separate sub models from their training (wip)

models/ae_body_model.py

@@ -77,4 +77,147 @@ class AutoEncoder(tf.keras.Model):
         # x = x * uv_mask[:,:, tf.newaxis]
         # x = x * uv_mask_body[tf.newaxis,tf.newaxis,:,:]
 
+        return x
+
+
+
+class Bottleneck32(tf.keras.Model):
+    
+    def __init__(self, dim, latent_dim):
+        super(Bottleneck32, 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)]
+            )
+        self.flatten = tf.keras.layers.Flatten()
+        self.dense = tf.keras.layers.Dense(latent_dim)
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = self.bottleneck(x)
+        x = self.flatten(x)
+        x = self.dense(x)
+        
+        return x
+
+
+class Decoder32(tf.keras.Model):
+    
+    def __init__(self, bottleneck_size, latent_dim):
+        super(Decoder32, self).__init__()
+
+        self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size)
+        self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size))
+        self.decoder = ConvNeXtReverse(depths=list(reversed([27, 27])), dims=list(reversed([bottleneck_size, 256])))
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = self.dense(x)
+        x = self.reshape(x)
+        x = self.decoder(x)
+
+        return x
+
+
+class AutoEncoder32(tf.keras.Model):
+    
+    def __init__(self):
+        super(AutoEncoder32, self).__init__()
+
+
+        bottleneck_size = 512
+        latent_dim = 128
+
+        self.encoder = ConvNeXt(depths=[27, 27], dims=[256, bottleneck_size], include_top=False)
+        self.bottleneck = Bottleneck32(bottleneck_size, latent_dim)
+        self.decoder = Decoder32(bottleneck_size, latent_dim)
+
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = tf.transpose(x, [0,2,3,1])
+        x = self.encoder(x, training=training)
+
+        x = self.bottleneck(x, training=training)
+
+        x = self.decoder(x, training=training)
+        # x = tf.image.resize(x, (512, 256), tf.image.ResizeMethod.LANCZOS5)
+        x = tf.transpose(x, [0,3,1,2])
+
+        return x
+
+
+
+
+class Bottleneck128(tf.keras.Model):
+    
+    def __init__(self, dim, latent_dim):
+        super(Bottleneck128, 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)]
+            )
+        self.flatten = tf.keras.layers.Flatten()
+        self.dense = tf.keras.layers.Dense(latent_dim)
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = self.bottleneck(x)
+        x = self.flatten(x)
+        x = self.dense(x)
+        
+        return x
+
+
+class Decoder128(tf.keras.Model):
+    
+    def __init__(self, bottleneck_size, latent_dim):
+        super(Decoder128, self).__init__()
+
+        self.dense = tf.keras.layers.Dense(4 * 2 * bottleneck_size)
+        self.reshape = tf.keras.layers.Reshape((4, 2, bottleneck_size))
+        self.decoder = ConvNeXtReverse(depths=list(reversed([16, 16, 9, 9])), dims=list(reversed([bottleneck_size, 256, 128, 64])))
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = self.dense(x)
+        x = self.reshape(x)
+        x = self.decoder(x)
+
+        return x
+
+
+class AutoEncoder128(tf.keras.Model):
+    
+    def __init__(self):
+        super(AutoEncoder128, self).__init__()
+
+
+        bottleneck_size = 512
+        latent_dim = 128
+
+        self.encoder = ConvNeXt(depths=[16, 16, 9, 9], dims=[64, 128, 256, bottleneck_size], include_top=False)
+        self.bottleneck = Bottleneck128(bottleneck_size, latent_dim)
+        self.decoder = Decoder128(bottleneck_size, latent_dim)
+
+
+    def call(self, inputs, training=None):
+        x = inputs
+
+        x = tf.transpose(x, [0,2,3,1])
+        x = self.encoder(x, training=training)
+
+        x = self.bottleneck(x, training=training)
+
+        x = self.decoder(x, training=training)
+        # x = tf.image.resize(x, (512, 256), tf.image.ResizeMethod.LANCZOS5)
+        x = tf.transpose(x, [0,3,1,2])
+
         return x