More pythonic way to find the longest sequence (#512)

* More pythonic way to find the longest sequence

* pep8 fix

Author: rasbt

appendix-E/01_main-chapter-code/previous_chapters.py

@@ -451,6 +451,9 @@ def _longest_encoded_length(self):
             if encoded_length > max_length:
                 max_length = encoded_length
         return max_length
+        # Note: A more pythonic version to implement this method
+        # is the following, which is also used in the next chapter:
+        # return max(len(encoded_text) for encoded_text in self.encoded_texts)
 
 
 @torch.no_grad()  # Disable gradient tracking for efficiency

ch06/01_main-chapter-code/ch06.ipynb

@@ -777,7 +777,10 @@
     "            encoded_length = len(encoded_text)\n",
     "            if encoded_length > max_length:\n",
     "                max_length = encoded_length\n",
-    "        return max_length"
+    "        return max_length\n",
+    "        # Note: A more pythonic version to implement this method\n",
+    "        # is the following, which is also used in the next chapter:\n",
+    "        # return max(len(encoded_text) for encoded_text in self.encoded_texts)"
    ]
   },
   {

ch06/01_main-chapter-code/gpt_class_finetune.py

@@ -132,6 +132,9 @@ def _longest_encoded_length(self):
             if encoded_length > max_length:
                 max_length = encoded_length
         return max_length
+        # Note: A more pythonic version to implement this method
+        # is the following, which is also used in the next chapter:
+        # return max(len(encoded_text) for encoded_text in self.encoded_texts)
 
 
 def calc_accuracy_loader(data_loader, model, device, num_batches=None):

ch06/02_bonus_additional-experiments/additional_experiments.py

@@ -94,6 +94,9 @@ def _longest_encoded_length(self, tokenizer):
             if encoded_length > max_length:
                 max_length = encoded_length
         return max_length
+        # Note: A more pythonic version to implement this method
+        # is the following, which is also used in the next chapter:
+        # return max(len(encoded_text) for encoded_text in self.encoded_texts)
 
 
 def download_and_unzip(url, zip_path, extract_to, new_file_path):

ch06/03_bonus_imdb-classification/train_bert_hf_spam.py

@@ -51,6 +51,9 @@ def _longest_encoded_length(self, tokenizer):
             if encoded_length > max_length:
                 max_length = encoded_length
         return max_length
+        # Note: A more pythonic version to implement this method
+        # is the following, which is also used in the next chapter:
+        # return max(len(encoded_text) for encoded_text in self.encoded_texts)
 
 
 def download_and_unzip(url, zip_path, extract_to, new_file_path):