def run_enhc(iter_index,
json_file,
machine_json,
base_dir='./'):
json_file = os.path.abspath(json_file)
base_dir = os.path.abspath(base_dir) + "/"
iter_name = make_iter_name(iter_index)
work_path = base_dir + iter_name + "/" + enhc_name + "/"
fp = open(json_file, 'r')
jdata = json.load(fp)
fp.close()
gmx_prep = jdata["gmx_prep"]
gmx_run = jdata["gmx_run"]
enhc_thread = jdata["enhc_thread"]
gmx_run = gmx_run + (" -nt %d" % enhc_thread)
gmx_prep_log = "gmx_grompp.log"
gmx_run_log = "gmx_mdrun.log"
# assuming at least one walker
graph_files = glob.glob(work_path + (make_walker_name(0)) + "/*.pb")
if len(graph_files) != 0:
gmx_run = gmx_run + " -plumed " + enhc_plm
else:
gmx_run = gmx_run + " -plumed " + enhc_bf_plm
gmx_prep_cmd = cmd_append_log(gmx_prep, gmx_prep_log)
gmx_run_cmd = cmd_append_log(gmx_run, gmx_run_log)
numb_walkers = jdata["numb_walkers"]
all_task = list(filter(lambda x: os.path.isdir(
x), glob.glob(work_path + "/[0-9]*[0-9]")))
all_task.sort()
all_task_basedir = [os.path.relpath(ii, work_path) for ii in all_task]
print('run_enhc:work_path', work_path)
print('run_enhc:gmx_prep_cmd:', gmx_prep_cmd)
print('run_enhc:gmx_run_cmd:', gmx_run_cmd)
print('run_enhc:all_task:', all_task)
print('run_enhc:all_task_basedir:', all_task_basedir)
machine = set_machine(machine_json, target="enhcMD")
resources = set_resource(machine_json, target="enhcMD")
gmx_prep_task = [Task(command=gmx_prep_cmd, task_work_path=ii,
outlog='gmx_grompp.log', errlog='gmx_grompp.log') for ii in all_task_basedir]
gmx_prep_submission = Submission(
work_base=work_path, machine=machine, resources=resources, task_list=gmx_prep_task)
gmx_prep_submission.run_submission()
gmx_run_task = [Task(command=gmx_run_cmd, task_work_path=ii,
outlog='gmx_mdrun.log', errlog='gmx_mdrun.log') for ii in all_task_basedir]
gmx_run_submission = Submission(
work_base=work_path, machine=machine, resources=resources, task_list=gmx_run_task)
gmx_run_submission.run_submission()
def post_enhc(iter_index, json_file, machine_json, base_dir="./"):
base_dir = os.path.abspath(base_dir) + "/"
iter_name = make_iter_name(iter_index)
work_path = base_dir + iter_name + "/" + enhc_name + "/"
json_file = os.path.abspath(json_file)
json_file = os.path.abspath(json_file)
fp = open(json_file, 'r')
jdata = json.load(fp)
fp.close()
gmx_split = jdata["gmx_split_traj"]
gmx_split_log = "gmx_split.log"
gmx_split_cmd = cmd_append_log(gmx_split, gmx_split_log)
all_task = list(
filter(lambda x: os.path.isdir(x),
glob.glob(work_path + "/[0-9]*[0-9]")))
all_task.sort()
cwd = os.getcwd()
numb_walkers = jdata["numb_walkers"]
for ii in range(numb_walkers):
walker_path = work_path + make_walker_name(ii) + "/"
os.chdir(walker_path)
if os.path.isdir("confs"):
shutil.rmtree("confs")
os.makedirs("confs")
os.chdir(cwd)
print('rid.py:post_enhc:gmx_split_cmd', gmx_split_cmd)
print('rid.py:post_enhc:work path', work_path)
machine = set_machine(machine_json, target="post_enhc")
resources = set_resource(machine_json, target="post_enhc")
all_task_relpath = [os.path.relpath(ii, work_path) for ii in all_task]
gmx_split_task = [
Task(command=gmx_split_cmd,
task_work_path=ii,
outlog='gmx_split.log',
errlog='gmx_split.log') for ii in all_task_relpath
]
gmx_split_submission = Submission(work_base=work_path,
resources=resources,
machine=machine,
task_list=gmx_split_task)
gmx_split_submission.run_submission()
for ii in range(numb_walkers):
walker_path = work_path + make_walker_name(ii) + "/"
angles = np.loadtxt(walker_path + enhc_out_plm)
np.savetxt(walker_path + enhc_out_angle, angles[:, 1:], fmt="%.6f")
print("Post process of enhanced sampling finished.")
def run_res(iter_index, json_file, machine_json, base_dir="./"):
json_file = os.path.abspath(json_file)
fp = open(json_file, 'r')
jdata = json.load(fp)
fp.close()
gmx_prep = jdata["gmx_prep"]
gmx_run = jdata["gmx_run"]
res_thread = jdata["res_thread"]
gmx_run = gmx_run + (" -nt %d" % res_thread)
gmx_run = gmx_run + " -plumed " + res_plm
# gmx_cont_run = gmx_run + " -cpi state.cpt"
gmx_prep_log = "gmx_grompp.log"
gmx_run_log = "gmx_mdrun.log"
gmx_prep_cmd = cmd_append_log(gmx_prep, gmx_prep_log)
gmx_run_cmd = cmd_append_log(gmx_run, gmx_run_log)
# gmx_cont_run_cmd = cmd_append_log (gmx_cont_run, gmx_run_log)
base_dir = os.path.abspath(base_dir) + "/"
iter_name = make_iter_name(iter_index)
res_path = base_dir + iter_name + "/" + res_name + "/"
if not os.path.isdir(res_path):
raise RuntimeError("do not see any restrained simulation (%s)." %
res_path)
all_task = list(
filter(lambda x: os.path.isdir(x),
glob.glob(res_path + "/[0-9]*[0-9]")))
print('run_res:all_task_propose:', all_task)
print('run_res:gmx_prep_cmd:', gmx_prep_cmd)
print('run_res:gmx_run_cmd:', gmx_run_cmd)
# print('run_res:gmx_cont_run_cmd:', gmx_cont_run_cmd)
if len(all_task) == 0:
return None
all_task.sort()
all_task_basedir = [os.path.relpath(ii, res_path) for ii in all_task]
res_resources = set_resource(machine_json, target="resMD")
machine = set_machine(machine_json, target="resMD")
gmx_prep_task = [
Task(command=gmx_prep_cmd,
task_work_path=ii,
outlog='gmx_grompp.log',
errlog='gmx_grompp.log') for ii in all_task_basedir
]
gmx_prep_submission = Submission(work_base=res_path,
machine=machine,
resources=res_resources,
task_list=gmx_prep_task)
gmx_prep_submission.run_submission()
gmx_run_task = [
Task(command=gmx_run_cmd,
task_work_path=ii,
outlog='gmx_mdrun.log',
errlog='gmx_mdrun.log') for ii in all_task_basedir
]
gmx_run_submission = Submission(work_base=res_path,
machine=machine,
resources=res_resources,
task_list=gmx_run_task)
gmx_run_submission.run_submission()
def test_cmd_append_log(self):
cmd_log = utils.cmd_append_log("gmx mdrun -deffnm em", 'md.log')
_cmd_log = "gmx mdrun -deffnm em 1> md.log 2> md.log"
self.assertTrue(cmd_log, _cmd_log)
def run_train(iter_index, json_file, machine_json, cv_file, base_dir="./"):
json_file = os.path.abspath(json_file)
cv_file = os.path.abspath(cv_file)
fp = open(json_file, 'r')
jdata = json.load(fp)
fp.close()
cv_file = os.path.abspath(cv_file)
numb_model = jdata["numb_model"]
train_thread = jdata["train_thread"]
res_iter = jdata["res_iter"]
base_dir = os.path.abspath(base_dir) + "/"
iter_name = make_iter_name(iter_index)
train_path = base_dir + iter_name + "/" + train_name + "/"
if check_new_data(iter_index, train_path, base_dir):
return
enhc_path = base_dir + iter_name + "/" + enhc_name + "/"
_conf_file = enhc_path + "000/conf.gro"
cv_dim_list = cal_cv_dim(_conf_file, cv_file)
cwd = os.getcwd()
neurons = jdata["neurons"]
batch_size = jdata["batch_size"]
if iter_index < res_iter:
numb_epoches = jdata["numb_epoches"]
starter_lr = jdata["starter_lr"]
decay_steps = jdata["decay_steps"]
decay_rate = jdata["decay_rate"]
cmdl_args = ""
else:
numb_epoches = jdata["res_numb_epoches"]
starter_lr = jdata["res_starter_lr"]
decay_steps = jdata["res_decay_steps"]
decay_rate = jdata["res_decay_rate"]
old_ratio = jdata["res_olddata_ratio"]
cmdl_args = " --restart --use-mix --old-ratio %f " % old_ratio
if jdata["resnet"]:
cmdl_args += " --resnet "
cmdl_args += " -n "
for nn in neurons:
cmdl_args += "%d " % nn
cmdl_args += " -c "
for cv_dim in cv_dim_list:
cmdl_args += "%d " % cv_dim
cmdl_args += " -b " + str(batch_size)
cmdl_args += " -e " + str(numb_epoches)
cmdl_args += " -l " + str(starter_lr)
cmdl_args += " --decay-steps " + str(decay_steps)
cmdl_args += " --decay-rate " + str(decay_rate)
train_cmd = "python3 {}/train.py -t {:d}".format(NN_PATH, train_thread)
train_cmd += cmdl_args
train_cmd = cmd_append_log(train_cmd, "train.log")
freez_cmd = "python3 {}/freeze.py -o graph.pb".format(NN_PATH)
freez_cmd = cmd_append_log(freez_cmd, "freeze.log")
task_dirs = [("%03d" % ii) for ii in range(numb_model)]
print('lib.modeling.run_train:train_cmd:', train_cmd)
print('lib.modeling.run_train:freez_cmd:', freez_cmd)
print('lib.modeling.run_train:train_path:', train_path)
print('lib.modeling.run_train:task_dirs:', task_dirs)
resources = set_resource(machine_json, target="train")
machine = set_machine(machine_json, target="train")
train_task = [
Task(command=train_cmd,
task_work_path=ii,
outlog='train.log',
errlog='train.log') for ii in task_dirs
]
train_submission = Submission(work_base=train_path,
machine=machine,
resources=resources,
task_list=train_task)
train_submission.run_submission()
freez_task = [
Task(command=freez_cmd,
task_work_path=ii,
outlog='freeze.log',
errlog='freeze.log') for ii in task_dirs
]
freez_submission = Submission(work_base=train_path,
machine=machine,
resources=resources,
task_list=freez_task)
freez_submission.run_submission()
os.chdir(train_path)
for ii in range(numb_model):
os.symlink("%03d/graph.pb" % ii, "graph.%03d.pb" % ii)
os.chdir(cwd)
print("Training finished!")