Spaces:
Runtime error
Runtime error
| # Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved. | |
| # | |
| # NVIDIA CORPORATION and its licensors retain all intellectual property | |
| # and proprietary rights in and to this software, related documentation | |
| # and any modifications thereto. Any use, reproduction, disclosure or | |
| # distribution of this software and related documentation without an express | |
| # license agreement from NVIDIA CORPORATION is strictly prohibited. | |
| import numpy as np | |
| from numpy.lib.type_check import imag | |
| import torch | |
| import torch.nn as nn | |
| from torch_utils import misc | |
| from torch_utils import persistence | |
| from torch_utils.ops import conv2d_resample | |
| from torch_utils.ops import upfirdn2d | |
| from torch_utils.ops import bias_act | |
| from torch_utils.ops import fma | |
| from icecream import ic | |
| import torch.nn.functional as F | |
| from training.ffc import FFCResnetBlock, ConcatTupleLayer | |
| import matplotlib.pyplot as plt | |
| import PIL | |
| #---------------------------------------------------------------------------- | |
| def normalize_2nd_moment(x, dim=1, eps=1e-8): | |
| return x * (x.square().mean(dim=dim, keepdim=True) + eps).rsqrt() | |
| def save_image_grid(feats, fname, gridsize): | |
| gw, gh = gridsize | |
| idx = gw * gh | |
| max_num = torch.max(feats[:idx]).item() | |
| min_num = torch.min(feats[:idx]).item() | |
| feats = feats[:idx].cpu() * 255 / (max_num - min_num) | |
| feats = np.asarray(feats, dtype=np.float32) | |
| feats = np.rint(feats).clip(0, 255).astype(np.uint8) | |
| C, H, W = feats.shape | |
| feats = feats.reshape(gh, gw, 1, H, W) | |
| feats = feats.transpose(0, 3, 1, 4, 2) | |
| feats = feats.reshape(gh * H, gw * W, 1) | |
| feats = np.stack([feats]*3, axis=2).squeeze() * 10 | |
| feats = np.rint(feats).clip(0, 255).astype(np.uint8) | |
| from icecream import ic | |
| ic(feats.shape) | |
| feats = PIL.Image.fromarray(feats) | |
| feats.save(fname + '.png') | |
| #---------------------------------------------------------------------------- | |
| def modulated_conv2d( | |
| x, # Input tensor of shape [batch_size, in_channels, in_height, in_width]. | |
| weight, # Weight tensor of shape [out_channels, in_channels, kernel_height, kernel_width]. | |
| styles, # Modulation coefficients of shape [batch_size, in_channels]. | |
| noise = None, # Optional noise tensor to add to the output activations. | |
| up = 1, # Integer upsampling factor. | |
| down = 1, # Integer downsampling factor. | |
| padding = 0, # Padding with respect to the upsampled image. | |
| resample_filter = None, # Low-pass filter to apply when resampling activations. Must be prepared beforehand by calling upfirdn2d.setup_filter(). | |
| demodulate = True, # Apply weight demodulation? | |
| flip_weight = True, # False = convolution, True = correlation (matches torch.nn.functional.conv2d). | |
| fused_modconv = True, # Perform modulation, convolution, and demodulation as a single fused operation? | |
| ): | |
| batch_size = x.shape[0] | |
| out_channels, in_channels, kh, kw = weight.shape | |
| misc.assert_shape(weight, [out_channels, in_channels, kh, kw]) # [OIkk] | |
| misc.assert_shape(x, [batch_size, in_channels, None, None]) # [NIHW] | |
| misc.assert_shape(styles, [batch_size, in_channels]) # [NI] | |
| # Pre-normalize inputs to avoid FP16 overflow. | |
| if x.dtype == torch.float16 and demodulate: | |
| weight = weight * (1 / np.sqrt(in_channels * kh * kw) / weight.norm(float('inf'), dim=[1,2,3], keepdim=True)) # max_Ikk | |
| styles = styles / styles.norm(float('inf'), dim=1, keepdim=True) # max_I | |
| # Calculate per-sample weights and demodulation coefficients. | |
| w = None | |
| dcoefs = None | |
| if demodulate or fused_modconv: | |
| w = weight.unsqueeze(0) # [NOIkk] | |
| w = w * styles.reshape(batch_size, 1, -1, 1, 1) # [NOIkk] | |
| if demodulate: | |
| dcoefs = (w.square().sum(dim=[2,3,4]) + 1e-8).rsqrt() # [NO] | |
| if demodulate and fused_modconv: | |
| w = w * dcoefs.reshape(batch_size, -1, 1, 1, 1) # [NOIkk] | |
| # Execute by scaling the activations before and after the convolution. | |
| if not fused_modconv: | |
| x = x * styles.to(x.dtype).reshape(batch_size, -1, 1, 1) | |
| x = conv2d_resample.conv2d_resample(x=x, w=weight.to(x.dtype), f=resample_filter, up=up, down=down, padding=padding, flip_weight=flip_weight) | |
| if demodulate and noise is not None: | |
| x = fma.fma(x, dcoefs.to(x.dtype).reshape(batch_size, -1, 1, 1), noise.to(x.dtype)) | |
| elif demodulate: | |
| x = x * dcoefs.to(x.dtype).reshape(batch_size, -1, 1, 1) | |
| elif noise is not None: | |
| x = x.add_(noise.to(x.dtype)) | |
| return x | |
| # Execute as one fused op using grouped convolution. | |
| with misc.suppress_tracer_warnings(): # this value will be treated as a constant | |
| batch_size = int(batch_size) | |
| misc.assert_shape(x, [batch_size, in_channels, None, None]) | |
| x = x.reshape(1, -1, *x.shape[2:]) | |
| w = w.reshape(-1, in_channels, kh, kw) | |
| x = conv2d_resample.conv2d_resample(x=x, w=w.to(x.dtype), f=resample_filter, up=up, down=down, padding=padding, groups=batch_size, flip_weight=flip_weight) | |
| x = x.reshape(batch_size, -1, *x.shape[2:]) | |
| if noise is not None: | |
| x = x.add_(noise) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class FullyConnectedLayer(torch.nn.Module): | |
| def __init__(self, | |
| in_features, # Number of input features. | |
| out_features, # Number of output features. | |
| bias = True, # Apply additive bias before the activation function? | |
| activation = 'linear', # Activation function: 'relu', 'lrelu', etc. | |
| lr_multiplier = 1, # Learning rate multiplier. | |
| bias_init = 0, # Initial value for the additive bias. | |
| ): | |
| super().__init__() | |
| self.activation = activation | |
| self.weight = torch.nn.Parameter(torch.randn([out_features, in_features]) / lr_multiplier) | |
| self.bias = torch.nn.Parameter(torch.full([out_features], np.float32(bias_init))) if bias else None | |
| self.weight_gain = lr_multiplier / np.sqrt(in_features) | |
| self.bias_gain = lr_multiplier | |
| def forward(self, x): | |
| w = self.weight.to(x.dtype) * self.weight_gain | |
| b = self.bias | |
| if b is not None: | |
| b = b.to(x.dtype) | |
| if self.bias_gain != 1: | |
| b = b * self.bias_gain | |
| if self.activation == 'linear' and b is not None: | |
| x = torch.addmm(b.unsqueeze(0), x, w.t()) | |
| else: | |
| x = x.matmul(w.t()) | |
| x = bias_act.bias_act(x, b, act=self.activation) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class Conv2dLayer(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels. | |
| out_channels, # Number of output channels. | |
| kernel_size, # Width and height of the convolution kernel. | |
| bias = True, # Apply additive bias before the activation function? | |
| activation = 'linear', # Activation function: 'relu', 'lrelu', etc. | |
| up = 1, # Integer upsampling factor. | |
| down = 1, # Integer downsampling factor. | |
| resample_filter = [1,3,3,1], # Low-pass filter to apply when resampling activations. | |
| conv_clamp = None, # Clamp the output to +-X, None = disable clamping. | |
| channels_last = False, # Expect the input to have memory_format=channels_last? | |
| trainable = True, # Update the weights of this layer during training? | |
| ): | |
| super().__init__() | |
| self.activation = activation | |
| self.up = up | |
| self.down = down | |
| self.conv_clamp = conv_clamp | |
| self.register_buffer('resample_filter', upfirdn2d.setup_filter(resample_filter)) | |
| self.padding = kernel_size // 2 | |
| self.weight_gain = 1 / np.sqrt(in_channels * (kernel_size ** 2)) | |
| self.act_gain = bias_act.activation_funcs[activation].def_gain | |
| memory_format = torch.channels_last if channels_last else torch.contiguous_format | |
| weight = torch.randn([out_channels, in_channels, kernel_size, kernel_size]).to(memory_format=memory_format) | |
| bias = torch.zeros([out_channels]) if bias else None | |
| if trainable: | |
| self.weight = torch.nn.Parameter(weight) | |
| self.bias = torch.nn.Parameter(bias) if bias is not None else None | |
| else: | |
| self.register_buffer('weight', weight) | |
| if bias is not None: | |
| self.register_buffer('bias', bias) | |
| else: | |
| self.bias = None | |
| def forward(self, x, gain=1): | |
| w = self.weight * self.weight_gain | |
| b = self.bias.to(x.dtype) if self.bias is not None else None | |
| flip_weight = (self.up == 1) # slightly faster | |
| x = conv2d_resample.conv2d_resample(x=x, w=w.to(x.dtype), f=self.resample_filter, up=self.up, down=self.down, padding=self.padding, flip_weight=flip_weight) | |
| act_gain = self.act_gain * gain | |
| act_clamp = self.conv_clamp * gain if self.conv_clamp is not None else None | |
| x = bias_act.bias_act(x, b, act=self.activation, gain=act_gain, clamp=act_clamp) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class FFCBlock(torch.nn.Module): | |
| def __init__(self, | |
| dim, # Number of output/input channels. | |
| kernel_size, # Width and height of the convolution kernel. | |
| padding, | |
| ratio_gin=0.75, | |
| ratio_gout=0.75, | |
| activation = 'linear', # Activation function: 'relu', 'lrelu', etc. | |
| ): | |
| super().__init__() | |
| if activation == 'linear': | |
| self.activation = nn.Identity | |
| else: | |
| self.activation = nn.ReLU | |
| self.padding = padding | |
| self.kernel_size = kernel_size | |
| self.ffc_block = FFCResnetBlock(dim=dim, | |
| padding_type='reflect', | |
| norm_layer=nn.SyncBatchNorm, | |
| activation_layer=self.activation, | |
| dilation=1, | |
| ratio_gin=ratio_gin, | |
| ratio_gout=ratio_gout) | |
| self.concat_layer = ConcatTupleLayer() | |
| def forward(self, gen_ft, mask, fname=None): | |
| x = gen_ft.float() | |
| # x = mask*enc_ft + (1-mask)*gen_ft | |
| x_l, x_g = x[:, :-self.ffc_block.conv1.ffc.global_in_num], x[:, -self.ffc_block.conv1.ffc.global_in_num:] | |
| id_l, id_g = x_l, x_g | |
| x_l, x_g = self.ffc_block((x_l, x_g), fname=fname) | |
| x_l, x_g = id_l + x_l, id_g + x_g | |
| x = self.concat_layer((x_l, x_g)) | |
| return x + gen_ft.float() | |
| #---------------------------------------------------------------------------- | |
| class EncoderEpilogue(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels. | |
| cmap_dim, # Dimensionality of mapped conditioning label, 0 = no label. | |
| z_dim, # Output Latent (Z) dimensionality. | |
| resolution, # Resolution of this block. | |
| img_channels, # Number of input color channels. | |
| architecture = 'resnet', # Architecture: 'orig', 'skip', 'resnet'. | |
| mbstd_group_size = 4, # Group size for the minibatch standard deviation layer, None = entire minibatch. | |
| mbstd_num_channels = 1, # Number of features for the minibatch standard deviation layer, 0 = disable. | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| ): | |
| assert architecture in ['orig', 'skip', 'resnet'] | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.cmap_dim = cmap_dim | |
| self.resolution = resolution | |
| self.img_channels = img_channels | |
| self.architecture = architecture | |
| if architecture == 'skip': | |
| self.fromrgb = Conv2dLayer(self.img_channels, in_channels, kernel_size=1, activation=activation) | |
| self.mbstd = MinibatchStdLayer(group_size=mbstd_group_size, num_channels=mbstd_num_channels) if mbstd_num_channels > 0 else None | |
| self.conv = Conv2dLayer(in_channels + mbstd_num_channels, in_channels, kernel_size=3, activation=activation, conv_clamp=conv_clamp) | |
| self.fc = FullyConnectedLayer(in_channels * (resolution ** 2), z_dim, activation=activation) | |
| # self.out = FullyConnectedLayer(in_channels, z_dim) | |
| self.dropout = torch.nn.Dropout(p=0.5) | |
| def forward(self, x, cmap, force_fp32=False): | |
| misc.assert_shape(x, [None, self.in_channels, self.resolution, self.resolution]) # [NCHW] | |
| _ = force_fp32 # unused | |
| dtype = torch.float32 | |
| memory_format = torch.contiguous_format | |
| # FromRGB. | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| # Main layers. | |
| if self.mbstd is not None: | |
| x = self.mbstd(x) | |
| const_e = self.conv(x) | |
| x = self.fc(const_e.flatten(1)) | |
| # x = self.out(x) | |
| x = self.dropout(x) | |
| # Conditioning. | |
| if self.cmap_dim > 0: | |
| misc.assert_shape(cmap, [None, self.cmap_dim]) | |
| x = (x * cmap).sum(dim=1, keepdim=True) * (1 / np.sqrt(self.cmap_dim)) | |
| assert x.dtype == dtype | |
| return x, const_e | |
| #---------------------------------------------------------------------------- | |
| class EncoderBlock(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels, 0 = first block. | |
| tmp_channels, # Number of intermediate channels. | |
| out_channels, # Number of output channels. | |
| resolution, # Resolution of this block. | |
| img_channels, # Number of input color channels. | |
| first_layer_idx, # Index of the first layer. | |
| architecture = 'skip', # Architecture: 'orig', 'skip', 'resnet'. | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| resample_filter = [1,3,3,1], # Low-pass filter to apply when resampling activations. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| use_fp16 = False, # Use FP16 for this block? | |
| fp16_channels_last = False, # Use channels-last memory format with FP16? | |
| freeze_layers = 0, # Freeze-D: Number of layers to freeze. | |
| ): | |
| assert in_channels in [0, tmp_channels] | |
| assert architecture in ['orig', 'skip', 'resnet'] | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.resolution = resolution | |
| self.img_channels = img_channels + 1 | |
| self.first_layer_idx = first_layer_idx | |
| self.architecture = architecture | |
| self.use_fp16 = use_fp16 | |
| self.channels_last = (use_fp16 and fp16_channels_last) | |
| self.register_buffer('resample_filter', upfirdn2d.setup_filter(resample_filter)) | |
| self.num_layers = 0 | |
| def trainable_gen(): | |
| while True: | |
| layer_idx = self.first_layer_idx + self.num_layers | |
| trainable = (layer_idx >= freeze_layers) | |
| self.num_layers += 1 | |
| yield trainable | |
| trainable_iter = trainable_gen() | |
| if in_channels == 0: | |
| self.fromrgb = Conv2dLayer(self.img_channels, tmp_channels, kernel_size=1, activation=activation, | |
| trainable=next(trainable_iter), conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| self.conv0 = Conv2dLayer(tmp_channels, tmp_channels, kernel_size=3, activation=activation, | |
| trainable=next(trainable_iter), conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| self.conv1 = Conv2dLayer(tmp_channels, out_channels, kernel_size=3, activation=activation, down=2, | |
| trainable=next(trainable_iter), resample_filter=resample_filter, conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| if architecture == 'resnet': | |
| self.skip = Conv2dLayer(tmp_channels, out_channels, kernel_size=1, bias=False, down=2, | |
| trainable=next(trainable_iter), resample_filter=resample_filter, channels_last=self.channels_last) | |
| def forward(self, x, img, force_fp32=False): | |
| dtype = torch.float16 if self.use_fp16 and not force_fp32 else torch.float32 | |
| memory_format = torch.channels_last if self.channels_last and not force_fp32 else torch.contiguous_format | |
| # Input. | |
| if x is not None: | |
| misc.assert_shape(x, [None, self.in_channels, self.resolution, self.resolution]) | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| # FromRGB. | |
| if self.in_channels == 0: | |
| misc.assert_shape(img, [None, self.img_channels, self.resolution, self.resolution]) | |
| img = img.to(dtype=dtype, memory_format=memory_format) | |
| y = self.fromrgb(img) | |
| x = x + y if x is not None else y | |
| img = upfirdn2d.downsample2d(img, self.resample_filter) if self.architecture == 'skip' else None | |
| # Main layers. | |
| if self.architecture == 'resnet': | |
| y = self.skip(x, gain=np.sqrt(0.5)) | |
| x = self.conv0(x) | |
| feat = x.clone() | |
| x = self.conv1(x, gain=np.sqrt(0.5)) | |
| x = y.add_(x) | |
| else: | |
| x = self.conv0(x) | |
| feat = x.clone() | |
| x = self.conv1(x) | |
| assert x.dtype == dtype | |
| return x, img, feat | |
| #---------------------------------------------------------------------------- | |
| class SynthesisLayer(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels. | |
| out_channels, # Number of output channels. | |
| w_dim, # Intermediate latent (W) dimensionality. | |
| resolution, # Resolution of this layer. | |
| kernel_size = 3, # Convolution kernel size. | |
| up = 1, # Integer upsampling factor. | |
| use_noise = True, # Enable noise input? | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| resample_filter = [1,3,3,1], # Low-pass filter to apply when resampling activations. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| channels_last = False, # Use channels_last format for the weights? | |
| ): | |
| super().__init__() | |
| self.resolution = resolution | |
| self.up = up | |
| self.use_noise = use_noise | |
| self.activation = activation | |
| self.conv_clamp = conv_clamp | |
| self.register_buffer('resample_filter', upfirdn2d.setup_filter(resample_filter)) | |
| self.padding = kernel_size // 2 | |
| self.act_gain = bias_act.activation_funcs[activation].def_gain | |
| self.affine = FullyConnectedLayer(w_dim, in_channels, bias_init=1) | |
| memory_format = torch.channels_last if channels_last else torch.contiguous_format | |
| self.weight = torch.nn.Parameter(torch.randn([out_channels, in_channels, kernel_size, kernel_size]).to(memory_format=memory_format)) | |
| if use_noise: | |
| self.register_buffer('noise_const', torch.randn([resolution, resolution])) | |
| self.noise_strength = torch.nn.Parameter(torch.zeros([])) | |
| self.bias = torch.nn.Parameter(torch.zeros([out_channels])) | |
| def forward(self, x, w, noise_mode='random', fused_modconv=True, gain=1): | |
| assert noise_mode in ['random', 'const', 'none'] | |
| in_resolution = self.resolution // self.up | |
| misc.assert_shape(x, [None, self.weight.shape[1], in_resolution, in_resolution]) | |
| styles = self.affine(w) | |
| noise = None | |
| if self.use_noise and noise_mode == 'random': | |
| noise = torch.randn([x.shape[0], 1, self.resolution, self.resolution], device=x.device) * self.noise_strength | |
| if self.use_noise and noise_mode == 'const': | |
| noise = self.noise_const * self.noise_strength | |
| flip_weight = (self.up == 1) # slightly faster | |
| x = modulated_conv2d(x=x, weight=self.weight, styles=styles, noise=noise, up=self.up, | |
| padding=self.padding, resample_filter=self.resample_filter, flip_weight=flip_weight, fused_modconv=fused_modconv) | |
| act_gain = self.act_gain * gain | |
| act_clamp = self.conv_clamp * gain if self.conv_clamp is not None else None | |
| x = F.leaky_relu(x, negative_slope=0.2, inplace=False) | |
| if act_gain != 1: | |
| x = x * act_gain | |
| if act_clamp is not None: | |
| x = x.clamp(-act_clamp, act_clamp) | |
| # x = bias_act.bias_act(x.clone(), self.bias.to(x.dtype), act=self.activation, gain=act_gain, clamp=act_clamp) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class FFCSkipLayer(torch.nn.Module): | |
| def __init__(self, | |
| dim, # Number of input/output channels. | |
| kernel_size = 3, # Convolution kernel size. | |
| ratio_gin=0.75, | |
| ratio_gout=0.75, | |
| ): | |
| super().__init__() | |
| self.padding = kernel_size // 2 | |
| self.ffc_act = FFCBlock(dim=dim, kernel_size=kernel_size, activation=nn.ReLU, | |
| padding=self.padding, ratio_gin=ratio_gin, ratio_gout=ratio_gout) | |
| def forward(self, gen_ft, mask, fname=None): | |
| x = self.ffc_act(gen_ft, mask, fname=fname) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class ToRGBLayer(torch.nn.Module): | |
| def __init__(self, in_channels, out_channels, w_dim, kernel_size=1, conv_clamp=None, channels_last=False): | |
| super().__init__() | |
| self.conv_clamp = conv_clamp | |
| self.affine = FullyConnectedLayer(w_dim, in_channels, bias_init=1) | |
| memory_format = torch.channels_last if channels_last else torch.contiguous_format | |
| self.weight = torch.nn.Parameter(torch.randn([out_channels, in_channels, kernel_size, kernel_size]).to(memory_format=memory_format)) | |
| self.bias = torch.nn.Parameter(torch.zeros([out_channels])) | |
| self.weight_gain = 1 / np.sqrt(in_channels * (kernel_size ** 2)) | |
| def forward(self, x, w, fused_modconv=True): | |
| styles = self.affine(w) * self.weight_gain | |
| x = modulated_conv2d(x=x, weight=self.weight, styles=styles, demodulate=False, fused_modconv=fused_modconv) | |
| x = bias_act.bias_act(x, self.bias.to(x.dtype), clamp=self.conv_clamp) | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class SynthesisBlock(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels, 0 = first block. | |
| out_channels, # Number of output channels. | |
| w_dim, # Intermediate latent (W) dimensionality. | |
| resolution, # Resolution of this block. | |
| img_channels, # Number of output color channels. | |
| is_last, # Is this the last block? | |
| architecture = 'skip', # Architecture: 'orig', 'skip', 'resnet'. | |
| resample_filter = [1,3,3,1], # Low-pass filter to apply when resampling activations. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| use_fp16 = False, # Use FP16 for this block? | |
| fp16_channels_last = False, # Use channels-last memory format with FP16? | |
| **layer_kwargs, # Arguments for SynthesisLayer. | |
| ): | |
| assert architecture in ['orig', 'skip', 'resnet'] | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.w_dim = w_dim | |
| self.resolution = resolution | |
| self.img_channels = img_channels | |
| self.is_last = is_last | |
| self.architecture = architecture | |
| self.use_fp16 = use_fp16 | |
| self.channels_last = (use_fp16 and fp16_channels_last) | |
| self.register_buffer('resample_filter', upfirdn2d.setup_filter(resample_filter)) | |
| self.num_conv = 0 | |
| self.num_torgb = 0 | |
| self.res_ffc = {4:0, 8: 0, 16: 0, 32: 1, 64: 1, 128: 1, 256: 1, 512: 1} | |
| if in_channels != 0 and resolution >= 8: | |
| self.ffc_skip = nn.ModuleList() | |
| for _ in range(self.res_ffc[resolution]): | |
| self.ffc_skip.append(FFCSkipLayer(dim=out_channels)) | |
| if in_channels == 0: | |
| self.const = torch.nn.Parameter(torch.randn([out_channels, resolution, resolution])) | |
| if in_channels != 0: | |
| self.conv0 = SynthesisLayer(in_channels, out_channels, w_dim=w_dim*3, resolution=resolution, up=2, | |
| resample_filter=resample_filter, conv_clamp=conv_clamp, channels_last=self.channels_last, **layer_kwargs) | |
| self.num_conv += 1 | |
| self.conv1 = SynthesisLayer(out_channels, out_channels, w_dim=w_dim*3, resolution=resolution, | |
| conv_clamp=conv_clamp, channels_last=self.channels_last, **layer_kwargs) | |
| self.num_conv += 1 | |
| if is_last or architecture == 'skip': | |
| self.torgb = ToRGBLayer(out_channels, img_channels, w_dim=w_dim*3, | |
| conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| self.num_torgb += 1 | |
| if in_channels != 0 and architecture == 'resnet': | |
| self.skip = Conv2dLayer(in_channels, out_channels, kernel_size=1, bias=False, up=2, | |
| resample_filter=resample_filter, channels_last=self.channels_last) | |
| def forward(self, x, mask, feats, img, ws, fname=None, force_fp32=False, fused_modconv=None, **layer_kwargs): | |
| # misc.assert_shape(ws, [None, self.num_conv + self.num_torgb, self.w_dim]) | |
| # w_iter = iter(ws.unbind(dim=1)) | |
| dtype = torch.float16 if self.use_fp16 and not force_fp32 else torch.float32 | |
| memory_format = torch.channels_last if self.channels_last and not force_fp32 else torch.contiguous_format | |
| if fused_modconv is None: | |
| with misc.suppress_tracer_warnings(): # this value will be treated as a constant | |
| fused_modconv = (not self.training) and (dtype == torch.float32 or int(x.shape[0]) == 1) | |
| # # Input. | |
| # if self.in_channels == 0: | |
| # ic(self.const.shape) | |
| # x = self.const.to(dtype=dtype, memory_format=memory_format) | |
| # x = x.unsqueeze(0).repeat([ws.shape[0], 1, 1, 1]) | |
| # ic(x.shape) | |
| # else: | |
| # misc.assert_shape(x, [None, self.in_channels, self.resolution // 2, self.resolution // 2]) | |
| # x = x.to(dtype=dtype, memory_format=memory_format) | |
| # ic(x.shape, 'ELSE') | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| x_skip = feats[self.resolution].clone().to(dtype=dtype, memory_format=memory_format) | |
| # Main layers. | |
| if self.in_channels == 0: | |
| x = self.conv1(x, ws[1], fused_modconv=fused_modconv, **layer_kwargs) | |
| elif self.architecture == 'resnet': | |
| y = self.skip(x, gain=np.sqrt(0.5)) | |
| x = self.conv0(x, ws[0].clone(), fused_modconv=fused_modconv, **layer_kwargs) | |
| if len(self.ffc_skip) > 0: | |
| mask = F.interpolate(mask, size=x_skip.shape[2:],) | |
| z = x + x_skip | |
| for fres in self.ffc_skip: | |
| z = fres(z, mask) | |
| x = x + z | |
| else: | |
| x = x + x_skip | |
| x = self.conv1(x, ws[1].clone(), fused_modconv=fused_modconv, gain=np.sqrt(0.5), **layer_kwargs) | |
| x = y.add_(x) | |
| else: | |
| x = self.conv0(x, ws[0].clone(), fused_modconv=fused_modconv, **layer_kwargs) | |
| if len(self.ffc_skip) > 0: | |
| # for i in range(x.shape[0]): | |
| # c, h, w = x[i].shape | |
| # gh = 3 | |
| # gw = 3 | |
| # save_image_grid(x[i].detach(), f'vis/{fname}_pre_{h}', (gh, gw)) | |
| mask = F.interpolate(mask, size=x_skip.shape[2:],) | |
| z = x + x_skip | |
| for fres in self.ffc_skip: | |
| z = fres(z, mask) | |
| # for i in range(z.shape[0]): | |
| # c, h, w = z[i].shape | |
| # gh = 3 | |
| # gw = 3 | |
| # save_image_grid(z[i].detach(), f'vis/{fname}_ffc_{h}', (gh, gw)) | |
| x = x + z | |
| # for i in range(x.shape[0]): | |
| # c, h, w = x[i].shape | |
| # gh = 3 | |
| # gw = 3 | |
| # save_image_grid(x[i].detach(), f'vis/{fname}_post_{h}', (gh, gw)) | |
| else: | |
| x = x + x_skip | |
| x = self.conv1(x, ws[1].clone(), fused_modconv=fused_modconv, **layer_kwargs) | |
| # ToRGB. | |
| if img is not None: | |
| misc.assert_shape(img, [None, self.img_channels, self.resolution // 2, self.resolution // 2]) | |
| img = upfirdn2d.upsample2d(img, self.resample_filter) | |
| if self.is_last or self.architecture == 'skip': | |
| y = self.torgb(x, ws[2].clone(), fused_modconv=fused_modconv) | |
| y = y.to(dtype=torch.float32, memory_format=torch.contiguous_format) | |
| img = img.add_(y) if img is not None else y | |
| x = x.to(dtype=dtype) | |
| assert x.dtype == dtype | |
| assert img is None or img.dtype == torch.float32 | |
| return x, img | |
| #---------------------------------------------------------------------------- | |
| class SynthesisForeword(torch.nn.Module): | |
| def __init__(self, | |
| z_dim, # Output Latent (Z) dimensionality. | |
| resolution, # Resolution of this block. | |
| in_channels, | |
| img_channels, # Number of input color channels. | |
| architecture = 'skip', # Architecture: 'orig', 'skip', 'resnet'. | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| ): | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.z_dim = z_dim | |
| self.resolution = resolution | |
| self.img_channels = img_channels | |
| self.architecture = architecture | |
| self.fc = FullyConnectedLayer(self.z_dim, (self.z_dim // 2) * 4 * 4, activation=activation) | |
| self.conv = SynthesisLayer(self.in_channels, self.in_channels, w_dim=(z_dim // 2) * 3, resolution=4) | |
| if architecture == 'skip': | |
| self.torgb = ToRGBLayer(self.in_channels, self.img_channels, kernel_size=1, w_dim = (z_dim // 2) * 3) | |
| def forward(self, x, ws, feats, img, force_fp32=False): | |
| misc.assert_shape(x, [None, self.z_dim]) # [NC] | |
| _ = force_fp32 # unused | |
| dtype = torch.float32 | |
| memory_format = torch.contiguous_format | |
| x_global = x.clone() | |
| # ToRGB. | |
| x = self.fc(x) | |
| x = x.view(-1, self.z_dim // 2, 4, 4) | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| # Main layers. | |
| x_skip = feats[4].clone() | |
| x = x + x_skip | |
| mod_vector = [] | |
| mod_vector.append(ws[:, 0]) | |
| mod_vector.append(x_global.clone()) | |
| mod_vector = torch.cat(mod_vector, dim = 1) | |
| x = self.conv(x, mod_vector) | |
| mod_vector = [] | |
| mod_vector.append(ws[:, 2*2-3]) | |
| mod_vector.append(x_global.clone()) | |
| mod_vector = torch.cat(mod_vector, dim = 1) | |
| if self.architecture == 'skip': | |
| img = self.torgb(x, mod_vector) | |
| img = img.to(dtype=torch.float32, memory_format=torch.contiguous_format) | |
| assert x.dtype == dtype | |
| return x, img | |
| #---------------------------------------------------------------------------- | |
| class DiscriminatorBlock(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels, 0 = first block. | |
| tmp_channels, # Number of intermediate channels. | |
| out_channels, # Number of output channels. | |
| resolution, # Resolution of this block. | |
| img_channels, # Number of input color channels. | |
| first_layer_idx, # Index of the first layer. | |
| architecture = 'resnet', # Architecture: 'orig', 'skip', 'resnet'. | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| resample_filter = [1,3,3,1], # Low-pass filter to apply when resampling activations. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| use_fp16 = False, # Use FP16 for this block? | |
| fp16_channels_last = False, # Use channels-last memory format with FP16? | |
| freeze_layers = 0, # Freeze-D: Number of layers to freeze. | |
| ): | |
| assert in_channels in [0, tmp_channels] | |
| assert architecture in ['orig', 'skip', 'resnet'] | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.resolution = resolution | |
| self.img_channels = img_channels + 1 | |
| self.first_layer_idx = first_layer_idx | |
| self.architecture = architecture | |
| self.use_fp16 = use_fp16 | |
| self.channels_last = (use_fp16 and fp16_channels_last) | |
| self.register_buffer('resample_filter', upfirdn2d.setup_filter(resample_filter)) | |
| self.num_layers = 0 | |
| def trainable_gen(): | |
| while True: | |
| layer_idx = self.first_layer_idx + self.num_layers | |
| trainable = (layer_idx >= freeze_layers) | |
| self.num_layers += 1 | |
| yield trainable | |
| trainable_iter = trainable_gen() | |
| if in_channels == 0 or architecture == 'skip': | |
| self.fromrgb = Conv2dLayer(self.img_channels, tmp_channels, kernel_size=1, activation=activation, | |
| trainable=next(trainable_iter), conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| self.conv0 = Conv2dLayer(tmp_channels, tmp_channels, kernel_size=3, activation=activation, | |
| trainable=next(trainable_iter), conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| self.conv1 = Conv2dLayer(tmp_channels, out_channels, kernel_size=3, activation=activation, down=2, | |
| trainable=next(trainable_iter), resample_filter=resample_filter, conv_clamp=conv_clamp, channels_last=self.channels_last) | |
| if architecture == 'resnet': | |
| self.skip = Conv2dLayer(tmp_channels, out_channels, kernel_size=1, bias=False, down=2, | |
| trainable=next(trainable_iter), resample_filter=resample_filter, channels_last=self.channels_last) | |
| def forward(self, x, img, force_fp32=False): | |
| dtype = torch.float16 if self.use_fp16 and not force_fp32 else torch.float32 | |
| memory_format = torch.channels_last if self.channels_last and not force_fp32 else torch.contiguous_format | |
| # Input. | |
| if x is not None: | |
| misc.assert_shape(x, [None, self.in_channels, self.resolution, self.resolution]) | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| # FromRGB. | |
| if self.in_channels == 0 or self.architecture == 'skip': | |
| misc.assert_shape(img, [None, self.img_channels, self.resolution, self.resolution]) | |
| img = img.to(dtype=dtype, memory_format=memory_format) | |
| y = self.fromrgb(img) | |
| x = x + y if x is not None else y | |
| img = upfirdn2d.downsample2d(img, self.resample_filter) if self.architecture == 'skip' else None | |
| # Main layers. | |
| if self.architecture == 'resnet': | |
| y = self.skip(x, gain=np.sqrt(0.5)) | |
| x = self.conv0(x) | |
| x = self.conv1(x, gain=np.sqrt(0.5)) | |
| x = y.add_(x) | |
| else: | |
| x = self.conv0(x) | |
| x = self.conv1(x) | |
| assert x.dtype == dtype | |
| return x, img | |
| #---------------------------------------------------------------------------- | |
| class MinibatchStdLayer(torch.nn.Module): | |
| def __init__(self, group_size, num_channels=1): | |
| super().__init__() | |
| self.group_size = group_size | |
| self.num_channels = num_channels | |
| def forward(self, x): | |
| N, C, H, W = x.shape | |
| with misc.suppress_tracer_warnings(): # as_tensor results are registered as constants | |
| G = torch.min(torch.as_tensor(self.group_size), torch.as_tensor(N)) if self.group_size is not None else N | |
| F = self.num_channels | |
| c = C // F | |
| y = x.reshape(G, -1, F, c, H, W) # [GnFcHW] Split minibatch N into n groups of size G, and channels C into F groups of size c. | |
| y = y - y.mean(dim=0) # [GnFcHW] Subtract mean over group. | |
| y = y.square().mean(dim=0) # [nFcHW] Calc variance over group. | |
| y = (y + 1e-8).sqrt() # [nFcHW] Calc stddev over group. | |
| y = y.mean(dim=[2,3,4]) # [nF] Take average over channels and pixels. | |
| y = y.reshape(-1, F, 1, 1) # [nF11] Add missing dimensions. | |
| y = y.repeat(G, 1, H, W) # [NFHW] Replicate over group and pixels. | |
| x = torch.cat([x, y], dim=1) # [NCHW] Append to input as new channels. | |
| return x | |
| #---------------------------------------------------------------------------- | |
| class DiscriminatorEpilogue(torch.nn.Module): | |
| def __init__(self, | |
| in_channels, # Number of input channels. | |
| cmap_dim, # Dimensionality of mapped conditioning label, 0 = no label. | |
| resolution, # Resolution of this block. | |
| img_channels, # Number of input color channels. | |
| architecture = 'resnet', # Architecture: 'orig', 'skip', 'resnet'. | |
| mbstd_group_size = 4, # Group size for the minibatch standard deviation layer, None = entire minibatch. | |
| mbstd_num_channels = 1, # Number of features for the minibatch standard deviation layer, 0 = disable. | |
| activation = 'lrelu', # Activation function: 'relu', 'lrelu', etc. | |
| conv_clamp = None, # Clamp the output of convolution layers to +-X, None = disable clamping. | |
| ): | |
| assert architecture in ['orig', 'skip', 'resnet'] | |
| super().__init__() | |
| self.in_channels = in_channels | |
| self.cmap_dim = cmap_dim | |
| self.resolution = resolution | |
| self.img_channels = img_channels | |
| self.architecture = architecture | |
| if architecture == 'skip': | |
| self.fromrgb = Conv2dLayer(img_channels, in_channels, kernel_size=1, activation=activation) | |
| self.mbstd = MinibatchStdLayer(group_size=mbstd_group_size, num_channels=mbstd_num_channels) if mbstd_num_channels > 0 else None | |
| self.conv = Conv2dLayer(in_channels + mbstd_num_channels, in_channels, kernel_size=3, activation=activation, conv_clamp=conv_clamp) | |
| self.fc = FullyConnectedLayer(in_channels * (resolution ** 2), in_channels, activation=activation) | |
| self.out = FullyConnectedLayer(in_channels, 1 if cmap_dim == 0 else cmap_dim) | |
| def forward(self, x, img, cmap, force_fp32=False): | |
| misc.assert_shape(x, [None, self.in_channels, self.resolution, self.resolution]) # [NCHW] | |
| _ = force_fp32 # unused | |
| dtype = torch.float32 | |
| memory_format = torch.contiguous_format | |
| # FromRGB. | |
| x = x.to(dtype=dtype, memory_format=memory_format) | |
| if self.architecture == 'skip': | |
| misc.assert_shape(img, [None, self.img_channels, self.resolution, self.resolution]) | |
| img = img.to(dtype=dtype, memory_format=memory_format) | |
| x = x + self.fromrgb(img) | |
| # Main layers. | |
| if self.mbstd is not None: | |
| x = self.mbstd(x) | |
| x = self.conv(x) | |
| x = self.fc(x.flatten(1)) | |
| x = self.out(x) | |
| # Conditioning. | |
| if self.cmap_dim > 0: | |
| misc.assert_shape(cmap, [None, self.cmap_dim]) | |
| x = (x * cmap).sum(dim=1, keepdim=True) * (1 / np.sqrt(self.cmap_dim)) | |
| assert x.dtype == dtype | |
| return x | |
| #---------------------------------------------------------------------------- |