MJ10 / BioSeq-GFN-AL

Code for "Biological Sequence Design with GFlowNets", 2022
MIT License
72 stars 16 forks source link

It seems not working for this script. #2

Open xdzhang-xdu opened 2 years ago

xdzhang-xdu commented 2 years ago

Traceback (most recent call last): File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/run_gfp.py", line 369, in main(args) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/run_gfp.py", line 364, in main train(args, oracle, dataset) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/run_gfp.py", line 340, in train proxy = construct_proxy(args, tokenizer, dataset=dataset) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/run_gfp.py", line 300, in construct_proxy proxy = get_proxy_model(args, tokenizer) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/lib/proxy/init.py", line 5, in get_proxy_model proxy = DropoutRegressor(args, tokenizer) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/lib/proxy/regression.py", line 17, in init self.init_model() File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/lib/proxy/regression.py", line 35, in init_model self.model.to(self.args.device) File "/home/sunsun/xdzhang/BioSeq-GFN-AL-master/venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in getattr raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'DropoutRegressor' object has no attribute 'model'

MJ10 commented 2 years ago

@xdzhang-xjtu apologies again for the late response, but I am not able to reproduce this issue. Would it be possible to provide more details about your environment? I am unable to reproduce this issue following the README on a clean environment.