tried testing (unsuccessfully)

2 files changed, 10 insertions, 8 deletions

diff --git a/__pycache__/losses.cpython-38.pyc b/__pycache__/losses.cpython-38.pyc
index e157ea9c..67d4f227 100644
--- a/__pycache__/losses.cpython-38.pyc
+++ b/__pycache__/losses.cpython-38.pyc
diff --git a/losses.py b/losses.py
index 297bd2f1..e39d0f8e 100644
--- a/losses.py
+++ b/losses.py
@@ -12,13 +12,13 @@ class YourModel(tf.keras.Model):
     def __init__(self, content_image, style_image): #normalize these images to float values
         super(YourModel, self).__init__()
        
-        self.content_image = transform.resize(content_image, np.shape(style_image), anti_aliasing=True)
-        self.content_image = np.expand_dims(self.content_image, axis=0)
+        self.content_image = transform.resize(content_image, tf.shape(style_image), anti_aliasing=True)
+        self.content_image = tf.expand_dims(self.content_image, axis=0)
 
         #perhaps consider cropping to avoid distortion
-        self.style_image = transform.resize(style_image, np.shape(style_image), anti_aliasing=True)
-        self.style_image = np.expand_dims(self.style_image, axis=0)
-        self.x = tf.Variable(tf.random.uniform(np.shape(content_image)), trainable=True) 
+        self.style_image = transform.resize(style_image, tf.shape(style_image), anti_aliasing=True)
+        self.style_image = tf.expand_dims(self.style_image, axis=0)
+        self.x = tf.Variable(tf.random.uniform(tf.shape(content_image)), trainable=True) 
         self.x = tf.expand_dims(self.x, axis=0)
         self.alpha = hp.alpha
         self.beta = hp.beta
@@ -85,7 +85,7 @@ class YourModel(tf.keras.Model):
             if layer.name in self.desired:
                 layers = np.append(layers, x)
             
-        return x, layers
+        return x, tf.Variable(layers, dtype=np.float32)
 
     def loss_fn(self, p, a, x):
         _, photo_layers = self.call(p)
@@ -98,7 +98,7 @@ class YourModel(tf.keras.Model):
         return (self.alpha * content_l) + (self.beta * style_l)
         
     def content_loss(self, photo_layers, input_layers):
-        L_content = np.mean(np.square(photo_layers - input_layers))
+        L_content = tf.reduce_mean(tf.square(photo_layers - input_layers))
         print('content loss', L_content)
         return L_content
     
@@ -116,13 +116,14 @@ class YourModel(tf.keras.Model):
             for j in range(input_dim):
                 k = np.dot(input_layers[i], art_layers[j])
                 G[i,j] = k
+        G = tf.Variable(G, dtype=np.float32)
 
         # get the loss per each lateral layer
         # N depends on # of filters in the layer, M depends on hight and width of feature map
         M_l = art_layers.shape[0] * art_layers.shape[1]
         
         # layer.filters might not work
-        E_l = 1/4 * (self.layer_to_filters[layer.name]**(-2)) * (M_l**(-2)) * np.sum(np.square(G - input_layers))
+        E_l = 1/4 * (self.layer_to_filters[layer.name]**(-2)) * (M_l**(-2)) * tf.reduce_sum(tf.square(G - input_layers))
 
         # while Sotech is botty:
         #         Jayson_tatum.tear_acl()
@@ -141,6 +142,7 @@ class YourModel(tf.keras.Model):
        with tf.GradientTape() as tape:
               loss = self.loss_fn(self.content_image, self.style_image, self.x)
        print('loss', loss)
+       print('self.x', self.x)
        gradients = tape.gradient(loss, self.x)
        print('gradients', gradients)
        self.optimizer.apply_gradients(zip(gradients, self.x))