HydraException: config_path in initialize() must be relative

#1

I have downloaded the dataset and devkit in E: directory and also installed miniconda3 in the same directory. and after activating nuplan using the command: conda activate nuplan, I opened jupyter notebook and followed the instructions for preparing training config, but when I run the commands it is showing the following error:



# Location of path with all training configs
CONFIG_PATH = '../nuplan/planning/script/config/training'
CONFIG_NAME = 'default_training'

# Create a temporary directory to store the cache and experiment artifacts
SAVE_DIR = Path(tempfile.gettempdir()) / 'tutorial_nuplan_framework'  # optionally replace with persistent dir
EXPERIMENT = 'training_raster_experiment'
JOB_NAME = 'train_default_raster'
LOG_DIR = str(SAVE_DIR / EXPERIMENT / JOB_NAME)

# Initialize configuration management system
hydra.core.global_hydra.GlobalHydra.instance().clear()
hydra.initialize(config_path=CONFIG_PATH)

# Compose the configuration
cfg = hydra.compose(config_name=CONFIG_NAME, overrides=[
   f'group={str(SAVE_DIR)}',
   f'cache.cache_path={str(SAVE_DIR)}/cache',
   f'experiment_name={EXPERIMENT}',
   f'job_name={JOB_NAME}',
   'py_func=train',
   '+training=training_raster_model',  # raster model that consumes ego, agents and map raster layers and regresses the ego's trajectory
   'scenario_builder=nuplan_mini',  # use nuplan mini database
   'scenario_filter.limit_total_scenarios=500',  # Choose 500 scenarios to train with
   'lightning.trainer.params.accelerator=ddp_spawn',  # ddp is not allowed in interactive environment, using ddp_spawn instead - this can bottleneck the data pipeline, it is recommended to run training outside the notebook
   'lightning.trainer.params.max_epochs=10',
   'data_loader.params.batch_size=8',
   'data_loader.params.num_workers=8',
])

The following is the error that is reported:



HydraException                            Traceback (most recent call last)
Cell In[7], line 13
     11 # Initialize configuration management system
     12 hydra.core.global_hydra.GlobalHydra.instance().clear()
---> 13 hydra.initialize(config_path=CONFIG_PATH)
     15 # Compose the configuration
     16 cfg = hydra.compose(config_name=CONFIG_NAME, overrides=[
     17     f'group={str(SAVE_DIR)}',
     18     f'cache.cache_path={str(SAVE_DIR)}/cache',
   (...)
     28     'data_loader.params.num_workers=8',
     29 ])

File E:\Miniconda\envs\nuplan\lib\site-packages\hydra\initialize.py:76, in initialize.__init__(self, config_path, job_name, caller_stack_depth)
     73     config_path = "."
     75 if config_path is not None and os.path.isabs(config_path):
---> 76     raise HydraException("config_path in initialize() must be relative")
     77 calling_file, calling_module = detect_calling_file_or_module_from_stack_frame(
     78     caller_stack_depth + 1
     79 )
     80 if job_name is None:

HydraException: config_path in initialize() must be relative

Please help, where I need to change code