RetroExplainer
RetroExplainer copied to clipboard
wangyu-sd
RetroExplainer: A chemical knowledge and deep-leaning guided molecular assembly approach for retrosynthesis prediction with quantitative interpretability
Hello @wangyu-sd First, thank you for sharing your work on RetroExplainer. It’s an exciting approach combining chemical knowledge and deep learning for retrosynthesis prediction with quantitative interpretability! I am particularly...
` raise ValueError(f"Target size ({target.size()}) must be the same as input size ({input.size()})") ValueError: Target size (torch.Size([256, 300, 10])) must be the same as input size (torch.Size([256, 300, 4])) `...
现有代码执行训练50K数据集生成的leaving_group的维度与测试时的维度不匹配，我将datamodule中50k的max_node/max_lg_na/get_num_size修改为50、23、4之后训练生成的leaving_group在运行测试脚本没有报错，但是测试结果的精度比预期低很多，是否我这么改是错误的。 ![Uploading image.png…]()
Hi Yu, Pytorch-lightning does not support " pl.Trainer.add_argparse_args(parser) " in 2.x.x version. Thus, it is better to install pytorch-lightning version > 1.5 and < 2.0 In README.md, you can change:...
I observed that requirements.txt is missing from the source code. Could you please update the documentation if an nVidia gpu is needed. I'm curious to know if there's any way...
i do the operation 'sh scripts/test_for_uspto50k_rxn_type_unknown.sh' ,and get the result 'tsne_data.pt'. but the result seems not been assembled. i can't find how to assemble the result through your readme. could...
I run the api_for_multistep.py with the same setting in README.md but the output is always "path not found"
Traceback (most recent call last): File "api_for_multistep.py", line 110, in model_dump="model_saved/model_for_multi_step.ckpt" File "api_for_multistep.py", line 41, in __init__ one_step = prepare_single_step_model(model_dump) File "/home/csn/Desktop/RetroExplainer/model/util.py", line 119, in prepare_single_step_model single_step_model = RetroAGT.load_from_checkpoint(ckpt, strict=False)...
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...
raise ValueError(f"Target size ({target.size()}) must be the same as input size ({input.size()})") ValueError: Target size (torch.Size([128, 300, 10])) must be the same as input size (torch.Size([128, 300, 4])) How to...
