luni/cvpr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

working pyramid pipeline

Browse Source
This commit is contained in:
luni
2022-09-27 21:26:15 +00:00
parent 1da83294ee
commit fa8f24f0c5
10 changed files with 997 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/cvae_model.py
+6 -5
View File
@@ -15,7 +15,7 @@ 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 : 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'])
@@ -35,6 +35,11 @@ class CVAE(tf.keras.Model):
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['latent_dim']),])
self.encoder = VariationalEncoder(config['cvae']['latent_dim'], config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
self.decoder = Decoder(config['cvae']['decoder_input'], config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
@@ -43,10 +48,6 @@ class CVAE(tf.keras.Model):
else:
self.avg_garment = None
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['latent_dim']),])
# @tf.function
models/pyramid_level.py
+97
View File
@@ -0,0 +1,97 @@
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 AEEncoder, VariationalEncoder, Decoder
from models.upscaler import UpscalerBasic
class PyramidLevel(tf.keras.Model):
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.upscale_enhancer = None
if config['upscale_enhancer'] != '':
self.upscale_enhancer = UpscalerBasic(512, config['resolution'])
load_model(self.upscale_enhancer, config['upscale_enhancer'])
self.upscale_enhancer = tf.keras.Sequential([
self.upscale_enhancer.flatten,
self.upscale_enhancer.seq,
self.upscale_enhancer.reshape
])
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, training=training)
x = x * (1 - mask[:,:,:,tf.newaxis])
low = x + low
return low
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 = 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, fix_noise=False):
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])
return eps * tf.exp(logvar * .5) + mean
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)
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
models/pyramid_model.py
+70
View File
@@ -0,0 +1,70 @@
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
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']))]
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):
uv_static, uv_body, uv_curv = inputs[-1][1], inputs[-1][2], inputs[-1][3]
z_cond = self.encode_conds(uv_static, uv_body, uv_curv)
out_levels = []
pred, mean, logvar = self.levels[0](inputs[0], z_cond, training=training)
out_levels.append([pred, mean, logvar])
for i in range(1, len(self.levels)):
pred_level, mean, logvar = self.levels[i](inputs[i], z_cond, training=training)
pred = pred + pred_level
out_levels.append([pred, mean, logvar])
return out_levels