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 from models.cvae_model import CVAE from models.pyramid_level import PyramidLevel 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']),]) 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 = UpscalerBasicConv(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=None): 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=None): 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, mean, logvar = self.levels[0](levels_input[0], z_cond, training=training) # 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]) 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] ] # 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=None): # 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=None): # 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