pyramid available with 128 res

models/ae_static_model.py

@@ -121,3 +121,52 @@ class AutoEncoder32(tf.keras.Model):
         # x = x * uv_mask[:,tf.newaxis,:,:]
 
         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 = Bottleneck(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.transpose(x, [0,3,1,2])
+
+        # x = x * uv_mask[:,:, tf.newaxis]
+        # x = x * uv_mask[:,tf.newaxis,:,:]
+
+        return x