omegaconf.errors.ConfigKeyError: Key 'config' not in 'InferredConfig'

[mjiangtao]

When I run the code 'omegaconf.errors.ConfigKeyError: Key 'config' not in 'InferredConfig'', it return a mistake that shows '
[5 rows x 3 columns]
{'target': ['CVDdeath2024'], 'continuous_cols': ['Age', 'BMI', 'Waist', 'Hipline', 'Neckcircumference', 'meanSBP', 'meanDBP', 'HR', 'ALT', 'AST', 'GGT', 'ALP', 'TP', 'TBIL', 'BT', 'UREA', 'CREA', 'UA', 'TG', 'CHOL', 'LDLc1', 'HDLc1', 'CK', 'WBC', 'RBC', 'HGB', 'PLT', 'HbA1C', 'eGFR', 'SIRI', 'PRI', 'QRSI', 'QT', 'QTc', 'PEleaxis', 'REleaxis', 'TEleaxis', 'Ravl', 'SV1', 'SV3', 'SV4', 'RV5', 'RV6', 'Smax', 'SmaxD', 'CbulbD', 'ICADmean', 'IMTmean', 'CCAD', 'CPT'], 'categorical_cols': ['Sex', 'Currentsmoking', 'Currentdrinking', 'Lackexercise', 'Eduaction', 'overweightobesity', 'HP', 'DM', 'Dyslipidemia', 'CAD', 'Stroke', 'Electrocardiogram', 'stenosis_Grade', 'CAS', 'dzT'], 'date_columns': [], 'encode_date_columns': True, 'validation_split': 0.2, 'continuous_feature_transform': None, 'normalize_continuous_features': True, 'quantile_noise': 0, 'num_workers': 0, 'pin_memory': True, 'handle_unknown_categories': True, 'handle_missing_values': True, 'pickle_protocol': 2, 'dataloader_kwargs': {}, 'task': 'classification', 'head': 'LinearHead', 'head_config': {'layers': ''}, 'embedding_dims': None, 'embedding_dropout': 0.0, 'batch_norm_continuous_input': True, 'learning_rate': 0.001, 'loss': 'CrossEntropyLoss', 'metrics': ['f1_score', 'accuracy'], 'metrics_prob_input': [False, False], 'metrics_params': [{'num_classes': 2, 'average': 'macro'}, {}], 'target_range': None, 'virtual_batch_size': None, 'seed': 42, '_module_src': 'models.tab_transformer', '_model_name': 'TabTransformerModel', '_backbone_name': 'TabTransformerBackbone', '_config_name': 'TabTransformerConfig', 'input_embed_dim': 32, 'embedding_initialization': 'kaiming_uniform', 'embedding_bias': False, 'share_embedding': True, 'share_embedding_strategy': 'add', 'shared_embedding_fraction': 0.25, 'num_heads': 8, 'num_attn_blocks': 6, 'transformer_head_dim': None, 'attn_dropout': 0.1, 'add_norm_dropout': 0.1, 'ff_dropout': 0.1, 'ff_hidden_multiplier': 4, 'transformer_activation': 'GEGLU', 'batch_size': 512, 'data_aware_init_batch_size': 2000, 'fast_dev_run': False, 'max_epochs': 20, 'min_epochs': 10, 'max_time': None, 'accelerator': 'auto', 'devices': -1, 'devices_list': None, 'accumulate_grad_batches': 1, 'auto_lr_find': False, 'auto_select_gpus': True, 'check_val_every_n_epoch': 1, 'gradient_clip_val': 0.0, 'overfit_batches': 0.0, 'deterministic': False, 'profiler': None, 'early_stopping': 'valid_loss', 'early_stopping_min_delta': 0.001, 'early_stopping_mode': 'min', 'early_stopping_patience': 3, 'early_stopping_kwargs': {}, 'checkpoints': 'valid_loss', 'checkpoints_path': 'saved_models', 'checkpoints_every_n_epochs': 1, 'checkpoints_name': None, 'checkpoints_mode': 'min', 'checkpoints_save_top_k': 1, 'checkpoints_kwargs': {}, 'load_best': True, 'track_grad_norm': -1, 'progress_bar': 'rich', 'precision': '32', 'trainer_kwargs': {}, 'project_name': 'GATE Dev', 'run_name': 'gate_w_t_softmax_w_init', 'exp_watch': 'gradients', 'log_target': 'wandb', 'log_logits': True, 'exp_log_freq': 100, 'optimizer': 'Adam', 'optimizer_params': {}, 'lr_scheduler': None, 'lr_scheduler_params': {}, 'lr_scheduler_monitor_metric': 'valid_loss', 'categorical_dim': 15, 'enable_checkpointing': True}
{'config': {'target': ['CVDdeath2024'], 'continuous_cols': ['Age', 'BMI', 'Waist', 'Hipline', 'Neckcircumference', 'meanSBP', 'meanDBP', 'HR', 'ALT', 'AST', 'GGT', 'ALP', 'TP', 'TBIL', 'BT', 'UREA', 'CREA', 'UA', 'TG', 'CHOL', 'LDLc1', 'HDLc1', 'CK', 'WBC', 'RBC', 'HGB', 'PLT', 'HbA1C', 'eGFR', 'SIRI', 'PRI', 'QRSI', 'QT', 'QTc', 'PEleaxis', 'REleaxis', 'TEleaxis', 'Ravl', 'SV1', 'SV3', 'SV4', 'RV5', 'RV6', 'Smax', 'SmaxD', 'CbulbD', 'ICADmean', 'IMTmean', 'CCAD', 'CPT'], 'categorical_cols': ['Sex', 'Currentsmoking', 'Currentdrinking', 'Lackexercise', 'Eduaction', 'overweightobesity', 'HP', 'DM', 'Dyslipidemia', 'CAD', 'Stroke', 'Electrocardiogram', 'stenosis_Grade', 'CAS', 'dzT'], 'date_columns': [], 'encode_date_columns': True, 'validation_split': 0.2, 'continuous_feature_transform': None, 'normalize_continuous_features': True, 'quantile_noise': 0, 'num_workers': 0, 'pin_memory': True, 'handle_unknown_categories': True, 'handle_missing_values': True, 'pickle_protocol': 2, 'dataloader_kwargs': {}, 'task': 'classification', 'head': 'LinearHead', 'head_config': {'layers': ''}, 'embedding_dims': None, 'embedding_dropout': 0.0, 'batch_norm_continuous_input': True, 'learning_rate': 0.001, 'loss': 'CrossEntropyLoss', 'metrics': ['f1_score', 'accuracy'], 'metrics_prob_input': [False, False], 'metrics_params': [{'num_classes': 2, 'average': 'macro'}, {}], 'target_range': None, 'virtual_batch_size': None, 'seed': 42, '_module_src': 'models.tab_transformer', '_model_name': 'TabTransformerModel', '_backbone_name': 'TabTransformerBackbone', '_config_name': 'TabTransformerConfig', 'input_embed_dim': 32, 'embedding_initialization': 'kaiming_uniform', 'embedding_bias': False, 'share_embedding': True, 'share_embedding_strategy': 'add', 'shared_embedding_fraction': 0.25, 'num_heads': 8, 'num_attn_blocks': 6, 'transformer_head_dim': None, 'attn_dropout': 0.1, 'add_norm_dropout': 0.1, 'ff_dropout': 0.1, 'ff_hidden_multiplier': 4, 'transformer_activation': 'GEGLU', 'batch_size': 512, 'data_aware_init_batch_size': 2000, 'fast_dev_run': False, 'max_epochs': 20, 'min_epochs': 10, 'max_time': None, 'accelerator': 'auto', 'devices': -1, 'devices_list': None, 'accumulate_grad_batches': 1, 'auto_lr_find': False, 'auto_select_gpus': True, 'check_val_every_n_epoch': 1, 'gradient_clip_val': 0.0, 'overfit_batches': 0.0, 'deterministic': False, 'profiler': None, 'early_stopping': 'valid_loss', 'early_stopping_min_delta': 0.001, 'early_stopping_mode': 'min', 'early_stopping_patience': 3, 'early_stopping_kwargs': {}, 'checkpoints': 'valid_loss', 'checkpoints_path': 'saved_models', 'checkpoints_every_n_epochs': 1, 'checkpoints_name': None, 'checkpoints_mode': 'min', 'checkpoints_save_top_k': 1, 'checkpoints_kwargs': {}, 'load_best': True, 'track_grad_norm': -1, 'progress_bar': 'rich', 'precision': '32', 'trainer_kwargs': {}, 'project_name': 'GATE Dev', 'run_name': 'gate_w_t_softmax_w_init', 'exp_watch': 'gradients', 'log_target': 'wandb', 'log_logits': True, 'exp_log_freq': 100, 'optimizer': 'Adam', 'optimizer_params': {}, 'lr_scheduler': None, 'lr_scheduler_params': {}, 'lr_scheduler_monitor_metric': 'valid_loss', 'categorical_dim': 15, 'enable_checkpointing': True}, 'inferred_config': {'categorical_dim': 15, 'continuous_dim': 50, 'output_dim': 2, 'output_cardinality': [2], 'categorical_cardinality': [3, 3, 3, 3, 5, 3, 3, 3, 3, 3, 3, 3, 5, 3, 3], 'embedding_dims': [[3, 2], [3, 2], [3, 2], [3, 2], [5, 3], [3, 2], [3, 2], [3, 2], [3, 2], [3, 2], [3, 2], [3, 2], [5, 3], [3, 2], [3, 2]], 'embedded_cat_dim': 32}}
Traceback (most recent call last):
File "D:\mjt\pytorch_tabular\22.py", line 114, in
new_model = TabularModel.load_model("test_save1")
File "D:\mjt\pytorch_tabular\src\pytorch_tabular\tabular_model.py", line 470, in load_model
model = model_callable.load_from_checkpoint(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\pytorch_lightning\utilities\model_helpers.py", line 125, in wrapper
return self.method(cls, *args, **kwargs)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\pytorch_lightning\core\module.py", line 1582, in load_from_checkpoint
loaded = _load_from_checkpoint(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\pytorch_lightning\core\saving.py", line 86, in _load_from_checkpoint
checkpoint[cls.CHECKPOINT_HYPER_PARAMS_KEY].update(kwargs)
File "C:\Users\User.conda\envs\tabr\lib_collections_abc.py", line 832, in update
self[key] = other[key]
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 310, in setitem
self._format_and_raise(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\base.py", line 231, in _format_and_raise
format_and_raise(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf_utils.py", line 819, in format_and_raise
_raise(ex, cause)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf_utils.py", line 797, in _raise
raise ex.with_traceback(sys.exc_info()[2]) # set env var OC_CAUSE=1 for full trace
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 308, in setitem
self.__set_impl(key=key, value=value)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 318, in __set_impl
self._set_item_impl(key, value)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\basecontainer.py", line 545, in _set_item_impl
self._validate_set(key, value)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 180, in _validate_set
target = self._get_node(key) if key is not None else self
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 475, in _get_node
self._validate_get(key)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\dictconfig.py", line 164, in _validate_get
self._format_and_raise(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf\base.py", line 231, in _format_and_raise
format_and_raise(
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf_utils.py", line 899, in format_and_raise
_raise(ex, cause)
File "C:\Users\User.conda\envs\tabr\lib\site-packages\omegaconf_utils.py", line 797, in _raise
raise ex.with_traceback(sys.exc_info()[2]) # set env var OC_CAUSE=1 for full trace
omegaconf.errors.ConfigKeyError: Key 'config' not in 'InferredConfig'
full_key: config
object_type=InferredConfig'. I have try many methods to deal with it,however Ican't. Can you help to to solve the problem, thank you.

[dosubot]

Hello @mjiangtao! I'm Dosu, your friendly bot here to help you solve bugs, answer questions, and assist you in becoming a contributor. I'm here while you wait for a human maintainer. Let's tackle that issue together!

The error you're encountering, omegaconf.errors.ConfigKeyError: Key 'config' not in 'InferredConfig', suggests that the key 'config' is missing in the InferredConfig object. This issue typically arises when the configuration structure expected by the code does not match the actual structure provided.

Here are a few steps you can take to resolve this issue:

1. Check Configuration Structure: Ensure that the configuration file or object you are using has the correct structure. The InferredConfig class in pytorch_tabular expects certain attributes, such as categorical_dim, continuous_dim, output_dim, etc. Make sure these attributes are correctly defined in your configuration ^[1].

2. Update Configuration Handling: If you are manually updating or merging configurations, ensure that the merge process correctly integrates the base configuration with the inferred configuration. The safe_merge_config function is used in pytorch_tabular to merge configurations safely, ensuring that existing values are preserved ^[2].

3. Verify Model Loading Process: When loading a model, ensure that the configuration is correctly passed and updated. The TabularModel class uses the safe_merge_config function to handle configuration updates during model loading ^[2].

4. Check for Missing Keys: If the error persists, manually inspect the configuration object to ensure all required keys are present. You might need to add missing keys or adjust the configuration structure to match the expected format.

By following these steps, you should be able to resolve the ConfigKeyError and ensure that your configuration is correctly handled during the model loading process.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}