modify project3

project_3/机器翻译项目/.ipynb_checkpoints/transformer_nmt_student-checkpoint.ipynb

-{
+{
@@ -129,7 +129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -158,13 +158,13 @@
     "        self.en_word_dict, self.en_total_words, self.en_index_dict = self.build_dict(self.train_en)\n",
     "        self.cn_word_dict, self.cn_total_words, self.cn_index_dict = self.build_dict(self.train_cn)\n",
     "\n",
-    "#         # id化\n",
-    "#         self.train_en, self.train_cn = self.wordToID(self.train_en, self.train_cn, self.en_word_dict, self.cn_word_dict)\n",
-    "#         self.dev_en, self.dev_cn = self.wordToID(self.dev_en, self.dev_cn, self.en_word_dict, self.cn_word_dict)\n",
+    "        # id化\n",
+    "        self.train_en, self.train_cn = self.wordToID(self.train_en, self.train_cn, self.en_word_dict, self.cn_word_dict)\n",
+    "        self.dev_en, self.dev_cn = self.wordToID(self.dev_en, self.dev_cn, self.en_word_dict, self.cn_word_dict)\n",
     "\n",
-    "#         # 划分batch + padding + mask\n",
-    "#         self.train_data = self.splitBatch(self.train_en, self.train_cn, BATCH_SIZE)\n",
-    "#         self.dev_data = self.splitBatch(self.dev_en, self.dev_cn, BATCH_SIZE)\n",
+    "        # 划分batch + padding + mask\n",
+    "        self.train_data = self.splitBatch(self.train_en, self.train_cn, BATCH_SIZE)\n",
+    "        self.dev_data = self.splitBatch(self.dev_en, self.dev_cn, BATCH_SIZE)\n",
     "\n",
     "    def load_data(self, path):\n",
     "        \"\"\"\n",
@@ -285,7 +285,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [

project_3/机器翻译项目/transformer_nmt_student.ipynb

-{
+{
@@ -129,7 +129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -158,13 +158,13 @@
     "        self.en_word_dict, self.en_total_words, self.en_index_dict = self.build_dict(self.train_en)\n",
     "        self.cn_word_dict, self.cn_total_words, self.cn_index_dict = self.build_dict(self.train_cn)\n",
     "\n",
-    "#         # id化\n",
-    "#         self.train_en, self.train_cn = self.wordToID(self.train_en, self.train_cn, self.en_word_dict, self.cn_word_dict)\n",
-    "#         self.dev_en, self.dev_cn = self.wordToID(self.dev_en, self.dev_cn, self.en_word_dict, self.cn_word_dict)\n",
+    "        # id化\n",
+    "        self.train_en, self.train_cn = self.wordToID(self.train_en, self.train_cn, self.en_word_dict, self.cn_word_dict)\n",
+    "        self.dev_en, self.dev_cn = self.wordToID(self.dev_en, self.dev_cn, self.en_word_dict, self.cn_word_dict)\n",
     "\n",
-    "#         # 划分batch + padding + mask\n",
-    "#         self.train_data = self.splitBatch(self.train_en, self.train_cn, BATCH_SIZE)\n",
-    "#         self.dev_data = self.splitBatch(self.dev_en, self.dev_cn, BATCH_SIZE)\n",
+    "        # 划分batch + padding + mask\n",
+    "        self.train_data = self.splitBatch(self.train_en, self.train_cn, BATCH_SIZE)\n",
+    "        self.dev_data = self.splitBatch(self.dev_en, self.dev_cn, BATCH_SIZE)\n",
     "\n",
     "    def load_data(self, path):\n",
     "        \"\"\"\n",
@@ -219,8 +219,8 @@
     "        length = len(en)\n",
     "        \n",
     "        # TODO: 将翻译前(英文)数据和翻译后(中文)数据都转换为id表示的形式\n",
-    "        out_en_ids = [[en_dict.get(w, 0) for w in sent] for sent in en]\n",
-    "        out_cn_ids = [[cn_dict.get(w, 0) for w in sent] for sent in cn]\n",
+    "        out_en_ids = [[en_dict.get(w) for w in sent] for sent in en]\n",
+    "        out_cn_ids = [[cn_dict.get(w) for w in sent] for sent in cn]\n",
     "\n",
     "\n",
     "        # 构建一个按照句子长度排序的函数\n",
@@ -285,14 +285,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 31,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# test load data\n",
     "prepare = PrepareData('nmt/en-cn/train_mini.txt','nmt/en-cn/train_mini.txt')\n",
     "# [en,cn] = prepare.load_data('nmt/en-cn/train_mini.txt')\n",
-    "# print(cn)"
+    "# print(cn)\n",
+    "d = {'a':3,'b':5}\n",
+    "d.get('a')"
    ]
   },
   {