Correct typo of "preiod" mistake to "period" in 6 files (keras-team#1536

)

*Correct typo mistake in 6 files, which the word should be "period" and not "preiod".

examples/generative/dreambooth.py

@@ -457,9 +457,9 @@ def train_step(self, inputs):
 
     def get_timestep_embedding(self, timestep, dim=320, max_period=10000):
         half = dim // 2
-        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))
+        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))
         freqs = tf.math.exp(
-            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half
+            -log_max_period * tf.range(0, half, dtype=tf.float32) / half
         )
         args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs
         embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)

examples/generative/finetune_stable_diffusion.py

@@ -326,9 +326,9 @@ def train_step(self, inputs):
 
     def get_timestep_embedding(self, timestep, dim=320, max_period=10000):
         half = dim // 2
-        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))
+        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))
         freqs = tf.math.exp(
-            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half
+            -log_max_period * tf.range(0, half, dtype=tf.float32) / half
         )
         args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs
         embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)

examples/generative/ipynb/dreambooth.ipynb

@@ -676,9 +676,9 @@
     "\n",
     "    def get_timestep_embedding(self, timestep, dim=320, max_period=10000):\n",
     "        half = dim // 2\n",
-    "        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))\n",
+    "        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))\n",
     "        freqs = tf.math.exp(\n",
-    "            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half\n",
+    "            -log_max_period * tf.range(0, half, dtype=tf.float32) / half\n",
     "        )\n",
     "        args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs\n",
     "        embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)\n",

examples/generative/ipynb/finetune_stable_diffusion.ipynb

@@ -446,9 +446,9 @@
     "\n",
     "    def get_timestep_embedding(self, timestep, dim=320, max_period=10000):\n",
     "        half = dim // 2\n",
-    "        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))\n",
+    "        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))\n",
     "        freqs = tf.math.exp(\n",
-    "            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half\n",
+    "            -log_max_period * tf.range(0, half, dtype=tf.float32) / half\n",
     "        )\n",
     "        args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs\n",
     "        embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)\n",

examples/generative/md/dreambooth.md

@@ -493,9 +493,9 @@ class DreamBoothTrainer(tf.keras.Model):
 
     def get_timestep_embedding(self, timestep, dim=320, max_period=10000):
         half = dim // 2
-        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))
+        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))
         freqs = tf.math.exp(
-            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half
+            -log_max_period * tf.range(0, half, dtype=tf.float32) / half
         )
         args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs
         embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)

examples/generative/md/finetune_stable_diffusion.md

@@ -410,9 +410,9 @@ class Trainer(tf.keras.Model):
 
     def get_timestep_embedding(self, timestep, dim=320, max_period=10000):
         half = dim // 2
-        log_max_preiod = tf.math.log(tf.cast(max_period, tf.float32))
+        log_max_period = tf.math.log(tf.cast(max_period, tf.float32))
         freqs = tf.math.exp(
-            -log_max_preiod * tf.range(0, half, dtype=tf.float32) / half
+            -log_max_period * tf.range(0, half, dtype=tf.float32) / half
         )
         args = tf.convert_to_tensor([timestep], dtype=tf.float32) * freqs
         embedding = tf.concat([tf.math.cos(args), tf.math.sin(args)], 0)