commit all

models/pyramid_level.py

@@ -8,7 +8,7 @@ import scipy as sp
 # import plotly.express as ex
 
 from custom_utils.custom_utils import load_model
-from models.base import AEEncoder, VariationalEncoder, Decoder
+from models.base import AEEncoder, VariationalEncoder, Decoder, VariationalEncoderNew, DecoderNew
 from models.upscaler import UpscalerBasic, UpscalerBasicConv, UpscalerBasicNew
 
 
@@ -24,7 +24,8 @@ class PyramidLevel(tf.keras.Model):
 
         self.upscale_enhancer = None
         if config['upscale_enhancer'] != '':
-            self.upscale_enhancer = UpscalerBasicConv(config['resolution'])
+            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']
 
@@ -57,13 +58,17 @@ class PyramidLevel(tf.keras.Model):
         return x
 
 
-    def reparameterize(self, mean, logvar, fix_noise=False):
-        if not fix_noise:
-            eps = tf.random.normal(shape=mean.shape)
+    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:
-            eps = tf.random.normal(shape=(1, mean.shape[1]))
-            eps = tf.tile(eps, [mean.shape[0],1])
-        return eps * tf.exp(logvar * .5) + mean
+            out = tf.exp(logvar * .5) + mean
+        return out
 
 
     def call(self, inputs, z_cond, training=None):
@@ -71,7 +76,7 @@ class PyramidLevel(tf.keras.Model):
 
         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 = self.reparameterize(mean, logvar, training)
 
         z = tf.concat([z, z_cond], axis=-1)
         x = self.decoder(z, training=training)
@@ -89,3 +94,88 @@ class PyramidLevel(tf.keras.Model):
 
         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 = 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]
+
+        # 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