aspuru-guzik-group / ga Goto Github PK

I am unable to resolve 'RuntimeError An attack has been made to start a new process before the current process has finished its bootstrapping phase.' Requesting assistance with this issue！

Hi all,

When I run the core_GA script with a list of 6 starting SELFiES, I appear to be running into a numpy operator issue when it tries to compute the fitness using the normalized values of logP, SAS and RingP. Was wondering if anyone ever ran into this before and whether it's an issue with my starting dataset or a newer version of a dependency?

   ###   On generation 1 of 200
Traceback (most recent call last):
  File "core_GA.py", line 130, in <module>
    impose_time_adapted_pen    = False
  File "core_GA.py", line 55, in initiate_ga
    image_dir,          data_dir,      max_fitness_collector, impose_time_adapted_pen)
  File "/nfshomes/schithrananda/generative_ml_experiments/GA/generation_props.py", line 296, in obtain_fitness
    disc_enc_type, generation_index,   max_molecules_len, device, num_processors, writer, beta, data_dir, max_fitness_collector, impose_time_adapted_pen) 
  File "/nfshomes/schithrananda/generative_ml_experiments/GA/generation_props.py", line 164, in fitness
    fitness = (logP_norm) - (SAS_norm) - (RingP_norm)
ValueError: operands could not be broadcast together with shapes (500,1) (0,1) 

Beyond modifying the starting_selfies to use a custom one rather than a sample of ZINC - these are the settings I used:

            # Initiate the Genetic Algorithm
            smiles_all_counter = initiate_ga(    num_generations            = 200,
                                                 generation_size            = 500,
                                                 starting_selfies           = selfies_list, # pass reference selfies
                                                 max_molecules_len          = 100, #changed to 100
                                                 disc_epochs_per_generation = 10,
                                                 disc_enc_type              = 'properties_rdkit',         # 'selfies' or 'smiles' or 'properties_rdkit'
                                                 disc_layers                = [100, 10],
                                                 training_start_gen         = 0,                          # generation index to start training discriminator
                                                 device                     = 'cpu',
                                                 # pass all penalties for now since I want to see ring size, synthesizability, drug-likeness and logP
                                                 properties_calc_ls         = ['logP', 'SAS', 'QED' 'RingP'],   # None: No properties ; 'logP', 'SAS', 'RingP', 'QED'
                                                 num_processors             = multiprocessing.cpu_count(),
                                                 beta                       = beta,
                                                 max_fitness_collector      = max_fitness_collector,
                                                 impose_time_adapted_pen    = True
                                            )
            

File "", line 1, in
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 125, in _main
prepare(preparation_data)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "/Users/opt/anaconda3/lib/python3.8/runpy.py", line 265, in run_path
return _run_module_code(code, init_globals, run_name,
File "/Users/opt/anaconda3/lib/python3.8/runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "/Users/opt/anaconda3/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/Users/Workspace/GA-master/core_GA.py", line 4, in
import discriminator as D
File "/Users/Workspace/GA-master/discriminator.py", line 3, in
import evolution_functions as evo
File "/Users/Workspace/GA-master/evolution_functions.py", line 15, in
manager = multiprocessing.Manager()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/context.py", line 57, in Manager
m.start()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/managers.py", line 579, in start
self._process.start()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 32, in init
super().init(process_obj)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/popen_fork.py", line 19, in init
self._launch(process_obj)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 42, in _launch
prep_data = spawn.get_preparation_data(process_obj._name)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Traceback (most recent call last):
File "core_GA.py", line 4, in
import discriminator as D
File "/Users/Workspace/repos/GA-master/discriminator.py", line 3, in
import evolution_functions as evo
File "/Users/Workspace/GA-master/evolution_functions.py", line 15, in
manager = multiprocessing.Manager()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/context.py", line 57, in Manager
m.start()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/managers.py", line 583, in start
self._address = reader.recv()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/connection.py", line 250, in recv
buf = self._recv_bytes()
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/connection.py", line 414, in _recv_bytes
buf = self._recv(4)
File "/Users/opt/anaconda3/lib/python3.8/multiprocessing/connection.py", line 383, in _recv
raise EOFError
EOFError

env: python3.8

    ## Impose the beta cuttoff! --------------------------
    if impose_time_adapted_pen: 
        if generation_index > 100:
            # Check if there is a stagnation for 5 generations! (检查了 max_fitness_collector 列表的最后五个元素是否都是相同的)
            if len(set(max_fitness_collector[-5:])) == 1:
                beta = 1000
                print('Beta cutoff imposed  index: ', generation_index)
                f = open('{}/beta_change_log.txt'.format(data_dir), 'a+')
                f.write(str(generation_index) + '\n')
                f.close()
    ## beta cuttoff imposed! --------------------------

fitness = (beta * discriminator_predictions) + fitness

when the len(set(max_fitness_collector[-5:])) == 1:, then the fitness is very big, and get the order, But the change doesn't seem to be working? It simply increases the overall fitness of the population in this generation