import os import time import random import tensorflow as tf 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 AEEncoderNew, VariationalEncoderNew, DecoderNew class CVAE(tf.keras.Model): def __init__(self, config): super(CVAE, self).__init__() self.latent_dim = config['latent_dim'] self.latent_dim = config['cvae']['latent_dim'] self.size = config['resolution'] 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['static_model'] != '': load_model(self.static_enc, config['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['body_model'] != '': load_model(self.body_enc, config['body_model'] + '_enc') if config['freeze_encoders']: self.static_enc.trainable = False self.body_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(self.latent_dim, activation='tanh'),]) self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'], latent_dim=config['cvae']['latent_dim']) self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'], is_label=config['cvae']['is_label']) self.reshape = tf.keras.layers.Reshape((8, 4, config['cvae']['latent_dim'])) self.add_noise = config['cvae']['add_noise'] self.noise_amount = config['cvae']['noise_amount'] # @tf.function def sample_single(self, uv_template, uv_body_posed, uv_mask, eps=None, nr_of_samples=4): if eps is None: eps = tf.random.normal(shape=(nr_of_samples, 8, 4, self.latent_dim)) uv_template = tf.tile(tf.transpose(uv_template, [1,2,0])[tf.newaxis,:,:,:], [nr_of_samples,1,1,1]) uv_body_posed = tf.tile(tf.transpose(uv_body_posed, [1,2,0])[tf.newaxis,:,:,:], [nr_of_samples,1,1,1]) uv_mask = tf.tile(uv_mask[tf.newaxis,:,:], [nr_of_samples,1,1]) # uv_template, uv_body_posed = tf.transpose(uv_template, [0,2,3,1]), tf.transpose(uv_body_posed, [0,2,3,1]) z_static = self.static_enc(uv_template) z_body = self.body_enc(uv_body_posed) z_cond = tf.concat([z_static, z_body], axis=-1) z_cond = self.cond_encoder(z_cond) z = tf.concat([eps, z_cond], axis=-1) x = self.decoder(z) x = x * uv_mask[:,:,:,tf.newaxis] return x def encode_conds(self, uv_template, uv_body_posed, training): z_static = self.static_enc(uv_template, training=training) z_body = self.body_enc(uv_body_posed, training=training) z_cond = tf.concat([z_static, z_body], axis=-1) z_cond = self.cond_encoder(z_cond, training=training) return z_cond def sample(self, uv_template, uv_body_posed, uv_mask, noise=None): if noise is None: eps = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim)) else: eps = noise z_cond = self.encode_conds(uv_template, uv_body_posed, training=False) z = tf.concat([eps, z_cond], axis=-1) x = self.decoder([z, uv_mask], training=False) # x = x * uv_mask[:,:,:,tf.newaxis] # background = tf.ones((uv_template.shape[0],512,256,1)) * (1 - uv_mask[:,:,:,tf.newaxis]) # x = tf.concat((background, x), axis=-1) # x = tf.math.softmax(x) return x # encoders have to be the same for curv_vae and general CVAE def sample_without_encoding(self, z_static, z_body, uv_mask, eps=None): eps = tf.random.normal(shape=(z_static.shape[0], self.latent_dim)) z_cond = tf.concat([z_static, z_body], axis=-1) z = tf.concat([eps, z_cond], axis=-1) x = self.decoder(z) 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, training): uv_template, uv_body_posed, uv_curv, uv_mask = inputs x = tf.concat([uv_template, uv_body_posed, uv_curv], axis=-1) mean, logvar = self.encoder(x) z = self.reparameterize(mean, logvar, training=training) z = self.reshape(z) z_cond = self.encode_conds(uv_template, uv_body_posed, training=training) z = tf.concat([z, z_cond], axis=-1) x = self.decoder([z, uv_mask], training=training) # x = x * uv_mask[:,:,:,tf.newaxis] # background = tf.ones((4,512,256,1)) * (1 - uv_mask[:,:,:,tf.newaxis]) # x = tf.concat((background, x), axis=-1) # x = tf.math.softmax(x) return x, mean, logvar def call_sample(self, inputs): uv_template, uv_body_posed, uv_curv, uv_mask = inputs z = tf.random.normal(shape=(uv_template.shape[0], 8, 4, self.latent_dim)) z_cond = self.encode_conds(uv_template, uv_body_posed, training=False) z = tf.concat([z, z_cond], axis=-1) x = self.decoder([z, uv_mask], training=False) return x