From 73e87b5db1bbd583ade83f3ae50b10de859ad9c1 Mon Sep 17 00:00:00 2001
From: choosewhatulike <1901722105@qq.com>
Date: Sat, 23 Jun 2018 17:36:53 +0800
Subject: [PATCH] add some sample data

---
 .../evaluate.py                               |  0
 .../model.py                                  |  0
 .../preprocess.py                             |  0
 .../train.py                                  | 10 ++++--
 reproduction/.gitignore                       |  1 -
 reproduction/README.md                        | 36 -------------------
 6 files changed, 7 insertions(+), 40 deletions(-)
 rename {reproduction => HAN-document_classification}/evaluate.py (100%)
 rename {reproduction => HAN-document_classification}/model.py (100%)
 rename {reproduction => HAN-document_classification}/preprocess.py (100%)
 rename {reproduction => HAN-document_classification}/train.py (95%)
 delete mode 100644 reproduction/.gitignore
 delete mode 100644 reproduction/README.md

diff --git a/reproduction/evaluate.py b/HAN-document_classification/evaluate.py
similarity index 100%
rename from reproduction/evaluate.py
rename to HAN-document_classification/evaluate.py
diff --git a/reproduction/model.py b/HAN-document_classification/model.py
similarity index 100%
rename from reproduction/model.py
rename to HAN-document_classification/model.py
diff --git a/reproduction/preprocess.py b/HAN-document_classification/preprocess.py
similarity index 100%
rename from reproduction/preprocess.py
rename to HAN-document_classification/preprocess.py
diff --git a/reproduction/train.py b/HAN-document_classification/train.py
similarity index 95%
rename from reproduction/train.py
rename to HAN-document_classification/train.py
index add570c1..72e2a696 100644
--- a/reproduction/train.py
+++ b/HAN-document_classification/train.py
@@ -147,7 +147,7 @@ if __name__ == '__main__':
     import gensim
     from gensim import models
 
-    # train_word_vec()
+    train_word_vec()
 
     embed_model = Word2Vec.load('yelp.word2vec')
     embedding = Embedding_layer(embed_model.wv, embed_model.wv.vector_size)
@@ -158,6 +158,10 @@ if __name__ == '__main__':
     net = HAN(input_size=200, output_size=5, 
             word_hidden_size=50, word_num_layers=1, word_context_size=100,
             sent_hidden_size=50, sent_num_layers=1, sent_context_size=100)
-        
-    net.load_state_dict(torch.load('model.dict'))
+    try:
+        net.load_state_dict(torch.load('model.dict'))
+        print("last time trained model has loaded")
+    except Exception:
+        print("cannot load model, train the inital model")
+    
     train(net, dataset, num_epoch=5, batch_size=64, use_cuda=True)
\ No newline at end of file
diff --git a/reproduction/.gitignore b/reproduction/.gitignore
deleted file mode 100644
index 7e99e367..00000000
--- a/reproduction/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-*.pyc
\ No newline at end of file
diff --git a/reproduction/README.md b/reproduction/README.md
deleted file mode 100644
index c5c197bd..00000000
--- a/reproduction/README.md
+++ /dev/null
@@ -1,36 +0,0 @@
-## Introduction
-This is the implementation of [Hierarchical Attention Networks for Document Classification](https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf) paper in PyTorch.
-* Dataset is 600k documents extracted from [Yelp 2018](https://www.yelp.com/dataset) customer reviews
-* Use [NLTK](http://www.nltk.org/) and [Stanford CoreNLP](https://stanfordnlp.github.io/CoreNLP/) to tokenize documents and sentences
-* Both CPU & GPU support
-* The best accuracy is 71%, reaching the same performance in the paper
-
-## Requirement
-* python 3.6
-* pytorch = 0.3.0
-* numpy
-* gensim
-* nltk
-* coreNLP
-
-## Parameters
-According to the paper and experiment, I set model parameters:
-|word embedding dimension|GRU hidden size|GRU layer|word/sentence context vector dimension|
-|---|---|---|---|
-|200|50|1|100|
-
-And the training parameters:
-|Epoch|learning rate|momentum|batch size|
-|---|---|---|---|
-|3|0.01|0.9|64|
-
-## Run
-1. Prepare dataset. Download the [data set](https://www.yelp.com/dataset), and unzip the custom reviews as a file. Use preprocess.py to transform file into data set foe model input.
-2. Train the model. The model will trained and autosaved in 'model.dict'
-```
-python train
-```
-3. Test the model.
-```
-python evaluate
-```
\ No newline at end of file