Update README

README.md

@@ -12,7 +12,7 @@ Accepted to KDD 2019 Research Track!
 
 - Linux or macOS
 - Python 3
-- TensorFlow >= 1.8
+- TensorFlow GPU >= 1.8
 - NVIDIA GPU + CUDA cuDNN
 
 ## Getting Started
@@ -41,14 +41,11 @@ These datasets are sampled from the original datasets.
 - YouTube contains 2,000 nodes and 1,310,617 edges. [Source](http://socialcomputing.asu.edu/datasets/YouTube)
 - Alibaba contains 6,163 nodes and 17,865 edges.
 
-You can download the preprocessed datasets by running `python scripts/download_preprocessed_data.py`. (Alibaba dataset is to be released.)
-If you're in regions where Dropbox are blocked (e.g. Mainland China), try `python scripts/download_preprocessed_data.py --cn`.
-
 ### Training
 
 #### Training on the existing datasets
 
-You can use `./scripts/run_example.sh` or `python src/main.py --input example_data` to train GATNE-T model on the example data. (If you share the server with others or you want to use the specific GPU(s), you may need to set `CUDA_VISIBLE_DEVICES`.) 
+You can use `./scripts/run_example.sh` or `python src/main.py --input data/example` to train GATNE-T model on the example data. (If you share the server with others or you want to use the specific GPU(s), you may need to set `CUDA_VISIBLE_DEVICES`.) 
 
 If you want to train on the Amazon dataset, you can run `python src/main.py --input data/amazon` or `python src/main.py --input data/amazon --features data/amazon/feature.txt` to train GATNE-T model or GATNE-I model, respectively. 
 

scripts/run_example.sh

@@ -1 +1 @@
-python src/main.py --input example_data
+python src/main.py --input data/example