Hanjun-Dai / graphnn

Training computational graph on top of structured data (string, graph, etc)
MIT License
287 stars 91 forks source link

Not able to run the mnist example #2

Closed shengwa closed 7 years ago

shengwa commented 7 years ago

I tried to run the mnist example but there was an error:

./run.sh
60000 images for training
10000 images for test
testing
Assertion `isReady[VarIdx(p)]` failed in src/nn/factor_graph.cpp line 170: required variable ReduceMean_7:out_0 is not ready

I also found the similar error with graph classification example

Assertion `isReady[VarIdx(p)]` failed in src/nn/factor_graph.cpp line 170: required variable ReduceMean_21:out_0 is not ready

Any idea what the problem is?

Hanjun-Dai commented 7 years ago

Hi, are you using the latest code? I just checked the HEAD of master, and it works fine.

shengwa commented 7 years ago

Oh, it seems not the latest version, I'll update it and see what's going on. Thank you :)

shengwa commented 7 years ago

Hi, I tried the latest code but the problem was still there. I guess I'll read more code to figure it out.

Hanjun-Dai commented 7 years ago

Are you using the commit 00351188349c9cfef783b5d17c2f07523891fd8e ?

shengwa commented 7 years ago

Yes, I'm using it. v1.11-85-g0035118

Hanjun-Dai commented 7 years ago

Can you simply zip your code folder and send it to daihanjun@gmail.com? (excluding the data and binary files)

Hanjun-Dai commented 7 years ago

It seems to be the Ubuntu 16.04 issue. Feel free to reopen if the problem is still there.