added assignment 4

assignment 2/sgd.py

@@ -86,7 +86,8 @@ def sgd(f, x0, step, iterations, postprocessing=None, useSaved=False,
 
         loss = None
         ### YOUR CODE HERE
-
+        loss,gradient = f(x)
+        x=x-step*gradient
         ### END YOUR CODE
 
         x = postprocessing(x)

assignment 4/a4/README.md

@@ -0,0 +1,2 @@
+# NMT Assignment
+Note: Heavily inspired by the https://github.com/pcyin/pytorch_nmt repository

assignment 4/a4/collect_submission.sh

@@ -0,0 +1,2 @@
+rm -f assignment4.zip
+zip -r assignment4.zip *.py ./en_es_data ./sanity_check_en_es_data ./outputs

assignment 4/a4/gpu_requirements.txt

@@ -0,0 +1,3 @@
+nltk
+docopt
+tqdm==4.29.1

assignment 4/a4/local_env.yml

@@ -0,0 +1,13 @@
+name: local_nmt
+channels:
+  - pytorch
+  - defaults
+dependencies:
+  - python=3.5
+  - numpy
+  - scipy
+  - tqdm
+  - docopt
+  - pytorch
+  - nltk
+  - torchvision

assignment 4/a4/model_embeddings.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+CS224N 2019-20: Homework 4
+model_embeddings.py: Embeddings for the NMT model
+Pencheng Yin <pcyin@cs.cmu.edu>
+Sahil Chopra <schopra8@stanford.edu>
+Anand Dhoot <anandd@stanford.edu>
+Vera Lin <veralin@stanford.edu>
+"""
+
+import torch.nn as nn
+
+class ModelEmbeddings(nn.Module): 
+    """
+    Class that converts input words to their embeddings.
+    """
+    def __init__(self, embed_size, vocab):
+        """
+        Init the Embedding layers.
+
+        @param embed_size (int): Embedding size (dimensionality)
+        @param vocab (Vocab): Vocabulary object containing src and tgt languages
+                              See vocab.py for documentation.
+        """
+        super(ModelEmbeddings, self).__init__()
+        self.embed_size = embed_size
+
+        # default values
+        self.source = None
+        self.target = None
+
+        src_pad_token_idx = vocab.src['<pad>']
+        tgt_pad_token_idx = vocab.tgt['<pad>']
+
+        ### YOUR CODE HERE (~2 Lines)
+        ### TODO - Initialize the following variables:
+        ###     self.source (Embedding Layer for source language)
+        ###     self.target (Embedding Layer for target langauge)
+        ###
+        ### Note:
+        ###     1. `vocab` object contains two vocabularies:
+        ###            `vocab.src` for source
+        ###            `vocab.tgt` for target
+        ###     2. You can get the length of a specific vocabulary by running:
+        ###             `len(vocab.<specific_vocabulary>)`
+        ###     3. Remember to include the padding token for the specific vocabulary
+        ###        when creating your Embedding.
+        ###
+        ### Use the following docs to properly initialize these variables:
+        ###     Embedding Layer:
+        ###         https://pytorch.org/docs/stable/nn.html#torch.nn.Embedding
+
+
+        ### END YOUR CODE
+
+