Update README to Pytorch v1.10

Author: wouterkool

README.md

@@ -38,7 +38,7 @@ pip install tensorboardx==1.5 fastprogress==0.1.18
 # conda install -c conda-forge cupy cudatoolkit=10.2 -y
 pip install cupy-cuda102
 # Also some efficient sparse operations using https://github.com/rusty1s/pytorch_scatter
-pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu102.html
+pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.10.0+cu102.html
 ```
 
 ## Generate instances (or download)
@@ -323,4 +323,4 @@ python visualize.py --problem vrp --instances data/vrp/vrp_nazari100_validation_
 ![pipeline](res/vrp.png)
 
 ## Acknowledgements
-This repository was built upon the excellent repository [graph-convnet-tsp](https://github.com/chaitjo/graph-convnet-tsp) by Chaitanya K. Joshi and my own repository [attention-learn-to-route](https://github.com/wouterkool/attention-learn-to-route). The TSPTW GVNS code is from the repository [TSPTW](https://github.com/sashakh/TSPTW), adapted from [the original code](http://homepages.dcc.ufmg.br/~rfsilva/tsptw/) of da Silva et al. We thank Quentin Cappart for kindly providing TSPTW instances and results.
+This repository was built upon the excellent repository [graph-convnet-tsp](https://github.com/chaitjo/graph-convnet-tsp) by Chaitanya K. Joshi and my own repository [attention-learn-to-route](https://github.com/wouterkool/attention-learn-to-route). The TSPTW GVNS code is from the repository [TSPTW](https://github.com/sashakh/TSPTW), adapted from [the original code](http://homepages.dcc.ufmg.br/~rfsilva/tsptw/) of da Silva et al. We thank Quentin Cappart for kindly providing TSPTW instances and results.