Typically, you would not run the code from in the directory it's install and would run from a separate model build directory so seems like a fix is needed?įile "/home/userid/.conda/envs/my-rdkit-env/lib/python3.6/site-packages/tap/utils.py", line 66, in get_git_urlįile "/home/userid/.conda/envs/my-rdkit-env/lib/python3.6/site-packages/tap/utils.py", line 33, in check_output Running the git config command within the install dir does return the repo chemprop]$ git config -get There is a simple work around, commenting out line 46 from /hpc/scratch/userid/builds/chemprop/chemprop/train/run_training.pyĤ6 #args.save(os.path.join(args.save_dir, 'args.json'))Ĥ8 # Set pytorch seed for random initial weights This problem persists for me even when I run the code from the install directory. Subprocess.CalledProcessError: Command '' returned non-zero exit status 128. Return check_output()įile "/data/nlim/Github/typed-argument-parser/tap/utils.py", line 30, in check_output Reproducibility = get_git_root()įile "/data/nlim/Github/typed-argument-parser/tap/utils.py", line 50, in get_git_root Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).įile "/data/nlim/Github/chemprop/train.py", line 11, in įile "/data/nlim/Github/typed-argument-parser/tap/tap.py", line 445, in saveįile "/data/nlim/Github/typed-argument-parser/tap/tap.py", line 277, in _log_allįile "/data/nlim/Github/typed-argument-parser/tap/tap.py", line 265, in get_reproducibility_info 'data_path': '/data/nlim/Projects/hitlist-clean.csv',įatal: not a git repository (or any parent up to mount point /data) Python /data/nlim/Github/chemprop/train.py -data_path /data/nlim/Projects//hitlist-clean.csv -save_dir full_checkpoints -dataset_type regression -smiles_column SMILES -target_columns Score -num_workers 48 -gpu 0 -batch_size 5000 Subprocess.CalledProcessError: Command '' returned non-zero exit status 129. Return subprocess.check_output(command).decode('utf-8').strip()įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/subprocess.py", line 411, in check_outputįile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/subprocess.py", line 512, in run Url = check_output()įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/site-packages/tap/utils.py", line 30, in check_output Reproducibility = get_git_url(commit_hash=True)įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/site-packages/tap/utils.py", line 61, in get_git_url Json.dump(self._log_all(), f, indent=4, sort_keys=True, cls=PythonObjectEncoder)įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/site-packages/tap/tap.py", line 277, in _log_allĪrg_log = self.get_reproducibility_info()įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/site-packages/tap/tap.py", line 266, in get_reproducibility_info Model_scores = run_training(args, logger)įile "/data/nlim/Github/chemprop/chemprop/train/run_training.py", line 48, in run_trainingĪrgs.save(os.path.join(args.save_dir, 'args.json'))įile "/data/nlim/anaconda3/envs/chemprop/lib/python3.7/site-packages/tap/tap.py", line 445, in save v, -verbose be verbose must be placed before a subcommandįile "/data/nlim/Github/chemprop/chemprop/train/cross_validate.py", line 29, in cross_validate Python train.py -data_path data/tox21.csv -dataset_type classification -save_dir tox21_checkpoints (chemprop) python train.py -data_path data/tox21.csv -dataset_type classification -save_dir tox21_checkpoints
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |