search

wengong-jin / hgraph2graph

Hierarchical Generation of Molecular Graphs using Structural Motifs
MIT License
360 stars 107 forks source link

TypeError: forward() missing 2 required positional arguments: 'y_orders' and 'beta' #42

Open amir-tagh opened 2 years ago

amir-tagh commented 2 years ago

I am using the train_translator.py for lead optimization and I am getting the following error. does anybody know how I can fix this?

Thanks,

Traceback (most recent call last): File "/apps/hgraph2graph/20210428/hgraph2graph/train_translator.py", line 86, in loss, kl_div, wacc, iacc, tacc, sacc = model(batch) File "/apps/hgraph2graph/20210428/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(input, **kwargs) TypeError: forward() missing 2 required positional arguments: 'y_orders' and 'beta'

zhangsan5213 commented 1 year ago

I am also running into this issue.

Bunnybeibei commented 1 year ago

You can see if you default mode is "pair" when you run process.py. The correct single input format is that each molecule has three pieces of information, and the pairs input has five pieces of information, because 'x_orders' is not required, as shown in the figure below. https://tudingtu.cn/i/2023/02/20/in38hi.png “beta” is the hyperparameter VAE loss, which is used to control the ratio of reconstruction error to KL divergence loss.