strange error: isinstance() arg 2 must be a type or tuple of types

[Arthurwyf]

MKL_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=1 python run.py +experiment=speaker_ecapa_tdnn tune_model=True data/module=dogbark trainer.auto_lr_find=auto_lr_find tune_iterations=5000 /home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/pytorch_lightning/core/decorators.py:65: LightningDeprecationWarning: The @auto_move_data decorator is deprecated in v1.3 and will be removed in v1.5. Please use trainer.predict instead for inference. The decorator was applied to forward rank_zero_deprecation( /home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/pytorch_lightning/core/decorators.py:65: LightningDeprecationWarning: The @auto_move_data decorator is deprecated in v1.3 and will be removed in v1.5. Please use trainer.predict instead for inference. The decorator was applied to forward rank_zero_deprecation( data_folder: ${oc.env:DATA_FOLDER} temp_folder: ${oc.env:TEMP_FOLDER} log_folder: ${oc.env:LOG_FOLDER} seed: 42133724 tune_model: true tune_iterations: 5000 verify_model: false fit_model: true eval_model: true load_network_from_checkpoint: null use_cometml: ${oc.decode:${oc.env:USE_COMET_ML}} gpus: ${oc.decode:${oc.env:NUM_GPUS}} project_name: ecapa-tdnn experiment_name: ${random_uuid:} tag: ${now:%Y-%m-%d} callbacks: to_add:

• lr_monitor
• ram_monitor
• checkpoint lr_monitor: target: pytorch_lightning.callbacks.LearningRateMonitor ram_monitor: target: src.callbacks.memory_monitor.RamMemoryMonitor frequency: 100 checkpoint: target: pytorch_lightning.callbacks.model_checkpoint.ModelCheckpoint monitor: val_eer save_top_k: 1 mode: min filename: '{epoch}.{step}.{val_eer:.4f}.best' save_last: true every_n_val_epochs: 1 last_checkpoint_pattern: '{epoch}.{step}.{val_eer:.4f}.last' data: module: target: src.data.modules.speaker.voxceleb.VoxCelebDataModuleConfig use_voxceleb1_dev: true use_voxceleb1_test: true use_voxceleb2_dev: false use_voxceleb2_test: false all_voxceleb1_is_test_set: false has_train: true has_val: false has_test: true test_split_file_path: ${data_folder}/veri_test.txt shards_folder: ${data_folder}/dog_barking_shards extraction_folder: ${temp_folder}/dog_barking split_mode: equal train_val_ratio: 0.97 num_val_speakers: -1 eer_validation_pairs: 10000 sequential_same_speaker_samples: 1 min_unique_speakers_per_shard: 500 discard_partial_shards: true voxceleb1_train_zip_path: ${data_folder}/voxceleb_archives/vox1_dev_wav.zip voxceleb1_test_zip_path: ${data_folder}/voxceleb_archives/vox1_test_wav.zip voxceleb2_train_zip_path: ${data_folder}/voxceleb_archives/vox2_dev_wav.zip voxceleb2_test_zip_path: ${data_folder}/voxceleb_archives/vox2_test_wav.zip train_collate_fn: pad_right val_collate_fn: default test_collate_fn: default add_batch_debug_info: false limit_samples: -1 batch_processing_mode: categorical pipeline: train_pipeline:
  • selector_train
  • filterbank
  • normalizer val_pipeline:
  • selector_val
  • filterbank
  • normalizer test_pipeline:
  • filterbank
  • normalizer selector_train: target: src.data.preprocess.random_chunks.AudioChunkSelector selection_strategy: random desired_chunk_length_sec: 3 selector_val: target: src.data.preprocess.random_chunks.AudioChunkSelector selection_strategy: start desired_chunk_length_sec: 3 filterbank: target: src.data.preprocess.audio_features.FilterBank n_mels: 40 normalizer: target: src.data.preprocess.input_normalisation.InputNormalizer2D normalize_over_channels: true shards: target: src.data.common.WebDataSetShardConfig samples_per_shard: 500 use_gzip_compression: true shuffle_shards: true queue_size: 1024 dataloader: target: src.data.common.SpeakerDataLoaderConfig train_batch_size: 32 val_batch_size: ${data.dataloader.train_batch_size} test_batch_size: 1 num_workers: 2 pin_memory: true evaluator: target: src.evaluation.speaker.cosine_distance.CosineDistanceEvaluator center_before_scoring: false length_norm_before_scoring: false max_num_training_samples: 0 network: target: src.lightning_modules.speaker.ecapa_tdnn.EcapaTDNNModuleConfig input_mel_coefficients: ${data.pipeline.filterbank.n_mels} lin_neurons: 192 channels:
• 1024
• 1024
• 1024
• 1024
• 3072 kernel_sizes:
• 5
• 3
• 3
• 3
• 1 dilations:
• 1
• 2
• 3
• 4
• 1 attention_channels: 128 res2net_scale: 8 se_channels: 128 global_context: true pretrained_weights_path: null explicit_stat_pool_embedding_size: null explicit_num_speakers: null tokenizer: target: src.tokenizer.tokenizer_wav2vec2.Wav2vec2TokenizerConfig tokenizer_huggingface_id: facebook/wav2vec2-base-960h optim: algo: target: torch.optim.Adam lr: 0.0001 weight_decay: 0 betas:
  • 0.9
  • 0.999 eps: 1.0e-08 amsgrad: false schedule: scheduler: target: torch.optim.lr_scheduler.OneCycleLR max_lr: ${optim.algo.lr} total_steps: ${trainer.max_steps} div_factor: 25 monitor: null interval: step frequency: null name: null loss: target: src.optim.loss.aam_softmax.AngularAdditiveMarginSoftMaxLoss input_features: 192 output_features: 5994 margin: 0.2 scale: 30 output_features: 48 trainer: target: pytorch_lightning.Trainer gpus: ${gpus} accelerator: null num_nodes: 1 min_epochs: null max_epochs: null min_steps: null max_steps: 100000 val_check_interval: 5000 accumulate_grad_batches: 1 progress_bar_refresh_rate: 500 deterministic: false limit_train_batches: 1.0 limit_val_batches: 1.0 limit_test_batches: 1.0 fast_dev_run: false precision: 32 num_sanity_val_steps: 2 auto_lr_find: auto_lr_find gradient_clip_val: 0

3.9.0 pytorch_lightning.version='1.4.5' torch.version='1.8.2+cu102' [2023-03-27 20:54:04,608][pytorch_lightning.utilities.seed][INFO] - Global seed set to 42133724 Error executing job with overrides: ['+experiment=speaker_ecapa_tdnn', 'tune_model=True', 'data/module=dogbark', 'trainer.auto_lr_find=auto_lr_find', 'tune_iterations=5000'] Traceback (most recent call last): File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 62, in _call_target return target(*args, **kwargs) File "", line 33, in init File "/home/arthur/dog_verification/w2v2-speaker-master/src/config_util.py", line 26, in __post_init__ post_init_type_cast(self) File "/home/arthur/dog_verification/w2v2-speaker-master/src/config_util.py", line 41, in post_init_type_cast elif isinstance(value, typehint_cls): TypeError: isinstance() arg 2 must be a type or tuple of types

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/utils.py", line 211, in run_and_report return func() File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/utils.py", line 368, in lambda: hydra.run( File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/internal/hydra.py", line 110, in run = ret.return_value File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/core/utils.py", line 233, in return_value raise self._return_value File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/core/utils.py", line 160, in run_job ret.return_value = task_function(task_cfg) File "run.py", line 38, in run return run_train_eval_script(cfg) File "/home/arthur/dog_verification/w2v2-speaker-master/src/main.py", line 429, in run_train_eval_script dm = construct_data_module(cfg) File "/home/arthur/dog_verification/w2v2-speaker-master/src/main.py", line 127, in construct_data_module dm_cfg = hydra.utils.instantiate(cfg.data.module) File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 180, in instantiate return instantiate_node(config, args, recursive=recursive, convert=convert) File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 249, in instantiate_node return _call_target(target, args, *kwargs) File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 64, in _call_target raise type(e)( File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 62, in _call_target return target(args, **kwargs) File "", line 33, in init File "/home/arthur/dog_verification/w2v2-speaker-master/src/config_util.py", line 26, in __post_init__ post_init_type_cast(self) File "/home/arthur/dog_verification/w2v2-speaker-master/src/config_util.py", line 41, in post_init_type_cast elif isinstance(value, typehint_cls): TypeError: Error instantiating 'src.data.modules.speaker.voxceleb.VoxCelebDataModuleConfig' : isinstance() arg 2 must be a type or tuple of types

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "run.py", line 48, in run() File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/main.py", line 49, in decorated_main _run_hydra( File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/utils.py", line 367, in _run_hydra run_and_report( File "/home/arthur/.conda/envs/w2v2/lib/python3.8/site-packages/hydra/_internal/utils.py", line 251, in run_and_report assert mdl is not None AssertionError