Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
xufana7 a722b61911 | 1 year ago | |
---|---|---|
data | 1 year ago | |
denovo | 1 year ago | |
sample_data | 1 year ago | |
01.py | 1 year ago | |
README.md | 1 year ago | |
casanovo.py | 1 year ago | |
command_env.sh | 1 year ago | |
config.yaml | 1 year ago | |
config_large.yaml | 1 year ago | |
config_small.yaml | 1 year ago | |
config_small_t5.yaml | 1 year ago | |
config_test.yaml | 1 year ago | |
data.mgf | 1 year ago | |
exp_record.txt | 1 year ago | |
get_t5.py | 1 year ago | |
log.log | 1 year ago | |
loss.pdf | 1 year ago | |
output.log | 1 year ago | |
plot_logs.ipynb | 1 year ago | |
read_data.ipynb | 1 year ago | |
utils.py | 1 year ago | |
version.py | 1 year ago |
conda activate casanovo_env1
# original
python casanovo.py --mode train --peak_path "/userhome/xufan/peptide_data/zhipu_data/casanovo/train_data/*" --peak_path_val "/userhome/xufan/peptide_data/zhipu_data/casanovo/val_data/*" --output exp_original/log --config config.yaml
# small pretrained model
python casanovo.py --mode train --pretrained "/userhome/xufan/peptide_data/zhipu_data/moco_mz/output_s1m1g1_6/checkpoint_0079_final.pth.tar" --peak_path "/userhome/xufan/peptide_data/zhipu_data/casanovo/train_data/*" --peak_path_val "/userhome/xufan/peptide_data/zhipu_data/casanovo/val_data/*" --output exp_small/log --config config_small.yaml
# large pretrained model
python casanovo.py --mode train --pretrained "/userhome/xufan/peptide_data/zhipu_data/moco_mz/output_alls1m1g1_1/checkpoint_0001_final.pth.tar" --peak_path "/userhome/xufan/peptide_data/zhipu_data/casanovo/train_data/*" --peak_path_val "/userhome/xufan/peptide_data/zhipu_data/casanovo/val_data/*" --output exp_large/log --config config_large.yaml
--train_only only train without eval
--pretrained pretrained model path
--encoder_lr encoder learning rate. If None, encoder_lr=learning_rate in config file.
No Description
Jupyter Notebook Python Shell Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》