learning representations

Author: Gladiator07

Seq_to_Seq/Learning_Phrase_Representations.ipynb

@@ -0,0 +1,71 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8c4bcc08",
+   "metadata": {},
+   "source": [
+    "## Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3b9f829",
+   "metadata": {},
+   "source": [
+    "n this second notebook on sequence-to-sequence models using PyTorch and TorchText, we'll be implementing the model from [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://arxiv.org/abs/1406.1078). This model will achieve improved test perplexity whilst only using a single layer RNN in both the encoder and the decoder."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77ac8433",
+   "metadata": {},
+   "source": [
+    " Refer [original notebook](https://github.com/bentrevett/pytorch-seq2seq/blob/master/2%20-%20Learning%20Phrase%20Representations%20using%20RNN%20Encoder-Decoder%20for%20Statistical%20Machine%20Translation.ipynb) for more details and explanation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8fc24434",
+   "metadata": {},
+   "source": [
+    "## Preparing data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d286925b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "\n",
+    "from torchtext.legacy.datasets import Multi30k"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Seq_to_Seq/Learning_Phrase_Representations.py

@@ -0,0 +1,26 @@
+# Importing stuff
+import torch
+import torch.nn
+import torch.optim as optim
+
+from torchtext.legacy.datasets import Multi30k
+from torchtext.legacy.data import Field, BucketIterator
+
+import spacy
+import numpy as np
+
+import random
+import math
+import time
+
+# Setting SEED
+SEED = 1234
+
+random.seed(SEED)
+np.random.seed(SEED)
+torch.manual_seed(SEED)
+torch.cuda.manual_seed(SEED)
+torch.backends.cudnn.deterministic = True
+
+spacy_de = spacy.load('de_core_news_sm')
+spacy_en = spacy.load('en_core_web_sm')