I want to know how to run your program

[106084]

I want to know how to run your program

[lijin118]

You can simply run LisGAN.py or python LisGAN with your own parameters. Please refere to the updated readme

[106084]

Thank you for your answer, and I want to know if I can use it on the CPU.

[lijin118]

Theoretically yes and you can try it. But it would be slow.

[106084]

When I used the hyper-parameter you gave and ran the code on the AWA dataset, I achieved the following results. Why is the accuracy so low? EP[29/30]************************************************************************************ First Seen: 86.18%, Unseen: 8.99%, First H: 16.28% 1NN Seen: 84.95%, Unseen: 8.70%, 1NN H: 15.78% FC Seen: 87.73%, Unseen: 7.98%, FC H: 14.63%

[HuangYL-0619]

https://github.com/106084 when I run this program,I find it can't run succeedly,Do you have such problem like File "F:/PythonProject/try0/lisgan.py", line 262, in sample() File "F:/PythonProject/try0/lisgan.py", line 135, in sample input_att.copy_(batch_att) RuntimeError: The size of tensor a (1024) must match the size of tensor b (85) at non-singleton dimension 1

[xugy16]

I always get the error when using CUN dataset,

train_loc = matcontent['train_loc'].squeeze() - 1 KeyError: 'train_loc'