no output

[LIU26549]

There is no output and display "0it [00:00, ?it/s]" when I run the command "python data_create/create_pretrain_datasets.py --save_path pretrain_data/esol --data_type exp1s --maxiters 500 --raw_data_path finetune_data/moleculenet/esol/raw/delaney-processed.csv" with anaconda. How can i figure it out please? Would you please give me some help please? Thank you very much.

[gihanpanapitiya]

Hello,
Can you try executing the command at the FragNet-master directory?
Go to FragNet-master. Then execute the following command,

python fragnet/data_create/create_pretrain_datasets.py --save_path fragnet/pretrain_data/esol --data_type exp1s --maxiters 500 --raw_data_path fragnet/finetune_data/moleculenet/esol/raw/delaney-processed.csv

The pre-training data should get created at fragnet/pretrain_data/esol.

To create finetuning data run the following at FragNet-master,

python fragnet/data_create/create_finetune_datasets.py --dataset_name moleculenet --dataset_subset esol --use_molebert True --output_dir fragnet/finetune_data/moleculenet_exp1s --data_dir fragnet/finetune_data/moleculenet --data_type exp1s

[LIU26549]

Hello, Can you try executing the command at the FragNet-master directory? Go to FragNet-master. Then execute the following command,

python fragnet/data_create/create_pretrain_datasets.py --save_path fragnet/pretrain_data/esol --data_type exp1s --maxiters 500 --raw_data_path fragnet/finetune_data/moleculenet/esol/raw/delaney-processed.csv

The pre-training data should get created at fragnet/pretrain_data/esol.

To create finetuning data run the following at FragNet-master,

python fragnet/data_create/create_finetune_datasets.py --dataset_name moleculenet --dataset_subset esol --use_molebert True --output_dir fragnet/finetune_data/moleculenet_exp1s --data_dir fragnet/finetune_data/moleculenet --data_type exp1s

thank you reply, I adopted your method,but it not successful

[gihanpanapitiya]

@LIU26549 I just did a fresh installation following the instructions in our README page. It ran without an issue. Can you try the following process?

Create a conda environment and activate it

conda create -n fragnet python=3.11
conda activate fragnet
 

Clone fragnet

git clone https://github.com/pnnl/FragNet.git
 

Go to the FragNet directory

cd FragNet
 

Install FragNet

pip instal -r requirements.txt
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.4.0+cpu.html
pip install .




Go to the fragnet folder

cd fragnet
 

Create pretraining data

mkdir -p finetune_data/moleculenet/esol/raw/
 
wget -O finetune_data/moleculenet/esol/raw/delaney-processed.csv https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/delaney-processed.csv
 
python data_create/create_pretrain_datasets.py --save_path pretrain_data/esol --data_type exp1s --maxiters 500 --raw_data_path finetune_data/moleculenet/esol/raw/delaney-processed.csv
 

Create finetuning data

python data_create/create_finetune_datasets.py --dataset_name moleculenet --dataset_subset esol --use_molebert True --output_dir finetune_data/moleculenet_exp1s --data_dir finetune_data/moleculenet --data_type exp1s
 

Pretrain

python train/pretrain/pretrain_gat2.py --config exps/pt/unimol_exp1s4/config.yaml
 

Finetune

python train/finetune/finetune_gat2.py --config exps/ft/esol/e1pt4.yaml