match original input shape
+            z_q = z_q.permute(0, 3, 1, 2).contiguous()
+
+        return z_q
+
+# pytorch_diffusion + derived encoder decoder
+def nonlinearity(x):
+    # swish
+    return x*torch.sigmoid(x)
+
+
+def Normalize(in_channels):
+    return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
+
+
+class Upsample(nn.Module):
+    def __init__(self, in_channels, with_conv):
+        super().__init__()
+        self.with_conv = with_conv
+        if self.with_conv:
+            self.conv = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x):
+        x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
+        if self.with_conv:
+            x = self.conv(x)
+        return x
+
+
+class Downsample(nn.Module):
+    def __init__(self, in_channels, with_conv):
+        super().__init__()
+        self.with_conv = with_conv
+        if self.with_conv:
+            # no asymmetric padding in torch conv, must do it ourselves
+            self.conv = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=3,
+                                        stride=2,
+                                        padding=0)
+
+    def forward(self, x):
+        if self.with_conv:
+            pad = (0,1,0,1)
+            x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
+            x = self.conv(x)
+        else:
+            x = torch.nn.functional.avg_pool2d(x, kernel_size=2, stride=2)
+        return x
+
+
+class ResnetBlock(nn.Module):
+    def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
+                 dropout, temb_channels=512):
+        super().__init__()
+        self.in_channels = in_channels
+        out_channels = in_channels if out_channels is None else out_channels
+        self.out_channels = out_channels
+        self.use_conv_shortcut = conv_shortcut
+
+        self.norm1 = Normalize(in_channels)
+        self.conv1 = torch.nn.Conv2d(in_channels,
+                                     out_channels,
+                                     kernel_size=3,
+                                     stride=1,
+                                     padding=1)
+        if temb_channels > 0:
+            self.temb_proj = torch.nn.Linear(temb_channels,
+                                             out_channels)
+        self.norm2 = Normalize(out_channels)
+        self.dropout = torch.nn.Dropout(dropout)
+        self.conv2 = torch.nn.Conv2d(out_channels,
+                                     out_channels,
+                                     kernel_size=3,
+                                     stride=1,
+                                     padding=1)
+        if self.in_channels != self.out_channels:
+            if self.use_conv_shortcut:
+                self.conv_shortcut = torch.nn.Conv2d(in_channels,
+                                                     out_channels,
+                                                     kernel_size=3,
+                                                     stride=1,
+                                                     padding=1)
+            else:
+                self.nin_shortcut = torch.nn.Conv2d(in_channels,
+                                                    out_channels,
+                                                    kernel_size=1,
+                                                    stride=1,
+                                                    padding=0)
+
+    def forward(self, x, temb):
+        h = x
+        h = self.norm1(h)
+        h = nonlinearity(h)
+        h = self.conv1(h)
+
+        if temb is not None:
+            h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]
+
+        h = self.norm2(h)
+        h = nonlinearity(h)
+        h = self.dropout(h)
+        h = self.conv2(h)
+
+        if self.in_channels != self.out_channels:
+            if self.use_conv_shortcut:
+                x = self.conv_shortcut(x)
+            else:
+                x = self.nin_shortcut(x)
+
+        return x+h
+
+
+class MultiHeadAttnBlock(nn.Module):
+    def __init__(self, in_channels, head_size=1):
+        super().__init__()
+        self.in_channels = in_channels
+        self.head_size = head_size
+        self.att_size = in_channels // head_size
+        assert(in_channels % head_size == 0), 'The size of head should be divided by the number of channels.'
+
+        self.norm1 = Normalize(in_channels)
+        self.norm2 = Normalize(in_channels)
+
+        self.q = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.k = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.v = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.proj_out = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=1,
+                                        stride=1,
+                                        padding=0)
+        self.num = 0
+
+    def forward(self, x, y=None):
+        h_ = x
+        h_ = self.norm1(h_)
+        if y is None:
+            y = h_
+        else:
+            y = self.norm2(y)
+
+        q = self.q(y)
+        k = self.k(h_)
+        v = self.v(h_)
+
+        # compute attention
+        b,c,h,w = q.shape
+        q = q.reshape(b, self.head_size, self.att_size ,h*w) 
+        q = q.permute(0, 3, 1, 2) # b, hw, head, att
+
+        k = k.reshape(b, self.head_size, self.att_size ,h*w) 
+        k = k.permute(0, 3, 1, 2)
+
+        v = v.reshape(b, self.head_size, self.att_size ,h*w) 
+        v = v.permute(0, 3, 1, 2)
+
+
+        q = q.transpose(1, 2)
+        v = v.transpose(1, 2)
+        k = k.transpose(1, 2).transpose(2,3)
+
+        scale = int(self.att_size)**(-0.5)
+        q.mul_(scale)
+        w_ = torch.matmul(q, k)
+        w_ = F.softmax(w_, dim=3)
+
+        w_ = w_.matmul(v)
+
+        w_ = w_.transpose(1, 2).contiguous() # [b, h*w, head, att]
+        w_ = w_.view(b, h, w, -1)
+        w_ = w_.permute(0, 3, 1, 2)
+
+        w_ = self.proj_out(w_)
+
+        return x+w_
+
+
+class MultiHeadEncoder(nn.Module):
+    def __init__(self, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks=2,
+                 attn_resolutions=[16], dropout=0.0, resamp_with_conv=True, in_channels=3,
+                 resolution=512, z_channels=256, double_z=True, enable_mid=True,
+                 head_size=1, **ignore_kwargs):
+        super().__init__()
+        self.ch = ch
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+        self.enable_mid = enable_mid
+
+        # downsampling
+        self.conv_in = torch.nn.Conv2d(in_channels,
+                                       self.ch,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        curr_res = resolution
+        in_ch_mult = (1,)+tuple(ch_mult)
+        self.down = nn.ModuleList()
+        for i_level in range(self.num_resolutions):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_in = ch*in_ch_mult[i_level]
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(MultiHeadAttnBlock(block_in, head_size))
+            down = nn.Module()
+            down.block = block
+            down.attn = attn
+            if i_level != self.num_resolutions-1:
+                down.downsample = Downsample(block_in, resamp_with_conv)
+                curr_res = curr_res // 2
+            self.down.append(down)
+
+        # middle
+        if self.enable_mid:
+            self.mid = nn.Module()
+            self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+            self.mid.attn_1 = MultiHeadAttnBlock(block_in, head_size)
+            self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        2*z_channels if double_z else z_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+
+    def forward(self, x):
+        #assert x.shape[2] == x.shape[3] == self.resolution, "{}, {}, {}".format(x.shape[2], x.shape[3], self.resolution)
+
+        hs = {}
+        # timestep embedding
+        temb = None
+
+        # downsampling
+        h = self.conv_in(x)
+        hs['in'] = h
+        for i_level in range(self.num_resolutions):
+            for i_block in range(self.num_res_blocks):
+                h = self.down[i_level].block[i_block](h, temb)
+                if len(self.down[i_level].attn) > 0:
+                    h = self.down[i_level].attn[i_block](h)
+
+            if i_level != self.num_resolutions-1:
+                # hs.append(h)
+                hs['block_'+str(i_level)] = h
+                h = self.down[i_level].downsample(h)
+
+        # middle
+        # h = hs[-1]
+        if self.enable_mid:
+            h = self.mid.block_1(h, temb)
+            hs['block_'+str(i_level)+'_atten'] = h
+            h = self.mid.attn_1(h)
+            h = self.mid.block_2(h, temb)
+            hs['mid_atten'] = h
+
+        # end
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        # hs.append(h)
+        hs['out'] = h
+
+        return hs
+
+class MultiHeadDecoder(nn.Module):
+    def __init__(self, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks=2,
+                 attn_resolutions=16, dropout=0.0, resamp_with_conv=True, in_channels=3,
+                 resolution=512, z_channels=256, give_pre_end=False, enable_mid=True,
+                 head_size=1, **ignorekwargs):
+        super().__init__()
+        self.ch = ch
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+        self.give_pre_end = give_pre_end
+        self.enable_mid = enable_mid
+
+        # compute in_ch_mult, block_in and curr_res at lowest res
+        in_ch_mult = (1,)+tuple(ch_mult)
+        block_in = ch*ch_mult[self.num_resolutions-1]
+        curr_res = resolution // 2**(self.num_resolutions-1)
+        self.z_shape = (1,z_channels,curr_res,curr_res)
+        print("Working with z of shape {} = {} dimensions.".format(
+            self.z_shape, np.prod(self.z_shape)))
+
+        # z to block_in
+        self.conv_in = torch.nn.Conv2d(z_channels,
+                                       block_in,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        # middle
+        if self.enable_mid:
+            self.mid = nn.Module()
+            self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+            self.mid.attn_1 = MultiHeadAttnBlock(block_in, head_size)
+            self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+
+        # upsampling
+        self.up = nn.ModuleList()
+        for i_level in reversed(range(self.num_resolutions)):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks+1):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(MultiHeadAttnBlock(block_in, head_size))
+            up = nn.Module()
+            up.block = block
+            up.attn = attn
+            if i_level != 0:
+                up.upsample = Upsample(block_in, resamp_with_conv)
+                curr_res = curr_res * 2
+            self.up.insert(0, up) # prepend to get consistent order
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        out_ch,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, z):
+        #assert z.shape[1:] == self.z_shape[1:]
+        self.last_z_shape = z.shape
+
+        # timestep embedding
+        temb = None
+
+        # z to block_in
+        h = self.conv_in(z)
+
+        # middle
+        if self.enable_mid:
+            h = self.mid.block_1(h, temb)
+            h = self.mid.attn_1(h)
+            h = self.mid.block_2(h, temb)
+
+        # upsampling
+        for i_level in reversed(range(self.num_resolutions)):
+            for i_block in range(self.num_res_blocks+1):
+                h = self.up[i_level].block[i_block](h, temb)
+                if len(self.up[i_level].attn) > 0:
+                    h = self.up[i_level].attn[i_block](h)
+            if i_level != 0:
+                h = self.up[i_level].upsample(h)
+
+        # end
+        if self.give_pre_end:
+            return h
+
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        return h
+
+class MultiHeadDecoderTransformer(nn.Module):
+    def __init__(self, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks=2,
+                 attn_resolutions=16, dropout=0.0, resamp_with_conv=True, in_channels=3,
+                 resolution=512, z_channels=256, give_pre_end=False, enable_mid=True,
+                 head_size=1, **ignorekwargs):
+        super().__init__()
+        self.ch = ch
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+        self.give_pre_end = give_pre_end
+        self.enable_mid = enable_mid
+
+        # compute in_ch_mult, block_in and curr_res at lowest res
+        in_ch_mult = (1,)+tuple(ch_mult)
+        block_in = ch*ch_mult[self.num_resolutions-1]
+        curr_res = resolution // 2**(self.num_resolutions-1)
+        self.z_shape = (1,z_channels,curr_res,curr_res)
+        print("Working with z of shape {} = {} dimensions.".format(
+            self.z_shape, np.prod(self.z_shape)))
+
+        # z to block_in
+        self.conv_in = torch.nn.Conv2d(z_channels,
+                                       block_in,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        # middle
+        if self.enable_mid:
+            self.mid = nn.Module()
+            self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+            self.mid.attn_1 = MultiHeadAttnBlock(block_in, head_size)
+            self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                           out_channels=block_in,
+                                           temb_channels=self.temb_ch,
+                                           dropout=dropout)
+
+        # upsampling
+        self.up = nn.ModuleList()
+        for i_level in reversed(range(self.num_resolutions)):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks+1):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(MultiHeadAttnBlock(block_in, head_size))
+            up = nn.Module()
+            up.block = block
+            up.attn = attn
+            if i_level != 0:
+                up.upsample = Upsample(block_in, resamp_with_conv)
+                curr_res = curr_res * 2
+            self.up.insert(0, up) # prepend to get consistent order
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        out_ch,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, z, hs):
+        #assert z.shape[1:] == self.z_shape[1:]
+        # self.last_z_shape = z.shape
+
+        # timestep embedding
+        temb = None
+
+        # z to block_in
+        h = self.conv_in(z)
+
+        # middle
+        if self.enable_mid:
+            h = self.mid.block_1(h, temb)
+            h = self.mid.attn_1(h, hs['mid_atten'])
+            h = self.mid.block_2(h, temb)
+
+        # upsampling
+        for i_level in reversed(range(self.num_resolutions)):
+            for i_block in range(self.num_res_blocks+1):
+                h = self.up[i_level].block[i_block](h, temb)
+                if len(self.up[i_level].attn) > 0:
+                    if 'block_'+str(i_level)+'_atten' in hs:
+                        h = self.up[i_level].attn[i_block](h, hs['block_'+str(i_level)+'_atten'])
+                    else:
+                        h = self.up[i_level].attn[i_block](h, hs['block_'+str(i_level)])
+            if i_level != 0:
+                h = self.up[i_level].upsample(h)
+
+        # end
+        if self.give_pre_end:
+            return h
+
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        return h
+
+
+class VQVAEGAN(nn.Module):
+    def __init__(self, n_embed=1024, embed_dim=256, ch=128, out_ch=3, ch_mult=(1,2,4,8), 
+                 num_res_blocks=2, attn_resolutions=16, dropout=0.0, in_channels=3, 
+                 resolution=512, z_channels=256, double_z=False, enable_mid=True, 
+                 fix_decoder=False, fix_codebook=False, head_size=1, **ignore_kwargs):
+        super(VQVAEGAN, self).__init__()
+
+        self.encoder = MultiHeadEncoder(ch=ch, out_ch=out_ch, ch_mult=ch_mult, num_res_blocks=num_res_blocks,
+                               attn_resolutions=attn_resolutions, dropout=dropout, in_channels=in_channels,
+                               resolution=resolution, z_channels=z_channels, double_z=double_z, 
+                               enable_mid=enable_mid, head_size=head_size)
+        self.decoder = MultiHeadDecoder(ch=ch, out_ch=out_ch, ch_mult=ch_mult, num_res_blocks=num_res_blocks,
+                               attn_resolutions=attn_resolutions, dropout=dropout, in_channels=in_channels,
+                               resolution=resolution, z_channels=z_channels, enable_mid=enable_mid, head_size=head_size)
+
+        self.quantize = VectorQuantizer(n_embed, embed_dim, beta=0.25)
+
+        self.quant_conv = torch.nn.Conv2d(z_channels, embed_dim, 1)
+        self.post_quant_conv = torch.nn.Conv2d(embed_dim, z_channels, 1)
+
+        if fix_decoder:
+            for _, param in self.decoder.named_parameters():
+                param.requires_grad = False
+            for _, param in self.post_quant_conv.named_parameters():
+                param.requires_grad = False
+            for _, param in self.quantize.named_parameters():
+                param.requires_grad = False
+        elif fix_codebook:
+            for _, param in self.quantize.named_parameters():
+                param.requires_grad = False
+
+    def encode(self, x):
+
+        hs = self.encoder(x)
+        h = self.quant_conv(hs['out'])
+        quant, emb_loss, info = self.quantize(h)
+        return quant, emb_loss, info, hs
+
+    def decode(self, quant):
+        quant = self.post_quant_conv(quant)
+        dec = self.decoder(quant)
+
+        return dec
+
+    def forward(self, input):
+        quant, diff, info, hs = self.encode(input)
+        dec = self.decode(quant)
+
+        return dec, diff, info, hs
+
+class VQVAEGANMultiHeadTransformer(nn.Module):
+    def __init__(self,
+                 n_embed=1024,
+                 embed_dim=256,
+                 ch=64,
+                 out_ch=3,
+                 ch_mult=(1, 2, 2, 4, 4, 8),
+                 num_res_blocks=2,
+                 attn_resolutions=(16, ),
+                 dropout=0.0,
+                 in_channels=3,
+                 resolution=512,
+                 z_channels=256,
+                 double_z=False,
+                 enable_mid=True,
+                 fix_decoder=False,
+                 fix_codebook=True,
+                 fix_encoder=False,
+                 head_size=4,
+                 ex_multi_scale_num=1):
+        super(VQVAEGANMultiHeadTransformer, self).__init__()
+
+        self.encoder = MultiHeadEncoder(ch=ch, out_ch=out_ch, ch_mult=ch_mult, num_res_blocks=num_res_blocks,
+                               attn_resolutions=attn_resolutions, dropout=dropout, in_channels=in_channels,
+                               resolution=resolution, z_channels=z_channels, double_z=double_z, 
+                               enable_mid=enable_mid, head_size=head_size)
+        for i in range(ex_multi_scale_num):
+                attn_resolutions = [attn_resolutions[0], attn_resolutions[-1]*2]
+        self.decoder = MultiHeadDecoderTransformer(ch=ch, out_ch=out_ch, ch_mult=ch_mult, num_res_blocks=num_res_blocks,
+                               attn_resolutions=attn_resolutions, dropout=dropout, in_channels=in_channels,
+                               resolution=resolution, z_channels=z_channels, enable_mid=enable_mid, head_size=head_size)
+
+        self.quantize = VectorQuantizer(n_embed, embed_dim, beta=0.25)
+
+        self.quant_conv = torch.nn.Conv2d(z_channels, embed_dim, 1)
+        self.post_quant_conv = torch.nn.Conv2d(embed_dim, z_channels, 1)
+
+        if fix_decoder:
+            for _, param in self.decoder.named_parameters():
+                param.requires_grad = False
+            for _, param in self.post_quant_conv.named_parameters():
+                param.requires_grad = False
+            for _, param in self.quantize.named_parameters():
+                param.requires_grad = False
+        elif fix_codebook:
+            for _, param in self.quantize.named_parameters():
+                param.requires_grad = False
+
+        if fix_encoder:
+            for _, param in self.encoder.named_parameters():
+                param.requires_grad = False
+            for _, param in self.quant_conv.named_parameters():
+                param.requires_grad = False
+	    
+
+    def encode(self, x):
+        
+        hs = self.encoder(x)
+        h = self.quant_conv(hs['out'])
+        quant, emb_loss, info = self.quantize(h)
+        return quant, emb_loss, info, hs
+
+    def decode(self, quant, hs):
+        quant = self.post_quant_conv(quant)
+        dec = self.decoder(quant, hs)
+
+        return dec
+
+    def forward(self, input):
+        quant, diff, info, hs = self.encode(input)
+        dec = self.decode(quant, hs)
+
+        return dec, diff, info, hs

app.py

@@ -0,0 +1,132 @@
+import os
+
+import cv2
+import gradio as gr
+import torch
+from basicsr.archs.srvgg_arch import SRVGGNetCompact
+from realesrgan.utils import RealESRGANer
+
+from RestoreFormer import RestoreFormer
+
+os.system("pip freeze")
+# download weights
+if not os.path.exists('realesr-general-x4v3.pth'):
+    os.system("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P .")
+if not os.path.exists('RestoreFormer.ckpt'):
+    os.system("wget https://github.com/wzhouxiff/RestoreFormerPlusPlus/releases/download/v1.0.0/RestoreFormer.ckpt -P .")
+if not os.path.exists('RestoreFormer++.pth'):
+    os.system("wget https://github.com/wzhouxiff/RestoreFormerPlusPlus/releases/download/v1.0.0/RestoreFormer++.ckpt -P .")
+
+# torch.hub.download_url_to_file(
+#     'https://upload.wikimedia.org/wikipedia/commons/thumb/a/ab/Abraham_Lincoln_O-77_matte_collodion_print.jpg/1024px-Abraham_Lincoln_O-77_matte_collodion_print.jpg',
+#     'lincoln.jpg')
+# torch.hub.download_url_to_file(
+#     'https://user-images.githubusercontent.com/17445847/187400315-87a90ac9-d231-45d6-b377-38702bd1838f.jpg',
+#     'AI-generate.jpg')
+# torch.hub.download_url_to_file(
+#     'https://user-images.githubusercontent.com/17445847/187400981-8a58f7a4-ef61-42d9-af80-bc6234cef860.jpg',
+#     'Blake_Lively.jpg')
+# torch.hub.download_url_to_file(
+#     'https://user-images.githubusercontent.com/17445847/187401133-8a3bf269-5b4d-4432-b2f0-6d26ee1d3307.png',
+#     '10045.png')
+
+# background enhancer with RealESRGAN
+model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+model_path = 'realesr-general-x4v3.pth'
+half = True if torch.cuda.is_available() else False
+upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, tile_pad=10, pre_pad=0, half=half)
+
+os.makedirs('output', exist_ok=True)
+
+
+# def inference(img, version, scale, weight):
+def inference(img, version, scale):
+    # weight /= 100
+    print(img, version, scale)
+    if scale > 4:
+        scale = 4  # avoid too large scale value
+    try:
+        extension = os.path.splitext(os.path.basename(str(img)))[1]
+        img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
+        if len(img.shape) == 3 and img.shape[2] == 4:
+            img_mode = 'RGBA'
+        elif len(img.shape) == 2:  # for gray inputs
+            img_mode = None
+            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+        else:
+            img_mode = None
+
+        h, w = img.shape[0:2]
+        if h > 3500 or w > 3500:
+            print('too large size')
+            return None, None
+        
+        if h < 300:
+            img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
+
+        if version == 'RestoreFormer':
+            face_enhancer = RestoreFormer(
+            model_path='RestoreFormer.ckpt', upscale=2, arch='RestoreFormer', channel_multiplier=2, bg_upsampler=upsampler)
+        elif version == 'RestoreFormer++':
+            face_enhancer = RestoreFormer(
+            model_path='RestoreFormer++.ckpt', upscale=2, arch='RestoreFormer++', channel_multiplier=2, bg_upsampler=upsampler)
+
+        try:
+            # _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True, weight=weight)
+            _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
+        except RuntimeError as error:
+            print('Error', error)
+
+        try:
+            if scale != 2:
+                interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
+                h, w = img.shape[0:2]
+                output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
+        except Exception as error:
+            print('wrong scale input.', error)
+        if img_mode == 'RGBA':  # RGBA images should be saved in png format
+            extension = 'png'
+        else:
+            extension = 'jpg'
+        save_path = f'output/out.{extension}'
+        cv2.imwrite(save_path, output)
+
+        output = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
+        return output, save_path
+    except Exception as error:
+        print('global exception', error)
+        return None, None
+
+
+title = "RestoreFormer: Blind Face Restoration Algorithm"
+description = r"""Gradio demo for <a href='https://github.com/wzhouxiff/RestoreFormerPlusPlus' target='_blank'><b>RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Paris</b></a>.<br>
+It is used to restore your **old photos**.<br>
+To use it, simply upload your image.<br>
+"""
+article = r"""
+# [![download](https://img.shields.io/github/downloads/TencentARC/GFPGAN/total.svg)](https://github.com/TencentARC/GFPGAN/releases)
+# [![GitHub Stars](https://img.shields.io/github/stars/TencentARC/GFPGAN?style=social)](https://github.com/TencentARC/GFPGAN)
+[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/pdf/2308.07228.pdf)
+[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_RestoreFormer_High-Quality_Blind_Face_Restoration_From_Undegraded_Key-Value_Pairs_CVPR_2022_paper.pdf)
+If you have any question, please email 📧 `wzhoux@connect.hku.hk`.
+# <center><img src='https://visitor-badge.glitch.me/badge?page_id=akhaliq_GFPGAN' alt='visitor badge'></center>
+# <center><img src='https://visitor-badge.glitch.me/badge?page_id=Gradio_Xintao_GFPGAN' alt='visitor badge'></center>
+"""
+demo = gr.Interface(
+    inference, [
+        gr.Image(type="filepath", label="Input"),
+        gr.Radio(['RestoreFormer', 'RestoreFormer++'], type="value", value='RestoreFormer++', label='version'),
+        gr.Number(label="Rescaling factor", value=2),
+    ], [
+        gr.Image(type="numpy", label="Output (The whole image)"),
+        gr.File(label="Download the output image")
+    ],
+    title=title,
+    description=description,
+    article=article,
+    # examples=[['AI-generate.jpg', 'v1.4', 2, 50], ['lincoln.jpg', 'v1.4', 2, 50], ['Blake_Lively.jpg', 'v1.4', 2, 50],
+    #           ['10045.png', 'v1.4', 2, 50]]).launch()
+    # examples=[['AI-generate.jpg', 'v1.4', 2], ['lincoln.jpg', 'v1.4', 2], ['Blake_Lively.jpg', 'v1.4', 2],
+    #           ['10045.png', 'v1.4', 2]]
+    )
+demo.queue().launch(share=True)

packages.txt

@@ -0,0 +1,3 @@
+ffmpeg
+libsm6
+libxext6

requirements.txt

@@ -0,0 +1,12 @@
+torch>=1.7
+basicsr>=1.4.2
+facexlib>=0.2.5
+realesrgan>=0.2.5
+numpy
+opencv-python
+torchvision
+scipy
+tqdm
+lmdb
+pyyaml
+yapf