Get ptb script change for licensing issues (#8899)

* Print license notification before downloading dataset

* Print license notification before downloading dataset

Author: cjolivier01

example/gluon/word_language_model/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;

example/model-parallel-lstm/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;

example/rnn-time-major/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;

example/rnn/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;

example/rnn/old/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;

perl-package/AI-MXNet/examples/get_ptb_data.sh

@@ -17,6 +17,11 @@
 # specific language governing permissions and limitations
 # under the License.
 
+echo ""
+echo "NOTE: Please review the licensing of the datasets in this script before proceeding"
+echo "See https://catalog.ldc.upenn.edu/ldc99t42 for the licensing"
+echo "Once that is done, please uncomment the wget commands in this script"
+echo ""
 
 RNN_DIR=$(cd `dirname $0`; pwd)
 DATA_DIR="${RNN_DIR}/data/"
@@ -26,7 +31,7 @@ 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/tinyshakespeare/input.txt;
+#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/tinyshakespeare/input.txt;