Ben Auffarth
Ben Auffarth
I don't remember tbh. It's been a long time.
I also get aborted, but after the training. ```bash $ graphvite baseline quick start running baseline: demo/quick_start.yaml loading graph from /home/ben/.graphvite/dataset/blogcatalog/blogcatalog_train.txt 0.00018755% > [time] GraphApplication.load: 0.0789478 s [time] GraphApplication.build: 0.665795...
I think this is a fantastic library, but I burned through some time already trying to set up graphvite with different settings. A minimal example of how to make this...
I tried again after removing pytorch and reinstalling (instead of just -U upgrading). Now I am getting something more promising, but still not there. ```bash $ graphvite baseline quick startrunning...
After a more testing it seems that for the diabetes dataset that I am using for benchmarking, the linear model actually outperforms the random forest regressor and the decision tree...
example.cpp - The only changes are: - it's using the new MiniDNN::Matrix - it prints if a matrix is row major ``` #include using namespace MiniDNN; int main() { //...
Sorry, I am struggling with this one. Could you help out? The convolutions do memory copies...
I thought this was a good idea for quicker inference or perhaps training without transposing the dataset, but it seems a lot of work...
Thanks for the feedback. I think you are right.
Please see my PR (or fork) for support of v2.