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 convnext.models.convnext_tf import ConvNeXt, Block, ConvNeXtReverseLabels from auto_encoder_body import AutoEncoder as BodyAE from auto_encoder_static import AutoEncoder as StaticAE class Bottleneck(tf.keras.Model): def __init__(self, dim): super(Bottleneck, self).__init__() self.bottleneck = tf.keras.Sequential( [Block(dim=dim, drop_path=0, layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)] ) def call(self, inputs, training=None): x = inputs x = self.bottleneck(x, training=training) return x class Encoder(tf.keras.Model): def __init__(self, latent_dim): super(Encoder, self).__init__() self.encoder = ConvNeXt(depths=[3, 3, 9, 3], dims=[32, 64, 128, 256], include_top=False) self.flatten = tf.keras.layers.Flatten() self.mean = tf.keras.layers.Dense(latent_dim) self.log_var = tf.keras.layers.Dense(latent_dim) def call(self, inputs, training=None): x = inputs x = self.encoder(x) x = self.flatten(x) mean = self.mean(x) log_var = self.log_var(x) return mean, log_var class Decoder(tf.keras.Model): def __init__(self): super(Decoder, self).__init__() self.dense = tf.keras.layers.Dense(16 * 8 * 80) self.reshape = tf.keras.layers.Reshape((16, 8, 80)) self.decoder = ConvNeXtReverseLabels(depths=list(reversed([3, 3, 9, 3])), dims=list(reversed([256, 128, 64, 16]))) def call(self, inputs, training=None): x = inputs x = self.dense(x) x = self.reshape(x) x = self.decoder(x) return x class CVAE(tf.keras.Model): def __init__(self, latent_dim=128, static_model='checkpoints/ae_static_3', body_model='checpoints/ae_body_6',): super(CVAE, self).__init__() self.latent_dim = latent_dim model : StaticAE = StaticAE(size=512) load_model(model, static_model) self.static_enc = tf.keras.Sequential([model.encoder, model.bottleneck]) self.static_enc.trainable = False model : BodyAE = BodyAE(size=512) load_model(model, body_model) self.body_enc = tf.keras.Sequential([model.encoder, model.bottleneck]) self.body_enc.trainable = False self.cond_encoder = tf.keras.Sequential([tf.keras.layers.Dense(256, activation='relu'), tf.keras.layers.Dense(256, activation='relu'), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dense(latent_dim),]) self.encoder = Encoder(latent_dim) self.decoder = Decoder() # @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, 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): if uv_template.shape[1] == 3: uv_template = tf.transpose(uv_template, [0,2,3,1]) if uv_body_posed.shape[1] == 3: uv_body_posed = 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) return z_cond def sample(self, uv_template, uv_body_posed, uv_mask=None, noise=None): if noise is None: eps = tf.random.normal(shape=(uv_template.shape[0], self.latent_dim)) else: eps = noise z_cond = self.encode_conds(uv_template, uv_body_posed) z = tf.concat([eps, z_cond], axis=-1) x = self.decoder(z) if uv_mask is not None: x = x * uv_mask[:,:,:,tf.newaxis] 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): eps = tf.random.normal(shape=mean.shape) return eps * tf.exp(logvar * .5) + mean def decode(self, z, apply_sigmoid=False): logits = self.decoder(z) if apply_sigmoid: probs = tf.sigmoid(logits) return probs return logits def call(self, inputs, training=None): uv_template, uv_body_posed, uv_curv, uv_mask = inputs if uv_template.shape[1] == 3: uv_template = tf.transpose(uv_template, [0,2,3,1]) if uv_body_posed.shape[1] == 3: uv_body_posed = tf.transpose(uv_body_posed, [0,2,3,1]) if uv_curv.shape[1] == 3: uv_curv = tf.transpose(uv_curv, [0,2,3,1]) z_cond = self.encode_conds(uv_template, uv_body_posed) x = tf.concat([uv_template, uv_body_posed, uv_curv], axis=-1) mean, logvar = self.encoder(x) z = self.reparameterize(mean, logvar) z = tf.concat([z, z_cond], axis=-1) x = self.decoder(z) x = x * uv_mask[:,:,:,tf.newaxis] return x, mean, logvar, z