fixed feature sizes, cvae working

models/base.py

@@ -1,6 +1,6 @@
 import tensorflow as tf
 from convnext.models.convnext_tf import ConvNeXt, ConvNeXtReverse, Block, ConvNeXtReverseLabels
-from models.resnet import resnet_18
+from models.resnet import resnet_18, make_basic_block_layer
 
 
 class Bottleneck(tf.keras.Model):
@@ -113,20 +113,18 @@ class Decoder(tf.keras.Model):
 
 class VariationalEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7):
+    def __init__(self, features):
         super(VariationalEncoderNew, self).__init__()
 
-        self.encoder = ConvNeXt(depths=depths, dims=dims, include_top=False, kernel_size=kernel_size)
+        self.encoder = resnet_18(features)
 
-        self.mean_branch = tf.keras.Sequential(
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-            )
+        self.mean_branch = make_basic_block_layer(filter_num=features,
+                                             blocks=2,
+                                             stride=1)
 
-        self.var_branch = tf.keras.Sequential(
-                [Block(dim=64, drop_path=0, kernel_size=kernel_size,
-                       layer_scale_init_value=1e-6, prefix=f'bottleneck{j}') for j in range(5)]
-            )
+        self.var_branch = make_basic_block_layer(filter_num=features,
+                                             blocks=2,
+                                             stride=1)
 
         self.flatten_mean = tf.keras.layers.Flatten()
         self.flatten_var = tf.keras.layers.Flatten()
@@ -149,10 +147,10 @@ class VariationalEncoderNew(tf.keras.Model):
 
 class AEEncoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, activation='tanh'):
+    def __init__(self, features, activation='tanh'):
         super(AEEncoderNew, self).__init__()
 
-        self.encoder = resnet_18()
+        self.encoder = resnet_18(features)
         self.act = tf.keras.layers.Activation(activation)
 
 
@@ -173,15 +171,15 @@ class AEEncoderNew(tf.keras.Model):
 
 class DecoderNew(tf.keras.Model):
     
-    def __init__(self, depths, dims, kernel_size=7, is_label=False):
+    def __init__(self, features, is_label=False, is_cvae=False):
         super(DecoderNew, self).__init__()
 
         self.is_label = is_label
 
         if not is_label:
-            self.decoder = resnet_18(reversed=True)
+            self.decoder = resnet_18(features, reversed=True, is_cvae=is_cvae)
         else:
-            self.decoder = resnet_18(reversed=True, labels=6)
+            self.decoder = resnet_18(features, reversed=True, labels=6, is_cvae=is_cvae)
             
 
     def call(self, inputs, training):

models/cond_encoder.py

@@ -25,8 +25,8 @@ class AutoEncoderNew(tf.keras.Model):
     def __init__(self, config):
         super(AutoEncoderNew, self).__init__()
 
-        self.encoder : AEEncoderNew = AEEncoderNew(config['encoder_depths'], config['encoder_dims'], config['kernel_size'], config['activation'])
-        self.decoder : DecoderNew = DecoderNew(config['decoder_depths'], config['decoder_dims'], kernel_size=config['kernel_size'], is_label=config['is_label'])
+        self.encoder : AEEncoderNew = AEEncoderNew(config['bottleneck_size'], config['activation'])
+        self.decoder : DecoderNew = DecoderNew(config['bottleneck_size'], is_label=config['is_label'])
 
 
     def call(self, inputs, training):

models/cvae_model.py

@@ -159,16 +159,16 @@ class CVAENew(tf.keras.Model):
         self.size = config['resolution']
 
         if not('only_curvatures' in config.keys() and config['only_curvatures'] == True):
-            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'])
+            self.static_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_static']['bottleneck_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'])
+            self.body_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_body']['bottleneck_size'])
             if config['body_model'] != '':
                 load_model(self.body_enc, config['body_model'] + '_enc')
 
         if config['use_curvature']:
-            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['encoder_depths'], config['cond_ae_curv']['encoder_dims'], config['cond_ae_curv']['kernel_size'], config['cond_ae_curv']['activation'])
+            self.curv_enc : AEEncoderNew = AEEncoderNew(config['cond_ae_curv']['bottleneck_size'], config['cond_ae_curv']['activation'])
             if config['curvature_model'] != '':
                 load_model(self.curv_enc, config['curvature_model'] + '_enc')
 
@@ -179,10 +179,10 @@ class CVAENew(tf.keras.Model):
             if config['use_curvature']:
                 self.curv_enc.trainable = False
 
-        self.encoder = VariationalEncoderNew(config['cvae']['encoder_depths'], config['cvae']['encoder_dims'], kernel_size=config['cvae']['kernel_size'])
-        self.decoder = DecoderNew(config['cvae']['decoder_depths'], config['cvae']['decoder_dims'], config['cvae']['kernel_size'])
+        self.encoder = VariationalEncoderNew(config['cvae']['encoder_dims'][-1])
+        self.decoder = DecoderNew(config['cvae']['decoder_dims'][-1], is_cvae=True)
 
-        self.reshape = tf.keras.layers.Reshape((8, 4, 64))
+        self.reshape = tf.keras.layers.Reshape((16, 8, config['cvae']['decoder_dims'][-1]))
 
         if config['avg_garment_path'] != '':
             self.avg_garment = np.load(config['avg_garment_path'])

models/resnet.py

@@ -116,7 +116,7 @@ def make_bottleneck_layer(filter_num, blocks, stride=1):
 
 
 class ResNetTypeI(tf.keras.Model):
-    def __init__(self, layer_params, reversed=False, labels=None):
+    def __init__(self, layer_params, features, reversed=False, labels=None, is_cvae=False):
         super(ResNetTypeI, self).__init__()
         self.reversed = reversed
         self.labels = labels
@@ -153,7 +153,7 @@ class ResNetTypeI(tf.keras.Model):
                                              blocks=layer_params[2],
                                              stride=2,
                                              upsample=reversed)
-        self.layer4 = make_basic_block_layer(filter_num=512,
+        self.layer4 = make_basic_block_layer(filter_num=features if not is_cvae else features*2,
                                              blocks=layer_params[3],
                                              stride=2 if not reversed else 1,
                                              upsample=reversed)
@@ -228,8 +228,8 @@ class ResNetTypeII(tf.keras.Model):
         return output
 
 
-def resnet_18(reversed=False, labels=None):
-    return ResNetTypeI(layer_params=[2, 2, 2, 2], reversed=reversed, labels=labels)
+def resnet_18(features, reversed=False, labels=None, is_cvae=False):
+    return ResNetTypeI(layer_params=[2, 2, 2, 2], features=features, reversed=reversed, labels=labels, is_cvae=is_cvae)
 
 
 def resnet_34():