From 52e461ca47b94ade469a0a7ef6a1021664c0ef93 Mon Sep 17 00:00:00 2001 From: Hunor Laczko Date: Mon, 22 May 2023 00:13:39 +0200 Subject: [PATCH] pyramid pipeline ready --- configs/pyr_32.py | 296 +++++++++++++++ models/pyramid_level.py | 240 ++++++------ models/pyramid_model.py | 246 +++++++++++++ models/pyramid_model_optimized.py | 365 ------------------- scripts/cvae_pyramid.py | 581 ++++++++++++++---------------- utils/postprocess.py | 3 +- 6 files changed, 938 insertions(+), 793 deletions(-) create mode 100644 configs/pyr_32.py create mode 100644 models/pyramid_model.py delete mode 100644 models/pyramid_model_optimized.py diff --git a/configs/pyr_32.py b/configs/pyr_32.py new file mode 100644 index 0000000..462fec2 --- /dev/null +++ b/configs/pyr_32.py @@ -0,0 +1,296 @@ +from utils.convnext_utils import CNBlockConfig + +config = dict() + +config['gpu'] = '5' +config['name'] = 'pyr_torch_32' +config['notes'] = '' +config['tags'] = ['pyr', 'iccv', 'torch'] +config['script'] = 'scripts/cvae_pyramid.py' + +config['batch_size'] = 4 +config['is_skirt'] = False +config['is_cape'] = False +config['device'] = 'cuda' + + +config['use_skinning'] = True # and deshaping +config['remove_global_orientation'] = True +config['use_extra_losses'] = True # edge, collision, 3d mesh +config['use_offsets'] = False +config['use_norm_loss'] = True +config['use_curvature'] = True + +config['pretrained_model'] = '' +config['pretrained_model_iteration'] = '' + +config['pyramid'] = dict() +config['pyramid']['resolutions'] = [32] +config['pyramid']['pretrained_pyramid'] = '' +config['pyramid']['pretrained_pyramid_iteration'] = '' +config['pyramid']['final_upscale_enhancer'] = '' + +config['train_dir'] = '/data-local/127/train' +config['valid_dir'] = '/data-local/127/valid' +config['test_dir'] = '/data-net/dataset/test_ready' +config['train_frames'] = None +config['valid_frames'] = None + +config['dataset_in_memory'] = False +config['resolution'] = None + +config['smpl_res'] = 14475 +if config['is_cape']: + config['smpl_res'] = 3638 + +config['lr'] = 0.0001 +config['starting_balancing_coeff'] = 0.001 +config['balancing_activation_limit'] = 0.015 +config['reg_loss_coeff'] = 0.1 # set to 0 if don't want to use edge+collision +config['avg_garment_path'] = '' +config['bottleneck_scale'] = 2 + +config['signature']: set = { 'id', + 'frame_nr', + 'pose_shape', + 'uv_body_posed', + 'mesh_body_posed', + 'mesh_posed', + 'mesh_unposed', + 'uv_unposed', + 'uv_curvature', + 'uv_static', + 'mesh_mask', + 'uv_mask', + } + +config['pyramid']['is_label'] = False +# config['pyramid']['add_noise'] = False +# config['pyramid']['noise_amount'] = 0.0 + +config['pyramid']['loss_weights'] = [1,1,1,1,1] + +for res in config['pyramid']['resolutions']: + if res != 512: + res_modifier = '_' + str(res) + config['signature'].add('uv_body_posed' + res_modifier) + config['signature'].add('uv_unposed' + res_modifier) + config['signature'].add('uv_curvature' + res_modifier) + config['signature'].add('uv_static' + res_modifier) + config['signature'].add('uv_mask' + res_modifier) + + +config['static_model'] = 'checkpoints/iccv/static_torch_orig_2' +config['body_model'] = 'checkpoints/iccv/body_torch_1' +config['curvature_model'] = 'checkpoints/iccv/curv_torch_1' +config['freeze_encoders'] = True + + +config['pyramid']['levels'] = [] +for res in config['pyramid']['resolutions']: + if res == 512: + level = dict() + level['resolution'] = 512 + level['bottleneck_size'] = 64 * config['bottleneck_scale'] + level['kernel_size'] = 7 + level['upscale_enhancer'] = '' + level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3 + + block_setting = [ + CNBlockConfig(16, 32, 3), + CNBlockConfig(32, 64, 3), + CNBlockConfig(64, 128, 3), + CNBlockConfig(128, level['bottleneck_size'], 9), + CNBlockConfig(level['bottleneck_size'], None, 3), + ] + + block_setting_reverse = [ + CNBlockConfig(level['bottleneck_size'] * 2, 128, 3), + CNBlockConfig(128, 64, 9), + CNBlockConfig(64, 32, 3), + CNBlockConfig(32, 16, 3), + CNBlockConfig(16, 3, 3), + ] + + level['encoder_block_settings'] = block_setting + level['decoder_block_settings'] = block_setting_reverse + config['pyramid']['levels'].append(level) + elif res == 256: + level = dict() + level['resolution'] = 256 + level['kernel_size'] = 5 + level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_256' + level['upscale_enhancer_freeze'] = True + level['bottleneck_size'] = 64 * config['bottleneck_scale'] + level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3 + + block_setting = [ + CNBlockConfig(64, 128, 3), + CNBlockConfig(128, 128, 3), + CNBlockConfig(128, level['bottleneck_size'], 9), + CNBlockConfig(level['bottleneck_size'], None, 3), + ] + + block_setting_reverse = [ + CNBlockConfig(level['bottleneck_size'] * 2, 128, 3), + CNBlockConfig(128, 128, 9), + CNBlockConfig(128, 65, 3), + CNBlockConfig(64, 3, 3), + ] + + level['encoder_block_settings'] = block_setting + level['decoder_block_settings'] = block_setting_reverse + config['pyramid']['levels'].append(level) + elif res == 128: + level = dict() + level['resolution'] = 128 + level['kernel_size'] = 5 + level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_128' + level['upscale_enhancer_freeze'] = True + level['bottleneck_size'] = 64 * config['bottleneck_scale'] + level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3 + + block_setting = [ + CNBlockConfig(64, 128, 9), + CNBlockConfig(128, level['bottleneck_size'], 9), + CNBlockConfig(level['bottleneck_size'], None, 9), + ] + + block_setting_reverse = [ + CNBlockConfig(level['bottleneck_size'] * 2, 128, 9), + CNBlockConfig(128, 128, 9), + CNBlockConfig(64, 3, 9), + ] + + level['encoder_block_settings'] = block_setting + level['decoder_block_settings'] = block_setting_reverse + config['pyramid']['levels'].append(level) + elif res == 64: + level = dict() + level['resolution'] = 64 + level['kernel_size'] = 3 + level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_64' + level['upscale_enhancer_freeze'] = True + level['bottleneck_size'] = 64 * config['bottleneck_scale'] + level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3 + + block_setting = [ + CNBlockConfig(64, level['bottleneck_size'], 9), + CNBlockConfig(level['bottleneck_size'], None, 9), + ] + + block_setting_reverse = [ + CNBlockConfig(level['bottleneck_size'] * 2, 64, 9), + CNBlockConfig(64, 3, 9), + ] + + level['encoder_block_settings'] = block_setting + level['decoder_block_settings'] = block_setting_reverse + config['pyramid']['levels'].append(level) + elif res == 32: + level = dict() + level['resolution'] = 32 + level['kernel_size'] = 3 + level['upscale_enhancer'] = 'checkpoints/iccv/torch/iccv_32' + level['upscale_enhancer_freeze'] = True + level['bottleneck_size'] = 64 * config['bottleneck_scale'] + level['input_features'] = 3+3+3+7 if config['use_curvature'] else 3+3+3 + + block_setting = [ + CNBlockConfig(level['bottleneck_size'], None, 16), + ] + + block_setting_reverse = [ + CNBlockConfig(level['bottleneck_size'] * 2, 3, 16), + ] + + level['encoder_block_settings'] = block_setting + level['decoder_block_settings'] = block_setting_reverse + config['pyramid']['levels'].append(level) + else: + raise NotImplementedError + + +####################### cond_ae_curv ############################ +config['cond_ae_curv'] = dict() +config['cond_ae_curv']['device'] = config['device'] +config['cond_ae_curv']['is_label'] = True +# config['cond_ae_curv']['latent_dim'] = config['latent_dim'] +config['cond_ae_curv']['kernel_size'] = 7 +config['cond_ae_curv']['bottleneck_size'] = 40 * config['bottleneck_scale'] + +block_setting = [ + CNBlockConfig(16, 32, 3), + CNBlockConfig(32, 64, 3), + CNBlockConfig(64, 128, 9), + CNBlockConfig(128, config['cond_ae_curv']['bottleneck_size'], 9), + CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], None, 3), +] + +block_setting_reverse = [ + CNBlockConfig(config['cond_ae_curv']['bottleneck_size'], 128, 3), + CNBlockConfig(128, 64, 9), + CNBlockConfig(64, 32, 9), + CNBlockConfig(32, 16, 3), + CNBlockConfig(16, 3, 3), +] + +config['cond_ae_curv']['encoder_block_settings'] = block_setting +config['cond_ae_curv']['decoder_block_settings'] = block_setting_reverse +config['cond_ae_curv']['activation'] = 'tanh' + +####################### cond_ae_body ############################ +config['cond_ae_body'] = dict() +config['cond_ae_body']['device'] = config['device'] +config['cond_ae_body']['is_label'] = False +# config['cond_ae_body']['latent_dim'] = config['latent_dim'] +config['cond_ae_body']['kernel_size'] = 7 +config['cond_ae_body']['bottleneck_size'] = 16 * config['bottleneck_scale'] + +block_setting = [ + CNBlockConfig(16, 32, 3), + CNBlockConfig(32, 64, 3), + CNBlockConfig(64, 128, 9), + CNBlockConfig(128, config['cond_ae_body']['bottleneck_size'], 9), + CNBlockConfig(config['cond_ae_body']['bottleneck_size'], None, 3), +] + +block_setting_reverse = [ + CNBlockConfig(config['cond_ae_body']['bottleneck_size'], 128, 3), + CNBlockConfig(128, 64, 9), + CNBlockConfig(64, 32, 9), + CNBlockConfig(32, 16, 3), + CNBlockConfig(16, 3, 3), +] + +config['cond_ae_body']['encoder_block_settings'] = block_setting +config['cond_ae_body']['decoder_block_settings'] = block_setting_reverse +config['cond_ae_body']['activation'] = 'tanh' + +####################### cond_ae_static ############################ +config['cond_ae_static'] = dict() +config['cond_ae_static']['device'] = config['device'] +config['cond_ae_static']['is_label'] = False +# config['cond_ae_static']['latent_dim'] = config['latent_dim'] +config['cond_ae_static']['kernel_size'] = 7 +config['cond_ae_static']['bottleneck_size'] = 8 * config['bottleneck_scale'] + +block_setting = [ + CNBlockConfig(8, 16, 3), + CNBlockConfig(16, 32, 3), + CNBlockConfig(32, 64, 3), + CNBlockConfig(64, config['cond_ae_static']['bottleneck_size'], 9), + CNBlockConfig(config['cond_ae_static']['bottleneck_size'], None, 3), +] + +block_setting_reverse = [ + CNBlockConfig(config['cond_ae_static']['bottleneck_size'], 64, 3), + CNBlockConfig(64, 32, 9), + CNBlockConfig(32, 16, 3), + CNBlockConfig(16, 8, 3), + CNBlockConfig(8, 3, 3), +] + +config['cond_ae_static']['encoder_block_settings'] = block_setting +config['cond_ae_static']['decoder_block_settings'] = block_setting_reverse +config['cond_ae_static']['activation'] = 'tanh' \ No newline at end of file diff --git a/models/pyramid_level.py b/models/pyramid_level.py index 9cf7322..62fcea1 100644 --- a/models/pyramid_level.py +++ b/models/pyramid_level.py @@ -1,176 +1,168 @@ import os import time import random -import tensorflow as tf +import torch +from torch import nn import numpy as np import scipy as sp # import plotly.graph_objects as go # import plotly.express as ex -from custom_utils.custom_utils import load_model -from models.base import AEEncoder, VariationalEncoder, Decoder, VariationalEncoderNew, DecoderNew -from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew +from utils.checkpoints import load_model +from models.base import AEEncoder, VariationalEncoder, Decoder +from models.upscaler import Upscaler -class PyramidLevel(tf.keras.Model): + +# class PyramidLevel(nn.Module): + +# def __init__(self, config): +# super(PyramidLevel, self).__init__() +# self.latent_dim = config['latent_dim'] +# self.size = config['resolution'] + +# self.encoder: VariationalEncoder = VariationalEncoder(config['encoder_block_settings'], config['input_features'], kernel_size=config['kernel_size']) +# self.decoder: Decoder = Decoder(config['decoder_block_settings'], config['kernel_size']) + +# self.upscale_enhancer = None +# if config['upscale_enhancer'] != '': +# k_size = config['upscale_enhancer_kernel_size'] +# self.upscale_enhancer = Upscaler(config['resolution'], kernel_size=k_size) +# load_model(self.upscale_enhancer, config['upscale_enhancer']) +# for param in self.upscale_enhancer.parameters(): param.requires_grad = False + +# if config['avg_garment_path'] != '': +# self.avg_garment = np.load(config['avg_garment_path']) +# else: +# self.avg_garment = None + + +# def enhance(self, low, mask, training=None): +# x = self.upscale_enhancer([low, mask], training=training) +# return x + + +# def sample(self, z_cond, uv_mask, noise=None): +# if noise is None: +# eps = torch.normal(shape=(uv_mask.shape[0], self.latent_dim)) +# else: +# eps = noise + +# z = torch.concat([eps, z_cond], dim=-1) + +# x = self.decoder(z) + +# if self.avg_garment is not None: +# x = x + self.avg_garment[None,:,:,:] + +# x = x * uv_mask[:,None,:,:] + +# return x + + +# def reparameterize(self, mean, logvar, training, fix_noise=False): +# if training == True: +# if not fix_noise: +# eps = torch.normal(mean=0.0, std=1.0, size=mean.shape) +# else: +# eps = torch.normal(mean=0.0, std=1.0, size=mean.shape) +# eps = torch.tile(eps, [mean.shape[0],1]) +# out = eps * torch.exp(logvar * .5) + mean +# else: +# out = torch.exp(logvar * .5) + mean +# return out + + +# def call(self, inputs, z_cond, training=None): +# uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs + +# x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1) +# mean, logvar = self.encoder(x, training=training) +# z = self.reparameterize(mean, logvar, training) + +# z = torch.concat([z, z_cond], dim=-1) +# x = self.decoder(z, training=training) + +# if self.avg_garment is not None: +# x = x + self.avg_garment[None,:,:,:] + +# x = x * uv_mask[:,None,:,:] + +# # if self.upscale_enhancer is not None: +# # pred_low = self.enhance(x, uv_mask, training=training) +# # x = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5) + +# # x = x * uv_mask_high[:,:,:,tf.newaxis] + +# return x, mean, logvar + + + +class PyramidLevel(nn.Module): def __init__(self, config): super(PyramidLevel, self).__init__() - self.latent_dim = config['latent_dim'] self.size = config['resolution'] - self.encoder = VariationalEncoder(config['latent_dim'], config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size']) - self.decoder = Decoder(config['decoder_input'], config['decoder_depths'], config['decoder_dims'], config['kernel_size']) + self.encoder: VariationalEncoder = VariationalEncoder(config['encoder_block_settings'], input_features=config['input_features'], kernel_size=config['kernel_size']) + self.decoder: Decoder = Decoder(config['decoder_block_settings'], config['kernel_size']) self.upscale_enhancer = None if config['upscale_enhancer'] != '': - k_size = config['upscale_enhancer_kernel_size'] if 'upscale_enhancer_kernel_size' in config.keys() else ((3 if config['resolution'] <= 64 else 5)) - self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=k_size) + k_size = config['kernel_size'] + self.upscale_enhancer = Upscaler(config['resolution'], kernel_size=k_size).to('cuda') load_model(self.upscale_enhancer, config['upscale_enhancer']) - self.upscale_enhancer.trainable = not config['upscale_enhancer_freeze'] - - if config['avg_garment_path'] != '': - self.avg_garment = np.load(config['avg_garment_path']) - else: - self.avg_garment = None + for param in self.upscale_enhancer.parameters(): param.requires_grad = False - def enhance(self, low, mask, training=None): - x = self.upscale_enhancer([low, mask], training=training) + def enhance(self, low, mask): + x = self.upscale_enhancer([low, mask]) return x def sample(self, z_cond, uv_mask, noise=None): if noise is None: - eps = tf.random.normal(shape=(uv_mask.shape[0], self.latent_dim)) + eps = torch.normal(shape=(uv_mask.shape[0], self.latent_dim)) else: eps = noise - z = tf.concat([eps, z_cond], axis=-1) + z = torch.concat([eps, z_cond], dim=-1) x = self.decoder(z) if self.avg_garment is not None: - x = x + self.avg_garment[tf.newaxis,:,:,:] + x = x + self.avg_garment[None,:,:,:] - x = x * uv_mask[:,:,:,tf.newaxis] + x = x * uv_mask[:,None:,:] return x - def reparameterize(self, mean, logvar, training, fix_noise=False): - if training == True: + def reparameterize(self, mean, logvar, fix_noise=False): + if self.training == True: if not fix_noise: - eps = tf.random.normal(shape=mean.shape) + eps = torch.normal(mean=0.0, std=1.0, size=mean.shape).to(mean.device) else: - eps = tf.random.normal(shape=(1, mean.shape[1])) - eps = tf.tile(eps, [mean.shape[0],1]) - out = eps * tf.exp(logvar * .5) + mean + eps = torch.normal(mean=0.0, std=1.0, size=mean.shape).to(mean.device) + eps = torch.tile(eps, [mean.shape[0],1]) + out = eps * torch.exp(logvar * .5) + mean else: - out = tf.exp(logvar * .5) + mean + out = torch.exp(logvar * .5) + mean return out - def call(self, inputs, z_cond, training=None): + def forward(self, inputs, z_cond): uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs - x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1) - mean, logvar = self.encoder(x, training=training) - z = self.reparameterize(mean, logvar, training) - - z = tf.concat([z, z_cond], axis=-1) - x = self.decoder(z, training=training) - - if self.avg_garment is not None: - x = x + self.avg_garment[tf.newaxis,:,:,:] - - x = x * uv_mask[:,:,:,tf.newaxis] - - # if self.upscale_enhancer is not None: - # pred_low = self.enhance(x, uv_mask, training=training) - # x = tf.image.resize(pred_low, (512, 256), tf.image.ResizeMethod.LANCZOS5) - - # x = x * uv_mask_high[:,:,:,tf.newaxis] - - return x, mean, logvar - - - -class PyramidLevelNew(tf.keras.Model): - - def __init__(self, config): - super(PyramidLevelNew, self).__init__() - self.size = config['resolution'] - - self.encoder = VariationalEncoderNew(config['encoder_depths'], config['encoder_dims'], kernel_size=config['kernel_size']) - self.decoder = DecoderNew(config['decoder_depths'], config['decoder_dims'], config['kernel_size']) - - self.upscale_enhancer = None - if config['upscale_enhancer'] != '': - k_size = config['upscale_enhancer_kernel_size'] if 'upscale_enhancer_kernel_size' in config.keys() else ((3 if config['resolution'] <= 64 else 5)) - self.upscale_enhancer = UpscalerBasicConv(config['resolution'], kernel_size=k_size) - load_model(self.upscale_enhancer, config['upscale_enhancer']) - self.upscale_enhancer.trainable = not config['upscale_enhancer_freeze'] - - if config['avg_garment_path'] != '': - self.avg_garment = np.load(config['avg_garment_path']) - else: - self.avg_garment = None - - self.reshape = tf.keras.layers.Reshape((8, 4, 64)) - - - def enhance(self, low, mask, training=None): - x = self.upscale_enhancer([low, mask], training=training) - return x - - - def sample(self, z_cond, uv_mask, noise=None): - if noise is None: - eps = tf.random.normal(shape=(uv_mask.shape[0], self.latent_dim)) - else: - eps = noise - - z = tf.concat([eps, z_cond], axis=-1) + x = torch.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], dim=1) + mean, logvar = self.encoder(x) + z = self.reparameterize(mean, logvar) + z = torch.reshape(z, (mean.shape[0], -1, 8, 4)) + z = torch.concat([z, z_cond], dim=1) x = self.decoder(z) - - if self.avg_garment is not None: - x = x + self.avg_garment[tf.newaxis,:,:,:] - - x = x * uv_mask[:,:,:,tf.newaxis] - return x - - - def reparameterize(self, mean, logvar, training, fix_noise=False): - if training == True: - if not fix_noise: - eps = tf.random.normal(shape=mean.shape) - else: - eps = tf.random.normal(shape=(1, mean.shape[1])) - eps = tf.tile(eps, [mean.shape[0],1]) - out = eps * tf.exp(logvar * .5) + mean - else: - out = tf.exp(logvar * .5) + mean - return out - - - def call(self, inputs, z_cond, training=None): - uv_unposed, uv_template, uv_body_posed, uv_curv, uv_mask, uv_mask_high = inputs - - x = tf.concat([uv_unposed, uv_template, uv_body_posed, uv_curv], axis=-1) - mean, logvar = self.encoder(x, training=training) - z = self.reparameterize(mean, logvar, training) - z = self.reshape(z) - - z = tf.concat([z, z_cond], axis=-1) - x = self.decoder(z, training=training) - - if self.avg_garment is not None: - x = x + self.avg_garment[tf.newaxis,:,:,:] - - x = x * uv_mask[:,:,:,tf.newaxis] + x = x * uv_mask[:,None,:,:] # if self.upscale_enhancer is not None: # pred_low = self.enhance(x, uv_mask, training=training) diff --git a/models/pyramid_model.py b/models/pyramid_model.py new file mode 100644 index 0000000..2613569 --- /dev/null +++ b/models/pyramid_model.py @@ -0,0 +1,246 @@ +import os +import time +import random +import torch +from torch import nn +import torch.nn.functional as F +# import numpy as np +# import scipy as sp +# import plotly.graph_objects as go +# import plotly.express as ex + +from utils.checkpoints import load_model +from models.base import AEEncoder +from models.pyramid_level import PyramidLevel + + +# class Pyramid(nn.Module): + +# def __init__(self, config): +# super(Pyramid, self).__init__() + +# self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], kernel_size=config['cond_ae_static']['kernel_size'], activation=config['cond_ae_static']['activation']) +# if config['pyramid']['static_model'] != '': +# load_model(self.static_enc, config['pyramid']['static_model'] + '_enc') + +# self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], kernel_size=config['cond_ae_body']['kernel_size'], activation=config['cond_ae_body']['activation']) +# if config['pyramid']['body_model'] != '': +# load_model(self.body_enc, config['pyramid']['body_model'] + '_enc') + +# self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], kernel_size=config['cond_ae_curv']['kernel_size'], activation=config['cond_ae_curv']['activation']) +# if config['pyramid']['curvature_model'] != '': +# load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc') + +# if config['freeze_encoders']: +# for param in self.static_enc.parameters(): param.requires_grad = False +# for param in self.body_enc.parameters(): param.requires_grad = False +# for param in self.curv_enc.parameters(): param.requires_grad = False + + +# self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae_static': config['cond_ae_static'], 'cond_ae_body': config['cond_ae_body'], 'cond_ae_curv': config['cond_ae_curv'], } }) for i in range(len(config['pyramid']['levels']))] + +# # if config['is_cape']: +# # if len(config['pyramid']['resolutions']) == 2: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # if len(config['pyramid']['resolutions']) == 3: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # if len(config['pyramid']['resolutions']) == 4: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # else: + +# # if len(config['pyramid']['resolutions']) == 2: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # if len(config['pyramid']['resolutions']) == 3: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) +# # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # if len(config['pyramid']['resolutions']) == 4: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) +# # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) +# # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) +# # if len(config['pyramid']['resolutions']) == 5: +# # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)]) +# # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) +# # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) +# # self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) + +# # self.add_noise = config['pyramid']['add_noise'] +# # self.noise_amount = config['pyramid']['noise_amount'] +# self.use_offsets = config['use_offsets'] + +# # self.upscale_enhancer = None +# # if config['pyramid']['final_upscale_enhancer'] != '': +# # k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5)) +# # self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size) +# # load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) +# # self.upscale_enhancer.trainable = False + +# def enhance(self, low, mask): +# x = self.upscale_enhancer([low, mask]) +# return x + +# def encode_conds(self, uv_template, uv_body_posed, uv_curv): +# z_static = self.static_enc(uv_template) +# z_body = self.body_enc(uv_body_posed) +# z_curv = self.curv_enc(uv_curv) + +# z_cond = torch.concat([z_static, z_body, z_curv], dim=-1) + +# return z_cond + +# def call(self, inputs): +# levels_input, conds = inputs +# uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2] + +# z_cond = self.encode_conds(uv_static, uv_body, uv_curv) + +# # if self.add_noise == True and training == True: +# # z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount) + +# out_levels = [] +# pred, mean, logvar = self.levels[0](levels_input[0], z_cond) +# if self.use_offsets: +# pred = pred + levels_input[0][2] # uv_body_posed_32 +# if 1 != len(self.levels): +# pred = self.levels[0].enhance(pred, levels_input[0][-2]) # levels_input[i][-2]=uv_mask_res +# pred = F.interpolate(pred, size=(self.levels[1].size, self.levels[1].size//2), mode='bilinear') +# out_levels.append([pred, mean, logvar]) +# pred = pred * levels_input[1][-2][:,None,:,:] +# else: +# pred = self.enhance(pred, levels_input[0][-2]) +# pred = F.interpolate(pred, size=(512, 256), mode='bilinear') +# pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask +# out_levels.append([pred, mean, logvar]) + +# for i in range(1, len(self.levels)): +# pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond) +# pred = pred + pred_level +# if i != len(self.levels) - 1: +# pred = self.levels[i].enhance(pred, levels_input[i][-2]) +# out_levels.append([pred, mean, logvar]) +# pred = F.interpolate(pred, size=(self.levels[i+1].size, self.levels[i+1].size//2), mode='bilinear') +# pred = pred * levels_input[i+1][-2][:,None,:,:] +# else: +# pred = self.enhance(pred, levels_input[i][-1]) +# pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask +# pred = F.interpolate(pred, size=(512, 256), mode='bilinear') +# out_levels.append([pred, mean, logvar]) + +# return out_levels + + + +class Pyramid(nn.Module): + + def __init__(self, config): + super(Pyramid, self).__init__() + + self.static_enc : AEEncoder = AEEncoder(config['cond_ae_static']['encoder_block_settings'], kernel_size=config['cond_ae_static']['kernel_size'], activation=config['cond_ae_static']['activation']) + if config['static_model'] != '': + load_model(self.static_enc, config['static_model'] + '_enc') + + self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['encoder_block_settings'], kernel_size=config['cond_ae_body']['kernel_size'], activation=config['cond_ae_body']['activation']) + if config['body_model'] != '': + load_model(self.body_enc, config['body_model'] + '_enc') + + self.curv_enc : AEEncoder = AEEncoder(config['cond_ae_curv']['encoder_block_settings'], kernel_size=config['cond_ae_curv']['kernel_size'], activation=config['cond_ae_curv']['activation'], is_label=True, nr_of_labels=7) + if config['curvature_model'] != '': + load_model(self.curv_enc, config['curvature_model'] + '_enc') + + if config['freeze_encoders']: + for param in self.static_enc.parameters(): param.requires_grad = False + for param in self.body_enc.parameters(): param.requires_grad = False + for param in self.curv_enc.parameters(): param.requires_grad = False + + self.levels = [PyramidLevel({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))] + + + # if len(config['pyramid']['resolutions']) == 2: + # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) + # if len(config['pyramid']['resolutions']) == 3: + # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) + # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) + # if len(config['pyramid']['resolutions']) == 4: + # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) + # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) + # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) + # if len(config['pyramid']['resolutions']) == 5: + # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)]) + # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) + # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) + # self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) + + # self.add_noise = config['pyramid']['add_noise'] + # self.noise_amount = config['pyramid']['noise_amount'] + # self.use_offsets = config['use_offsets'] + + # self.upscale_enhancer = None + # if config['pyramid']['final_upscale_enhancer'] != '': + # k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5)) + # self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size) + # load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) + # self.upscale_enhancer.trainable = False + + # def enhance(self, low, mask, training): + # x = self.upscale_enhancer([low, mask], training=training) + # return x + + def encode_conds(self, uv_template, uv_body_posed, uv_curv): + z_static = self.static_enc(uv_template) + z_body = self.body_enc(uv_body_posed) + z_curv = self.curv_enc(uv_curv) + + z_cond = torch.concat([z_static, z_body, z_curv], dim=1) + + return z_cond + + def forward(self, inputs): + levels_input, conds = inputs + uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2] + + z_cond = self.encode_conds(uv_static, uv_body, uv_curv) + + # if self.add_noise == True and training == True: + # z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount) + + out_levels = [] + pred, mean, logvar = self.levels[0](levels_input[0], z_cond) + # if self.use_offsets: + # pred = pred + levels_input[0][2] # uv_body_posed_32 + if 1 != len(self.levels): + pred = self.levels[0].enhance(pred, levels_input[0][-2]) # levels_input[i][-2]=uv_mask_res + pred = F.interpolate(pred, size=(self.levels[1].size, self.levels[1].size//2), mode='bilinear') + out_levels.append([pred, mean, logvar]) + pred = pred * levels_input[1][-2][:,None,:,:] + else: + # pred = self.enhance(pred, levels_input[0][-2], training=training) + pred = self.levels[0].enhance(pred, levels_input[0][-2]) # levels_input[i][-2]=uv_mask_res + pred = F.interpolate(pred, size=(512, 256), mode='bilinear') + pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask + out_levels.append([pred, mean, logvar]) + + for i in range(1, len(self.levels)): + input = levels_input[i] + # input[0] = input[0] - pred + # input_min, input_max = tf.reduce_min(input[0], axis=[1,2,3]), tf.reduce_max(input[0], axis=[1,2,3]) + # input[0] = (input[0] - input_min[:,None,None,None]) / (input_max - input_min)[:,None,None,None] + # input[0] = input[0] * input[-2][:,None,:,:] # uv_mask_res + pred_level, mean, logvar = self.levels[i](input, z_cond) + # pred_level = ( (pred_level * (input_max - input_min)[:,None,None,None]) + input_min[:,None,None,None] ) * input[-2][:,:,:,None] # uv_mask_res + pred = pred + pred_level + if i != len(self.levels) - 1: + pred = self.levels[i].enhance(pred, levels_input[i][-2]) + out_levels.append([pred, mean, logvar]) + pred = F.interpolate(pred, size=(self.levels[i+1].size, self.levels[i+1].size//2), mode='bilinear') + pred = pred * levels_input[i+1][-2][:,None,:,:] + else: + # if self.upscale_enhancer is not None: + # pred = self.enhance(pred, levels_input[-1][-2], training=training) + pred = self.levels[-1].enhance(pred, levels_input[-1][-2]) + pred = F.interpolate(pred, size=(512, 256), mode='bilinear') + pred = pred * levels_input[-1][-1][:,None,:,:] # full res uv mask + out_levels.append([pred, mean, logvar]) + + return out_levels \ No newline at end of file diff --git a/models/pyramid_model_optimized.py b/models/pyramid_model_optimized.py deleted file mode 100644 index 5301872..0000000 --- a/models/pyramid_model_optimized.py +++ /dev/null @@ -1,365 +0,0 @@ -import os -import time -import random -import tensorflow as tf -import numpy as np -# import plotly.graph_objects as go -# import plotly.express as ex - -from custom_utils.custom_utils import load_model -from models.base import AEEncoder, AEEncoderNew -from models.pyramid_level import PyramidLevel, PyramidLevelNew -from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew - - -class Pyramid(tf.keras.Model): - - def __init__(self, config): - super(Pyramid, self).__init__() - - self.static_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size']) - if config['pyramid']['static_model'] != '': - load_model(self.static_enc, config['pyramid']['static_model'] + '_enc') - - self.body_enc : AEEncoder = AEEncoder(config['cond_ae_body']['latent_dim'], config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['bottleneck_size'], config['cond_ae_body']['kernel_size']) - if config['pyramid']['body_model'] != '': - load_model(self.body_enc, config['pyramid']['body_model'] + '_enc') - - self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size']) - if config['pyramid']['curvature_model'] != '': - load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc') - - if config['pyramid']['freeze_encoders']: - self.static_enc.trainable = False - self.body_enc.trainable = False - self.curv_enc.trainable = False - - self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'), - tf.keras.layers.Dense(256, activation='relu'), - tf.keras.layers.Dense(128, activation='relu'), - tf.keras.layers.Dense(config['pyramid']['latent_dim'], activation='tanh'),]) - - self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) for i in range(len(config['pyramid']['levels']))] - - # if config['is_cape']: - # if len(config['pyramid']['resolutions']) == 2: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # if len(config['pyramid']['resolutions']) == 3: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # if len(config['pyramid']['resolutions']) == 4: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # else: - if len(config['pyramid']['resolutions']) == 2: - self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - if len(config['pyramid']['resolutions']) == 3: - self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - if len(config['pyramid']['resolutions']) == 4: - self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) - self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - if len(config['pyramid']['resolutions']) == 5: - self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)]) - self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) - self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - - self.add_noise = config['pyramid']['add_noise'] - self.noise_amount = config['pyramid']['noise_amount'] - self.use_offsets = config['use_offsets'] - - self.upscale_enhancer = None - if config['pyramid']['final_upscale_enhancer'] != '': - k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5)) - self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size) - load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) - self.upscale_enhancer.trainable = False - - def enhance(self, low, mask, training): - x = self.upscale_enhancer([low, mask], training=training) - return x - - def encode_conds(self, uv_template, uv_body_posed, uv_curv, training): - z_static = self.static_enc(uv_template, training) - z_body = self.body_enc(uv_body_posed, training) - z_curv = self.curv_enc(uv_curv, training) - - z_cond = tf.concat([z_static, z_body, z_curv], axis=-1) - z_cond = self.cond_encoder(z_cond, training=training) - - return z_cond - - def call(self, inputs, training): - levels_input, conds = inputs - uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2] - - z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training) - - if self.add_noise == True and training == True: - z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount) - - out_levels = [] - pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training) - if self.use_offsets: - pred = pred + levels_input[0][2] # uv_body_posed_32 - if 1 != len(self.levels): - pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res - pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5) - out_levels.append([pred, mean, logvar]) - pred = pred * levels_input[1][-2][:,:,:,tf.newaxis] - else: - pred = self.enhance(pred, levels_input[0][-2], training=training) - pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5) - pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - out_levels.append([pred, mean, logvar]) - - for i in range(1, len(self.levels)): - pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training) - pred = pred + pred_level - if i != len(self.levels) - 1: - pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training) - out_levels.append([pred, mean, logvar]) - pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5) - pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis] - else: - if self.upscale_enhancer is not None: - pred = self.enhance(pred, levels_input[-1][-2], training=training) - pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5) - pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - out_levels.append([pred, mean, logvar]) - - return out_levels - - # # 32 - # pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training) - # pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training) - # pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5) - # pred_0 = pred_0 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - # return [ [pred_0, mean_0, logvar_0] ] - - # # 32 64 - # pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training) - # pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res - # pred_0 = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5) - # pred = pred_0 * levels_input[1][-2][:,:,:,tf.newaxis] - - # pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training) - # pred_1 = pred + pred_1 - # pred_1 = self.enhance(pred_1, levels_input[-1][-2], training=training) - # pred_1 = tf.image.resize(pred_1, (512, 256), tf.image.ResizeMethod.LANCZOS5) - # pred_1 = pred_1 * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - - # return [ [pred_0, mean_0, logvar_0], [pred_1, mean_1, logvar_1] ] - - -# class Pyramid(tf.keras.Model): - -# def __init__(self, config): -# super(Pyramid, self).__init__() - -# self.static_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size']) -# if config['pyramid']['static_model'] != '': -# load_model(self.static_enc, config['pyramid']['static_model'] + '_enc') - -# self.body_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size']) -# if config['pyramid']['body_model'] != '': -# load_model(self.body_enc, config['pyramid']['body_model'] + '_enc') - -# self.curv_enc : AEEncoder = AEEncoder(config['cond_ae']['latent_dim'], config['cond_ae']['encoder_depths'], config['cond_ae']['encoder_dims'], config['cond_ae']['bottleneck_size'], config['cond_ae']['kernel_size']) -# if config['pyramid']['curvature_model'] != '': -# load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc') - -# if config['pyramid']['freeze_encoders']: -# self.static_enc.trainable = False -# self.body_enc.trainable = False -# self.curv_enc.trainable = False - -# self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(512, activation='relu'), -# tf.keras.layers.Dense(256, activation='relu'), -# tf.keras.layers.Dense(128, activation='relu'), -# tf.keras.layers.Dense(config['pyramid']['latent_dim']),]) - -# self.levels = [PyramidLevel({ **config['pyramid']['levels'][i], **{ 'cond_ae': config['cond_ae']} }) for i in range(len(config['pyramid']['levels']))] - - -# self.upscale_enhancer = None -# if config['pyramid']['final_upscale_enhancer'] != '': -# self.upscale_enhancer = UpscalerBasicNew(low_res=config['pyramid']['resolutions'][-1]) -# load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) -# self.upscale_enhancer.trainable = False - -# def enhance(self, low, mask, training): -# x = self.upscale_enhancer([low, mask], training=training) -# return x - -# def encode_conds(self, uv_template, uv_body_posed, uv_curv): -# z_static = self.static_enc(uv_template) -# z_body = self.body_enc(uv_body_posed) -# z_curv = self.curv_enc(uv_curv) - -# z_cond = tf.concat([z_static, z_body, z_curv], axis=-1) -# z_cond = self.cond_encoder(z_cond) - -# return z_cond - -# def call(self, inputs, training): -# levels_input, conds = inputs -# uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2] -# z_cond = self.encode_conds(uv_static, uv_body, uv_curv) - -# out_levels = [] -# pred_0, mean_0, logvar_0 = self.levels[0](levels_input[0], z_cond, training=training) -# pred_0 = self.levels[0].enhance(pred_0, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res -# # pred_0 = self.enhance(pred_0, levels_input[0][-2], training=training) - -# ################## -# # if more than 1 level -# # x = tf.image.resize(pred_0, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.LANCZOS5) -# # x = x * levels_input[1][-2][:,:,:,tf.newaxis] - -# # if only 1 level -# pred_0 = tf.image.resize(pred_0, (512, 256), tf.image.ResizeMethod.LANCZOS5) -# ################## - - -# # pred_1, mean_1, logvar_1 = self.levels[1](levels_input[1], z_cond, training=training) -# # pred_1 = pred_0 + pred_1 -# # pred_1 = self.levels[1].enhance(pred, levels_input[1][-2], training=training) - -# # for i in range(1, len(self.levels)): -# # pred_level, mean, logvar = self.levels[i](levels_input[i], z_cond, training=training) -# # pred = pred + pred_level -# # if i != len(self.levels) - 1: -# # pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training) -# # out_levels.append([pred, mean, logvar]) -# # pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.LANCZOS5) -# # pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis] -# # else: -# # if self.upscale_enhancer is not None: -# # pred = self.enhance(pred, levels_input[-1][-2], training=training) -# # pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.LANCZOS5) -# # out_levels.append([pred, mean, logvar]) -# # pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - -# out_levels = [ -# [pred_0, mean_0, logvar_0] -# ] - -# return out_levels - - -class PyramidNew(tf.keras.Model): - - def __init__(self, config): - super(PyramidNew, self).__init__() - - self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['encoder_depths'], config['cond_ae_static']['encoder_dims'], config['cond_ae_static']['kernel_size'], config['cond_ae_static']['activation']) - if config['pyramid']['static_model'] != '': - load_model(self.static_enc, config['pyramid']['static_model'] + '_enc') - - self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['encoder_depths'], config['cond_ae_body']['encoder_dims'], config['cond_ae_body']['kernel_size']) - if config['pyramid']['body_model'] != '': - load_model(self.body_enc, config['pyramid']['body_model'] + '_enc') - - self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation']) - if config['pyramid']['curvature_model'] != '': - load_model(self.curv_enc, config['pyramid']['curvature_model'] + '_enc') - - if config['pyramid']['freeze_encoders']: - self.static_enc.trainable = False - self.body_enc.trainable = False - self.curv_enc.trainable = False - - self.levels = [PyramidLevelNew({ **config['pyramid']['levels'][i] }) for i in range(len(config['pyramid']['levels']))] - - - # if len(config['pyramid']['resolutions']) == 2: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # if len(config['pyramid']['resolutions']) == 3: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # if len(config['pyramid']['resolutions']) == 4: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) - # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - # if len(config['pyramid']['resolutions']) == 5: - # self.levels[-1].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100000)]) - # self.levels[-2].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 10000)]) - # self.levels[-3].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 1000)]) - # self.levels[-4].decoder.decoder.last = tf.keras.Sequential([tf.keras.layers.Dense(3), tf.keras.layers.Lambda(lambda x: x / 100)]) - - self.add_noise = config['pyramid']['add_noise'] - self.noise_amount = config['pyramid']['noise_amount'] - self.use_offsets = config['use_offsets'] - - self.upscale_enhancer = None - if config['pyramid']['final_upscale_enhancer'] != '': - k_size = config['pyramid']['final_upscale_enhancer_kernel_size'] if 'final_upscale_enhancer_kernel_size' in config['pyramid'].keys() else ((3 if config['pyramid']['resolutions'][-1] <= 64 else 5)) - self.upscale_enhancer = UpscalerBasicConv(low_res=config['pyramid']['resolutions'][-1], kernel_size=k_size) - load_model(self.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) - self.upscale_enhancer.trainable = False - - def enhance(self, low, mask, training): - x = self.upscale_enhancer([low, mask], training=training) - return x - - def encode_conds(self, uv_template, uv_body_posed, uv_curv, training): - z_static = self.static_enc(uv_template, training) - z_body = self.body_enc(uv_body_posed, training) - z_curv = self.curv_enc(uv_curv, training) - - z_cond = tf.concat([z_static, z_body, z_curv], axis=-1) - - return z_cond - - def call(self, inputs, training): - levels_input, conds = inputs - uv_static, uv_body, uv_curv = conds[0], conds[1], conds[2] - - z_cond = self.encode_conds(uv_static, uv_body, uv_curv, training) - - if self.add_noise == True and training == True: - z_cond = z_cond + (tf.random.uniform(z_cond.shape, maxval=self.noise_amount * 2) - self.noise_amount) - - out_levels = [] - pred, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training) - if self.use_offsets: - pred = pred + levels_input[0][2] # uv_body_posed_32 - if 1 != len(self.levels): - pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res - pred = tf.image.resize(pred, (self.levels[1].size, self.levels[1].size//2), tf.image.ResizeMethod.BILINEAR) - out_levels.append([pred, mean, logvar]) - pred = pred * levels_input[1][-2][:,:,:,tf.newaxis] - else: - # pred = self.enhance(pred, levels_input[0][-2], training=training) - pred = self.levels[0].enhance(pred, levels_input[0][-2], training=training) # levels_input[i][-2]=uv_mask_res - pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR) - pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - out_levels.append([pred, mean, logvar]) - - for i in range(1, len(self.levels)): - input = levels_input[i] - input[0] = input[0] - pred - input_min, input_max = tf.reduce_min(input[0], axis=[1,2,3]), tf.reduce_max(input[0], axis=[1,2,3]) - input[0] = (input[0] - input_min[:,None,None,None]) / (input_max - input_min)[:,None,None,None] - input[0] = input[0] * input[-2][:,:,:,None] # uv_mask_res - pred_level, mean, logvar = self.levels[i](input, z_cond, training=training) - pred_level = ( (pred_level * (input_max - input_min)[:,None,None,None]) + input_min[:,None,None,None] ) * input[-2][:,:,:,None] # uv_mask_res - pred = pred + pred_level - if i != len(self.levels) - 1: - pred = self.levels[i].enhance(pred, levels_input[i][-2], training=training) - out_levels.append([pred, mean, logvar]) - pred = tf.image.resize(pred, (self.levels[i+1].size, self.levels[i+1].size//2), tf.image.ResizeMethod.BILINEAR) - pred = pred * levels_input[i+1][-2][:,:,:,tf.newaxis] - else: - # if self.upscale_enhancer is not None: - # pred = self.enhance(pred, levels_input[-1][-2], training=training) - pred = self.levels[-1].enhance(pred, levels_input[-1][-2], training=training) - pred = tf.image.resize(pred, (512, 256), tf.image.ResizeMethod.BILINEAR) - pred = pred * levels_input[-1][-1][:,:,:,tf.newaxis] # full res uv mask - out_levels.append([pred, mean, logvar]) - - return out_levels \ No newline at end of file diff --git a/scripts/cvae_pyramid.py b/scripts/cvae_pyramid.py index 7594a89..deb3e2c 100644 --- a/scripts/cvae_pyramid.py +++ b/scripts/cvae_pyramid.py @@ -1,65 +1,67 @@ import os import sys -from configs.config_abl_pyr_32_skirt import config +sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..') +import importlib +import argparse +parser = argparse.ArgumentParser(description='') +parser.add_argument('--name', type=str) +parser.add_argument('--config', type=str) +parser.add_argument('--debug', action='store_true') +args = vars(parser.parse_args()) + +config_module = importlib.import_module(args['config']) +config = config_module.config +if args['debug']: + from configs.pyr_32 import config +os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = config['gpu'] -import tensorflow as tf - -gpus = tf.config.experimental.list_physical_devices('GPU') -if gpus: - try: - # Currently, memory growth needs to be the same across GPUs - for gpu in gpus: - tf.config.experimental.set_memory_growth(gpu, True) - logical_gpus = tf.config.experimental.list_logical_devices('GPU') - print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs") - except RuntimeError as e: - # Memory growth must be set before GPUs have been initialized - print(e) +if args['debug']: + os.environ["CUDA_LAUNCH_BLOCKING"] = '1' import time -import tqdm import argparse import wandb +import tqdm import random import numpy as np -import scipy as sp -from custom_utils.custom_utils import UV2Mesh, get_summary_html, maskFacesBatch, _maskFaces, get_summary_str, plot_3d_collision, group_inputs_for_levels import plotly.graph_objects as go import plotly.express as ex -from plotly.subplots import make_subplots from PIL import Image if config['is_skirt']: - from losses import edge_loss_skirt as edge_loss + from losses.losses import edge_loss_skirt as edge_loss else: - from losses import edge_loss + from losses.losses import edge_loss -from losses import uv_mask_loss, bend_loss, kl_loss, collision_ratio, normal_loss -# from losses import collision_penalty as collision_penalty -from losses import collision_loss as collision_penalty -from custom_utils.custom_utils import batch_to_dict, load_model -from dataset import DatasetFactory, StaticDataset -from custom_utils.smpl import SMPL -from models.pyramid_model_optimized import Pyramid -from postprocessing import fix_collision +import torch +import torch.nn as nn +import torch.optim as optim +import torch.nn.functional as F +from data.dataset import Dataset +from utils.checkpoints import CheckpointSaver, load_model +from utils.utils import InfiniteDataLoader as DataLoader +from utils.postprocess import fix_collision +from losses.losses import collision_loss, normal_loss, kl_loss +from pytorch_msssim import MS_SSIM +from custom_utils.custom_utils import UV2Mesh, Accumulator, plot_3d, get_summary_html, maskFacesBatch, get_summary_str, plot_3d_collision, group_inputs_for_levels +from smpl.smpl_torch import SMPL +from plotly.subplots import make_subplots +from models.pyramid_model import Pyramid def init_wandb(): - run = wandb.init(project='ablation', name=config['name'], notes=config['notes'], dir='/wandb', tags=config['tags']) - + run = wandb.init(project='iccv', name=config['name'], notes=config['notes'], dir='/data-local/127/temp', tags=config['tags']) artifact = wandb.Artifact('code', type='code') - artifact.add_file('cvae_pyramid.py') - artifact.add_file('models/cvae_model.py') - artifact.add_file('models/pyramid_model_optimized.py') - artifact.add_file('models/pyramid_level.py') - artifact.add_file('models/upscaler.py') - artifact.add_file('losses.py') + artifact.add_file('scripts/cvae_pyramid.py') + artifact.add_file('losses/losses.py') artifact.add_file('models/base.py') artifact.add_file('models/cond_encoder.py') - artifact.add_file('dataset.py') - artifact.add_file('convnext/models/convnext_tf.py') - config_file_names = [key for key in sys.modules.keys() if key.startswith('configs')] + artifact.add_file('models/convnext.py') + artifact.add_file('models/pyramid_model.py') + artifact.add_file('models/pyramid_level.py') + artifact.add_file('data/dataset.py') + config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] for config_file_name in config_file_names: file_name = '/'.join(config_file_name.split('.')) + '.py' if os.path.exists(file_name): @@ -210,86 +212,12 @@ def plot_3d(mesh_gt, mesh_pred_unposed_levels, faces, mesh_posed, collision, col return fig -# @tf.function def train_step(batch): + model.train() + # with torch.autocast(device_type='cuda', dtype=torch.float16, enabled=use_amp): levels_input, conds = group_inputs_for_levels(batch, config) - with tf.GradientTape() as tape: - out_levels = model([levels_input, conds], training=True) - - if config['use_skinning']: - mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] - else: - mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] - - output = dict() - reconstr_loss_total = 0 - kl_total = 0 - - #for i, res in enumerate(config['pyramid']['resolutions']): - i = -1 - res = config['pyramid']['resolutions'][-1] - res_modifier = '_' + str(res) if res != 512 else '' - pred, mean, logvar = out_levels[i] - - mesh_pred = uv2mesh(pred) - - if config['use_skinning']: - shape = batch['pose_shape'][:, 72:] - gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) - - mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] - mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) - else: - mesh_pred_posed = mesh_pred - - # is the output already masked? - - e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) - c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) - c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) - l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) - # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) - # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) - l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1)) - n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt']) - kl = kl_loss(mean, logvar) - - if config['use_extra_losses']: - reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) - if not config['is_cape']: - reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] - else: - reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) - - # if config['use_norm_loss'] and step > 2000: - # reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] - - kl_total += kl - - mean = tf.reduce_mean(mean) - logvar = tf.reduce_mean(logvar) - - metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) - - output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, - 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl, - 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss, - 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss } } # 'train/ms_ssim' + res_modifier: ms_ssim, - - loss = reconstr_loss_total + balancing_coeff * kl_total - - gradients = tape.gradient(loss, model.trainable_variables) - optimizer.apply_gradients(zip(gradients, model.trainable_variables)) - return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output } - - -@tf.function -def valid_step(batch): - levels_input, conds = group_inputs_for_levels(batch, config) - out_levels = model([levels_input, conds], training=False) - + out_levels = model([levels_input, conds]) if config['use_skinning']: mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] @@ -310,23 +238,24 @@ def valid_step(batch): if config['use_skinning']: shape = batch['pose_shape'][:, 72:] - gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) - mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] - mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] else: mesh_pred_posed = mesh_pred - # is the output already masked? - e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) - c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) - c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) - l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((uv_orig - pred) ** 2), axis=-1), axis=[1, 2])) - # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) - # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) - l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, axis=-1), axis=-1)) - n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt']) + # is the output already masked? + # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) + # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) + + e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) + c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) + c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) + l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) + n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) kl = kl_loss(mean, logvar) if config['use_extra_losses']: @@ -335,35 +264,121 @@ def valid_step(batch): reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] else: reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) + + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] - # if config['use_norm_loss'] and step > 2000: - # reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] - kl_total += kl + loss = reconstr_loss_total + g_balancing_coeff * kl_total - mean = tf.reduce_mean(mean) - logvar = tf.reduce_mean(logvar) + # scaler.scale(loss).backward() + # scaler.step(optimizer) + # scaler.update() + # optimizer.zero_grad() - metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) + optimizer.zero_grad() + loss.backward() + optimizer.step() + + model.eval() + with torch.inference_mode(): + mean = torch.mean(mean) + logvar = torch.mean(logvar) + + ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1)) + metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask']) + + output = { **output, **{ 'train/edge_loss' + res_modifier: e_loss, 'train/collision_loss' + res_modifier: c_loss,'train/euclid_error' + res_modifier: metric, + 'train/mean' + res_modifier: mean, 'train/logvar' + res_modifier: logvar, 'train/kl_loss' + res_modifier: kl, + 'train/var' + res_modifier: np.e ** logvar, 'train/l2_loss' + res_modifier: l2_loss, 'train/normal_loss': n_loss, + 'train/euclid_error': metric, 'train/l2_mesh_loss': l2_mesh_loss, 'train/ms_ssim' + res_modifier: ms_ssim, } } # + + + return { **{ 'train/loss': loss, 'train/reconstr_loss_total': reconstr_loss_total, 'train/kl_total': kl_total }, **output } + + +def valid_step(batch): + model.eval() + with torch.inference_mode(): + levels_input, conds = group_inputs_for_levels(batch, config) + + out_levels = model([levels_input, conds]) + + if config['use_skinning']: + mesh_orig, uv_orig = batch['mesh_unposed'], batch['uv_unposed'] + else: + mesh_orig, uv_orig = batch['mesh_posed'], batch['uv_posed'] + + output = dict() + reconstr_loss_total = 0 + kl_total = 0 + + #for i, res in enumerate(config['pyramid']['resolutions']): + i = -1 + res = config['pyramid']['resolutions'][-1] + res_modifier = '_' + str(res) if res != 512 else '' + pred, mean, logvar = out_levels[i] + + mesh_pred = uv2mesh(pred) + + if config['use_skinning']: + shape = batch['pose_shape'][:, 72:] + gender = torch.greater_equal(shape[:, 10] , 0.5).to(dtype=torch.int64) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]) + + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] + mesh_pred_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped)[0] + else: + mesh_pred_posed = mesh_pred + + # is the output already masked? + # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) + # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) + + e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) + c_loss, c_ratio = collision_loss(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) + c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((uv_orig - pred) ** 2), dim=-1), dim=[1, 2])) + l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (batch['mesh_posed'] - mesh_pred_posed) ** 2, dim=-1), dim=-1)) + n_loss = normal_loss(mesh_pred_posed, batch['mesh_posed'], batch['mesh_mask'], is_skirt=config['is_skirt'], is_smpl_orig=config['is_cape']) + kl = kl_loss(mean, logvar) + + if config['use_extra_losses']: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) + if not config['is_cape']: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (e_loss + c_loss) * config['reg_loss_coeff'] + else: + reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss) + + if config['use_norm_loss'] and step > 2000: + reconstr_loss_total = reconstr_loss_total + n_loss * config['reg_loss_coeff'] + + kl_total += kl + loss = reconstr_loss_total + g_balancing_coeff * kl_total + + mean = torch.mean(mean) + logvar = torch.mean(logvar) + + ms_ssim = torch.mean(_MSSSIM(pred + 1, batch['uv_static'] + 1)) + metric = torch.sum(torch.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred.detach()) ** 2, axis=-1))) / torch.sum(batch['mesh_mask']) + + output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, + 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl, + 'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss, + 'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss, 'valid/ms_ssim' + res_modifier: ms_ssim, } } # - output = { **output, **{ 'valid/edge_loss' + res_modifier: e_loss, 'valid/collision_loss' + res_modifier: c_loss,'valid/euclid_error' + res_modifier: metric, - 'valid/mean' + res_modifier: mean, 'valid/logvar' + res_modifier: logvar, 'valid/kl_loss' + res_modifier: kl, - 'valid/var' + res_modifier: np.e ** logvar, 'valid/l2_loss' + res_modifier: l2_loss, 'valid/normal_loss': n_loss, - 'valid/euclid_error': metric, 'valid/l2_mesh_loss': l2_mesh_loss } } # 'valid/ms_ssim' + res_modifier: ms_ssim, - loss = reconstr_loss_total + balancing_coeff * kl_total return { **{ 'valid/loss': loss, 'valid/reconstr_loss_total': reconstr_loss_total, 'valid/kl_total': kl_total }, **output } -@tf.function def test_step(batch): levels_input, conds = group_inputs_for_levels(batch, config) out_levels = model([levels_input, conds], training=False) shape = batch['pose_shape'][:, 72:] gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) + shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, dim=0) for i in range(shape.shape[0])]) mesh_orig = batch['mesh_unposed'] output = dict() @@ -377,18 +392,18 @@ def test_step(batch): pred, mean, logvar = out_levels[i] mesh_pred = uv2mesh(pred) - mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) # is the output already masked? - e_loss = tf.reduce_mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) + e_loss = torch.mean(edge_loss(mesh_pred, mesh_orig, batch['mesh_mask'])) c_loss, c_ratio = collision_penalty(mesh_pred_posed, batch['mesh_body_posed'], batch['mesh_mask']) - c_loss, c_ratio = tf.reduce_mean(c_loss), tf.reduce_mean(c_ratio) - l2_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(((batch['uv_unposed'] - pred) ** 2), axis=-1), axis=[1, 2])) - l2_mesh_loss = tf.reduce_mean(1e3 * tf.reduce_mean(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1), axis=-1)) - # ms_ssim = tf.reduce_mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) - # ms_ssim = tf.reduce_mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) + c_loss, c_ratio = torch.mean(c_loss), torch.mean(c_ratio) + l2_loss = torch.mean(1e3 * torch.mean(torch.sum(((batch['uv_unposed'] - pred) ** 2), dim=-1), dim=[1, 2])) + l2_mesh_loss = torch.mean(1e3 * torch.mean(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1), dim=-1)) + # ms_ssim = torch.mean(tf.image.ssim_multiscale(pred + 5, batch['uv_unposed'] + 5, max_val=10, power_factors=(0.5, 0.2, 0.1, 0.1, 0.1))) + # ms_ssim = torch.mean(tf.image.ssim(pred + 1, batch['uv_unposed'] + 1, max_val=3)) kl = kl_loss(mean, logvar) reconstr_loss_total = reconstr_loss_total + config['pyramid']['loss_weights'][i] * (l2_loss + l2_mesh_loss) @@ -397,11 +412,11 @@ def test_step(batch): # reconstr_loss_total += config['pyramid']['loss_weights'][i] * (l2_loss + (e_loss + c_loss) * config['reg_loss_coeff']) kl_total += kl - mean = tf.reduce_mean(mean) - logvar = tf.reduce_mean(logvar) + mean = torch.mean(mean) + logvar = torch.mean(logvar) - metric = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1))) / tf.reduce_sum(batch['mesh_mask']) - euclid_error_per_garment = tf.reduce_sum(tf.math.sqrt(tf.reduce_sum(batch['mesh_mask'][:,:,tf.newaxis] * (mesh_orig - mesh_pred) ** 2, axis=-1)), axis=1) / tf.reduce_sum(batch['mesh_mask'], axis=1) + metric = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1))) / torch.sum(batch['mesh_mask']) + euclid_error_per_garment = torch.sum(tf.math.sqrt(torch.sum(batch['mesh_mask'][:,:,None] * (mesh_orig - mesh_pred) ** 2, dim=-1)), dim=1) / torch.sum(batch['mesh_mask'], dim=1) output = { **output, **{ 'test/edge_loss' + res_modifier: e_loss, 'test/collision_loss' + res_modifier: c_loss,'test/euclid_error' + res_modifier: metric, 'test/mean' + res_modifier: mean, 'test/logvar' + res_modifier: logvar, 'test/kl_loss' + res_modifier: kl, @@ -416,50 +431,52 @@ def test_step(batch): def plot_everything(batch: dict, type: str): if config['use_skinning']: - mesh_orig, uv_orig = batch['mesh_unposed'].numpy(), batch['uv_unposed'].numpy() + mesh_orig, uv_orig = batch['mesh_unposed'].cpu().numpy(), batch['uv_unposed'] else: - mesh_orig, uv_orig = batch['mesh_posed'].numpy(), batch['uv_posed'].numpy() + mesh_orig, uv_orig = batch['mesh_posed'].cpu().numpy(), batch['uv_posed'] - levels_input = group_inputs_for_levels(batch, config) - output_levels = model(levels_input, training=False) + model.eval() + with torch.inference_mode(): + levels_input = group_inputs_for_levels(batch, config) + output_levels = model(levels_input) - mesh_pred_levels = [uv2mesh(output_levels[i][0]).numpy() for i in range(len(output_levels))] - mesh_orig_posed = batch['mesh_posed'].numpy() - body = batch['mesh_body_posed'].numpy() + mesh_pred_levels = [uv2mesh(output_levels[i][0]).detach().cpu().numpy() for i in range(len(output_levels))] + mesh_orig_posed = batch['mesh_posed'].cpu().numpy() + body = batch['mesh_body_posed'].cpu().numpy() - orig_img = (uv_orig + 1) / 2 - uv_static_img = (batch['uv_static'].numpy() + 1) / 2 - uv_body_posed_img = (batch['uv_body_posed'].numpy() + 1) / 2 - uv_curvature = (np.tile(batch['uv_curvature'].numpy().argmax(-1)[:,:,:,np.newaxis], [1,1,1,3]) / 6) - pred_img = np.concatenate([tf.image.resize(output_levels[i][0], (512, 256), tf.image.ResizeMethod.LANCZOS5) for i in range(len(output_levels))], axis=2) - pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) - img = tf.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2) - imgs = [wandb.Image(img[i]) for i in range(4)] + orig_img = (torch.permute(uv_orig, [0,2,3,1]) + 1) / 2 + uv_static_img = (torch.permute(batch['uv_static'], [0,2,3,1]) + 1) / 2 + uv_body_posed_img = (torch.permute(batch['uv_body_posed'], [0,2,3,1]) + 1) / 2 + uv_curvature = (torch.tile(torch.argmax(torch.permute(batch['uv_curvature'], [0,2,3,1]), dim=-1)[:,:,:,None], [1,1,1,3]) / 6) + pred_img = torch.concatenate([torch.permute(F.interpolate(output_levels[i][0], size=(512, 256), mode='bilinear'), [0,2,3,1]) for i in range(len(output_levels))], dim=3) + # pred_img = (pred_img - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) / (pred_img.max(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis] - pred_img.min(axis=(1,2,3))[:,np.newaxis,np.newaxis,np.newaxis]) + pred_img = (pred_img - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) / (pred_img.flatten().reshape(pred_img.shape[0], -1).max(1)[0][:,None,None,None] - pred_img.flatten().reshape(pred_img.shape[0], -1).min(1)[0][:,None,None,None]) - F = np.load("custom_utils/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") - mask = batch['mesh_mask'].numpy().astype(bool) - _, faces = maskFacesBatch(np.ones_like(mesh_orig), F, mask) + img = torch.concat((uv_static_img, uv_body_posed_img, uv_curvature, orig_img, pred_img), axis=2) + imgs = [wandb.Image(img[i].cpu().numpy()) for i in range(4)] + + _F = np.load("smpl/smpl_faces" + skirt_modifier + ("_orig" if config['is_cape'] else "") + ".npy") + mask = batch['mesh_mask'].cpu().numpy().astype(bool) + _, faces = maskFacesBatch(np.ones_like(mesh_orig), _F, mask) if config['use_skinning']: shape = batch['pose_shape'][:, 72:] - gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]).numpy() - + gender = torch.greater_equal(shape[:, 10] , 0.5).to(torch.long) + shape_offsets = torch.stack([torch.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], dims=[[1], [2]])[0,smpl.to_keep,:] for i in range(shape.shape[0])]).cpu().numpy() gt = [mesh_orig[i][mask[i], :] + shape_offsets[i, mask[i], :] for i in range(mask.shape[0])] - + mesh_unposed_shaped_levels = [[] for _ in range(mask.shape[0])] for i in range(len(output_levels)): mesh_unposed_shaped = [mesh_pred_levels[i][j, mask[j], :] + shape_offsets[j, mask[j]] for j in range(mask.shape[0])] for k in range(mask.shape[0]): mesh_unposed_shaped_levels[k].append(mesh_unposed_shaped[k]) - + # full res version mesh_unposed_shaped_full = np.zeros((mask.shape[0], config['smpl_res'], 3), dtype=np.float32) for i in range(mask.shape[0]): mesh_unposed_shaped_full[i, mask[i], :] = mesh_unposed_shaped[i] - - mesh_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_unposed_shaped_full).numpy() + mesh_posed = smpl(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], torch.tensor(mesh_unposed_shaped_full, device=config['device']))[0].cpu().numpy() else: mesh_posed = mesh_pred_levels[-1] gt = [mesh_orig[i][mask[i], :] for i in range(mesh_posed.shape[0])] @@ -467,7 +484,7 @@ def plot_everything(batch: dict, type: str): gt_posed = [mesh_orig_posed[i, mask[i], :] for i in range(mask.shape[0])] - mesh_posed_fixed = fix_collision(mesh_posed, body, mask).numpy() + mesh_posed_fixed = fix_collision(torch.Tensor(mesh_posed).to('cuda'), torch.Tensor(body).to('cuda'), torch.Tensor(mask).to('cuda')).cpu().numpy() mesh_posed = [mesh_posed[j, mask[j], :] for j in range(mask.shape[0])] @@ -477,7 +494,7 @@ def plot_everything(batch: dict, type: str): collision_color = [np.ones_like(mesh_posed[i], dtype=np.int32)*230 for i in range(len(mesh_posed))] else: collision = [np.concatenate((body[i], mesh_posed[i]), axis=0) for i in range(len(mesh_posed))] - collision_faces = [np.concatenate((F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))] + collision_faces = [np.concatenate((_F, faces[i] + config['smpl_res']), axis=0) for i in range(len(mesh_posed))] collision_color = [np.concatenate((np.ones_like(body[i], dtype=np.int32)*100, np.ones_like(mesh_posed[i], dtype=np.int32)*230), axis=0) for i in range(len(mesh_posed))] figs = { type + "/garment_" + str(i): plot_3d(gt[i], mesh_unposed_shaped_levels[i], faces[i], gt_posed[i], collision[i], collision_faces[i], collision_color[i]) for i in range(4) } @@ -487,7 +504,7 @@ def plot_everything(batch: dict, type: str): else: garment_posed_fixed = [mesh_posed_fixed[i, mask[i], :] for i in range(body.shape[0])] collision_fixed = [np.concatenate((body[i], garment_posed_fixed[i]), axis=0) for i in range(len(mesh_posed))] - gt_posed = [batch['mesh_posed'].numpy()[i, mask[i], :] for i in range(mask.shape[0])] + gt_posed = [batch['mesh_posed'].cpu().numpy()[i, mask[i], :] for i in range(mask.shape[0])] collision_gt = [np.concatenate((body[i], gt_posed[i]), axis=0) for i in range(len(gt_posed))] figs_coll = { type + "/garment_" + str(i) + '_collision': plot_3d_collision(collision_gt[i], collision[i], collision_fixed[i], collision_faces[i], collision_color[i]) for i in range(4) } @@ -505,7 +522,7 @@ def sample(folder): pred = model.sample(batch['uv_static'][0], batch['uv_body_posed'][0], uv_curvature[0], batch['uv_mask'][0], nr_of_samples=nr_of_samples) pose, shape = batch['pose_shape'][0, :72], batch['pose_shape'][0, 72:] - pose, shape = tf.tile(pose[tf.newaxis,:], [nr_of_samples,1]), tf.tile(shape[tf.newaxis,:], [nr_of_samples,1]) + pose, shape = tf.tile(pose[None,:], [nr_of_samples,1]), tf.tile(shape[None,:], [nr_of_samples,1]) mesh_pred = uv2mesh(tf.transpose(pred, [0,3,1,2])) mesh_posed = smpl.run_garment(pose, shape, mesh_pred).numpy() @@ -706,13 +723,13 @@ def generate_results(): shape = batch['pose_shape'][:, 72:] gender = tf.cast(tf.greater_equal(shape[:, 10] , 0.5), tf.int32) - shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][tf.newaxis, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) + shape_offsets = tf.stack([tf.gather(tf.tensordot(shape[i,:10][None, :], smpl.shapedirs[gender[i]], axes=[[1], [2]])[0,:,:], smpl.to_keep, axis=0) for i in range(shape.shape[0])]) i = -1 pred = out_levels[i][0] mesh_pred = uv2mesh(pred) - mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,tf.newaxis] + mesh_pred_shaped = mesh_pred + shape_offsets * batch['mesh_mask'][:,:,None] mesh_pred_posed = smpl.run_garment(batch['pose_shape'][:, :72], batch['pose_shape'][:, 72:], mesh_pred_shaped) for i in range(batch['id'].shape[0]): @@ -725,157 +742,117 @@ def generate_results(): pass -@tf.function def speed_step(levels_input, conds): return model.sample([levels_input, conds], training=False) +def train(): + global g_balancing_coeff + global step + valid_iterator = iter(valid_dataloader) + + for batch in train_dataloader: + train_loss = train_step(batch) + train_accumulator.update(train_loss) + + if step % 25 == 0: + data_valid = next(valid_iterator) + valid_loss = valid_step(data_valid) + valid_accumulator.update(valid_loss) + + if step % 1000 == 0 or (step < 1000 and step % 100 == 0): + to_log = dict({ **train_loss, **valid_loss, **{ 'current_step': step } }) + if step % 5000 == 0 or (step < 5000 and step % 1000 == 0): + train_figs = plot_everything(batch, 'train') + valid_figs = plot_everything(data_valid, 'valid') + to_log = { **to_log, **train_figs, **valid_figs } + if step == 0: + to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } } + + if not args['debug']: + wandb.log(to_log, step=step) + train_accumulator.reset() + valid_accumulator.reset() + print(step) + + if train_loss['train/euclid_error'] < config['balancing_activation_limit']: + g_balancing_coeff += 1 / 10000 + + if step % 10000 == 0: + ckpt_saver(model, step, optimizer, None) + + step += 1 + + if __name__ == '__main__': - # init_wandb() - parser = argparse.ArgumentParser(description='') - parser.add_argument('--name', type=str, default='lhunor') - args = vars(parser.parse_args()) + if not args['debug']: + init_wandb() - # config_file_names = [key for key in sys.modules.keys() if key.startswith('configs.')] - # assert len(config_file_names) == 1 - # config_file_name = config_file_names[0] - # # assert config_file_name.split('.')[1].endswith(args.name) - # assert config_file_name.split('.')[1].endswith(config['name']) - - smpl = SMPL(orig_smpl=config['is_cape']) + use_amp = True + smpl = SMPL(orig_smpl=config['is_cape'], path='smpl', device=config['device']) skirt_modifier = '_skirt' if config['is_skirt'] else '' dataset_resolutions = config['pyramid']['resolutions'].copy() if 512 not in dataset_resolutions: dataset_resolutions.append(512) - factory = DatasetFactory() - dataset_train = factory.get_dataset(folder=config['train_dir'], - batch_size=config['batch_size'], - # batch_size=1, - signature=config['signature_dynamic'], - resolutions=dataset_resolutions, - in_memory=config['dataset_in_memory'], - is_cape=config['is_cape'], - frames_file=config['frames_file'] if 'frames_file' in config.keys() else None) - static_dataset_train = StaticDataset(folder=config['train_dir'], - signature=config['signature_static'], - resolutions=dataset_resolutions, - in_memory=True, - is_cape=config['is_cape']) - dataset_valid = factory.get_dataset(folder=config['valid_dir'], - batch_size=config['batch_size'], - signature=config['signature_dynamic'], - resolutions=dataset_resolutions, - in_memory=config['dataset_in_memory'], - is_cape=config['is_cape'], - frames_file=config['frames_file_valid'] if 'frames_file_valid' in config.keys() else None) - static_dataset_valid = StaticDataset(folder=config['valid_dir'], - signature=config['signature_static'], - resolutions=dataset_resolutions, - in_memory=True, - is_cape=config['is_cape']) + dataset_train = Dataset(config['train_dir'], config['signature'], device=config['device'], frames_file=config['train_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + dataset_valid = Dataset(config['valid_dir'], config['signature'], device=config['device'], frames_file=config['valid_frames'], use_cache=config['dataset_in_memory'], resolutions=dataset_resolutions, is_cape=config['is_cape']) + train_dataloader = DataLoader(dataset_train, batch_size=4, drop_last=True, shuffle=True, ) + valid_dataloader = DataLoader(dataset_valid, batch_size=4, drop_last=True, shuffle=True) + train_accumulator = Accumulator() + valid_accumulator = Accumulator() model: Pyramid = Pyramid(config) - optimizer = tf.optimizers.Adam(learning_rate=config['lr']) - balancing_coeff = config['starting_balancing_coeff'] + optimizer = optim.Adam(model.parameters(), lr=config['lr']) + _MSSSIM = MS_SSIM(data_range=2, size_average=True, channel=3) + ckpt_saver = CheckpointSaver('checkpoints/iccv/torch/' + config['name'], top_n=5) + scaler = torch.cuda.amp.GradScaler(enabled=use_amp) + + g_balancing_coeff = config['starting_balancing_coeff'] reg_coeff = 1 - valid_iterator = iter(dataset_valid) - gamma = 1 - balancing_activated_step = 0 - - # sample('checkpoints/cvae_13') - # test() - - # generate_results() - - ckpt = tf.train.Checkpoint(model=model) - manager = tf.train.CheckpointManager(ckpt, 'checkpoints/' + config['name'], max_to_keep=20) - - # load_model(model, 'checkpoints/pyr_abl_32_skirt', iteration='180000') + step = 0 if config['pretrained_model'] != '': # assert len(config['pyramid']['resolutions']) == 1 - load_model(model, config['pretrained_model'], iteration=config['pretrained_model_iteration']) + step = load_model(model, config['pretrained_model'], optimizer=optimizer, scaler=scaler, iteration=config['pretrained_model_iteration']) + + if not args['debug']: + model = torch.compile(model) + wandb.watch(model, log='all', log_freq=1000, log_graph=True) + if len(config['pyramid']['resolutions']) == 1: - model.static_enc.trainable = False - model.body_enc.trainable = False - model.curv_enc.trainable = False + for param in model.static_enc.parameters(): param.requires_grad = False + for param in model.body_enc.parameters(): param.requires_grad = False + for param in model.curv_enc.parameters(): param.requires_grad = False else: load_model(model, config['pyramid']['pretrained_pyramid'], iteration=(config['pyramid']['pretrained_pyramid_iteration'] if 'pretrained_pyramid_iteration' in config.keys() else '')) - model.static_enc.trainable = False - model.body_enc.trainable = False - model.curv_enc.trainable = False - model.cond_encoder.trainable = False + for param in model.static_enc.parameters(): param.requires_grad = False + for param in model.body_enc.parameters(): param.requires_grad = False + for param in model.curv_enc.parameters(): param.requires_grad = False # load_model(model.levels[0].upscale_enhancer, config['pyramid']['levels'][0]['upscale_enhancer']) # model.levels[0].upscale_enhancer.trainable = False + # for i in range(len(model.levels)-1): + # load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer']) + # model.levels[i].upscale_enhancer.trainable = False + # if config['pyramid']['resolutions'][-1] != 512: + # load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) + # model.upscale_enhancer.trainable = False for i in range(len(model.levels)-1): - load_model(model.levels[i].upscale_enhancer, config['pyramid']['levels'][i]['upscale_enhancer']) - model.levels[i].upscale_enhancer.trainable = False - if config['pyramid']['resolutions'][-1] != 512: - load_model(model.upscale_enhancer, config['pyramid']['final_upscale_enhancer']) - model.upscale_enhancer.trainable = False - - for i in range(len(model.levels)-1): - model.levels[i].trainable = False + for param in model.levels[i].parameters(): param.requires_grad = False # load_model(model.cond_encoder, config['pyramid']['pretrained_pyramid']) # load_model(model.levels[0], config['pyramid']['pretrained_pyramid']) # load_model(model.levels[-1], 'checkpoints/cvae_19') + if not args['debug']: + model = torch.compile(model) + wandb.watch(model, log='all', log_freq=1000, log_graph=True) - step = 0 - times = [] - for batch in dataset_train: - batch = static_dataset_train.expand_batch(batch_to_dict(batch, config['signature_dynamic'])) - - # levels_input, conds = group_inputs_for_levels(batch, config) - - # start = time.perf_counter() - # out = speed_step(levels_input, conds) - # t = time.perf_counter() - start - # print(t) - # times.append(t) - - # if step > 200: - # break - - - train_loss = train_step(batch) - - data_valid = valid_iterator.get_next() - data_valid = static_dataset_valid.expand_batch(batch_to_dict(data_valid, config['signature_dynamic'])) - valid_loss = valid_step(data_valid) - - to_log = { **train_loss, **valid_loss, **{ 'current_step': step} } - if step % 5000 == 0 or (step < 5000 and step % 500 == 0): - train_figs = plot_everything(batch, 'train') - valid_figs = plot_everything(data_valid, 'valid') - to_log = { **to_log, **train_figs, **valid_figs } - - if step % 5000 == 0: - manager.save(checkpoint_number=step) - if step == 0: - to_log = { **to_log, **{ 'model/summary': wandb.Html(get_summary_html(model)) } } - - if train_loss['train/euclid_error'] < 0.004: - if balancing_activated_step == 0: - balancing_activated_step = step - balancing_coeff = balancing_coeff + 1 / 20000 - - - to_log = { **to_log, **{ 'train/balancing_coeff': balancing_coeff, 'train/gamma': gamma } } - - wandb.log(to_log, step = step) - - print(step) - - step += 1 - # print('mean:') - # print(np.mean(times[1:])) \ No newline at end of file + train() \ No newline at end of file diff --git a/utils/postprocess.py b/utils/postprocess.py index d6e2d2d..53e3c15 100644 --- a/utils/postprocess.py +++ b/utils/postprocess.py @@ -25,8 +25,7 @@ to_keep = sio.loadmat('smpl/keep_remove.mat')['keep'].reshape(-1) F_fix_coll = torch.tensor(np.tile(np.load("smpl/smpl_faces.npy")[to_keep,:][None,:,:], [4,1,1]), device='cuda') - -def fix_collision(V, B, mask, thr=.004): +def fix_collision(V: torch.Tensor, B: torch.Tensor, mask: torch.Tensor, thr=.004): mesh = Meshes(B, F_fix_coll) B_vn = torch.stack(mesh.verts_normals_list())