search

sg-nm / cgp-cnn-PyTorch

A Genetic Programming Approach to Designing CNN Architectures, In GECCO 2017 (oral presentation, Best Paper Award)
MIT License
46 stars 24 forks source link

AssertionError: group argument must be None for now #11

Closed archeltaneka closed 3 years ago

archeltaneka commented 3 years ago

Hi, I encountered an error while executing the exp_main.py. I got this following error:

Traceback (most recent call last): File "exp_main.py", line 36, in cgp.modified_evolution(max_eval=250, mutation_rate=0.1, log_file=args.log_file) File "D:\Archel\Mini Projects\cgp-cnn-PyTorch\cgp.py", line 288, in modified_evolution self._evaluation([self.pop[0]], np.array([True])) File "D:\Archel\Mini Projects\cgp-cnn-PyTorch\cgp.py", line 231, in _evaluation fp = self.eval_func(net_lists) File "D:\Archel\Mini Projects\cgp-cnn-PyTorch\cgp_config.py", line 51, in call pool = NoDaemonProcessPool(process_num) File "C:\Users\Archel\anaconda3\envs\machine-learning\lib\multiprocessing\pool.py", line 212, in init self._repopulate_pool() File "C:\Users\Archel\anaconda3\envs\machine-learning\lib\multiprocessing\pool.py", line 303, in _repopulate_pool return self._repopulate_pool_static(self._ctx, self.Process, File "C:\Users\Archel\anaconda3\envs\machine-learning\lib\multiprocessing\pool.py", line 319, in _repopulate_pool_static w = Process(ctx, target=worker, File "C:\Users\Archel\anaconda3\envs\machine-learning\lib\multiprocessing\process.py", line 82, in init assert group is None, 'group argument must be None for now' AssertionError: group argument must be None for now

My environment: Python 3.8.5 PyTorch 1.6.0 CUDA 10.2 Windows 10 64-bit (20H2)