update word_lm example

apache · Jun 27, 2018 · 7c1acb4 · 7c1acb4
1 parent 13bc6d8
commit 7c1acb4
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 6 deletions.
diff --git a/example/rnn/old/bucket_io.py b/example/rnn/old/bucket_io.py
@@ -21,7 +21,6 @@
 import sys
 sys.path.insert(0, "../../python")
 import numpy as np
-import math
 import mxnet as mx
 
 # The interface of a data iter that works for bucketing
@@ -203,7 +202,7 @@ def make_data_iter_plan(self):
         # truncate each bucket into multiple of batch-size
         bucket_n_batches = []
         for i in range(len(self.data)):
-            bucket_n_batches.append(math.floor((self.data[i]) / self.batch_size))
+            bucket_n_batches.append(np.floor((self.data[i]) / self.batch_size))
             self.data[i] = self.data[i][:int(bucket_n_batches[i]*self.batch_size)]
 
         bucket_plan = np.hstack([np.zeros(n, int)+i for i, n in enumerate(bucket_n_batches)])

diff --git a/example/rnn/word_lm/get_ptb_data.sh → ...le/rnn/word_lm/get_sherlockholmes_data.sh b/example/rnn/word_lm/get_ptb_data.sh → ...le/rnn/word_lm/get_sherlockholmes_data.sh
@@ -37,7 +37,7 @@ if [[ ! -d "${DATA_DIR}" ]]; then
   mkdir -p ${DATA_DIR}
 fi
 
-wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/ptb/ptb.train.txt;
-wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/ptb/ptb.valid.txt;
-wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/ptb/ptb.test.txt;
+wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/sherlockholmes/sherlockholmes.train.txt;
+wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/sherlockholmes/sherlockholmes.valid.txt;
+wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/sherlockholmes/sherlockholmes.test.txt;
 wget -P ${DATA_DIR} https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/tinyshakespeare/input.txt;
diff --git a/example/rnn/word_lm/train.py b/example/rnn/word_lm/train.py
@@ -25,7 +25,7 @@
 from mxnet.model import BatchEndParam
 
 parser = argparse.ArgumentParser(description='PennTreeBank LSTM Language Model')
-parser.add_argument('--data', type=str, default='./data/ptb.',
+parser.add_argument('--data', type=str, default='./data/sherlockholmes.',
                     help='location of the data corpus')
 parser.add_argument('--emsize', type=int, default=650,
                     help='size of word embeddings')