Hi, thanks for the amazing work! However, when I'm using your provided code, dataset and model, I can only obtain leaving_group.pt of USPTO50K with 238 size, while the model provided has the size of 228, how to make them match?
Traceback (most recent call last):
File "entry.py", line 195, in
main()
File "entry.py", line 67, in main
model = build_model(args)
File "entry.py", line 187, in build_model
dataset_path=args.dataset
File "/data/env-retro/anaconda3/envs/retro_liuth/lib/python3.7/site-packages/pytorch_lightning/core/saving.py", line 142, in load_from_checkpoint
**kwargs,
File "/data/env-retro/anaconda3/envs/retro_liuth/lib/python3.7/site-packages/pytorch_lightning/core/saving.py", line 179, in _load_from_checkpoint
return _load_state(cls, checkpoint, strict=strict, **kwargs)
File "/data/env-retro/anaconda3/envs/retro_liuth/lib/python3.7/site-packages/pytorch_lightning/core/saving.py", line 237, in _load_state
keys = obj.load_state_dict(checkpoint["state_dict"], strict=strict)
File "/data/env-retro/anaconda3/envs/retro_liuth/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1672, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for RetroAGT:
size mismatch for lg_out_fn.0.weight: copying a param with shape torch.Size([228, 512]) from checkpoint, the shape in current model is torch.Size([238, 512]).
size mismatch for lg_out_fn.0.bias: copying a param with shape torch.Size([228]) from checkpoint, the shape in current model is torch.Size([238]).
and also, I cannot find the route for CC(CC1=CC=C2OCOC2=C1)NCC(O)C1=CC=C(O)C(O)=C1 by using the provided model even with 1000 iterations
root : INFO Final search status | success value | iter: 47.70581531524658 | inf | 1000
root : INFO Synthesis path for CC(CC1=CC=C2OCOC2=C1)NCC(O)C1=CC=C(O)C(O)=C1 not found. Please try increasing the number of iterations.
None
wangyu-sd
