Meet the problem when run the fb15k-237-image and wn18-images

[Larry-Liu02]

Dear authors, I met this problem when I ran the MKG task. I tried to solve it in the data_module file, but I failed. Have you ever met the same problem? warnings.warn( Namespace(accelerator=None, accumulate_grad_batches=1, amp_backend='native', amp_level='O2', auto_lr_find=False, auto_scale_batch_size=False, auto_select_gpus=False, automatic_optimization=None, batch_size=64, bce=0, benchmark=False, check_val_every_n_epoch=1, checkpoint=None, checkpoint_callback=True, chunk='', data_class='KGC', data_dir='dataset/FB15k-237', dataset='./dataset/NELL', default_root_dir=None, deterministic=False, distributed_backend=None, enable_pl_optimizer=None, eval_batch_size=64, fast_dev_run=False, flush_logs_every_n_steps=100, gpus='0,', gradient_clip_val=0, label_smoothing=0.1, limit_predict_batches=1.0, limit_test_batches=1.0, limit_train_batches=1.0, limit_val_batches=1.0, litmodel_class='TransformerLitModel', log_every_n_steps=50, log_gpu_memory=None, logger=True, lr=0.0005, max_epochs=15, max_seq_length=64, max_steps=None, min_epochs=None, min_steps=None, model_class='UnimoKGC', model_name_or_path='bert-base-uncased', move_metrics_to_cpu=False, multiple_trainloader_mode='max_size_cycle', num_nodes=1, num_processes=1, num_sanity_val_steps=2, num_workers=4, optimizer='AdamW', overfit_batches=0.0, overwrite_cache=True, plugins=None, precision=32, prepare_data_per_node=True, pretrain=1, process_position=0, profiler=None, progress_bar_refresh_rate=None, reload_dataloaders_every_epoch=False, replace_sampler_ddp=True, resume_from_checkpoint=None, seed=7, stochastic_weight_avg=False, sync_batchnorm=False, task_name='fb15k-237', terminate_on_nan=False, tpu_cores=None, track_grad_norm=-1, truncated_bptt_steps=None, val_check_interval=1.0, wandb=False, warm_up_radio=0.1, weight_decay=0.01, weights_save_path=None, weights_summary='top') Global seed set to 7 Load model state dict successful. 14951 unimo.text_embeddings.word_embeddings.weight GPU available: True, used: True TPU available: False, using: 0 TPU cores delete entities without text name.: 100%|█| 272115/272115 [00:00<00:00, 3973516. total entity not in text : 0 max number of filter entities : 4364 954 convert text to examples: 100%|████████| 14951/14951 [00:00<00:00, 87945.79it/s] 100%|███████████████████████████████████| 14951/14951 [00:02<00:00, 5994.50it/s] delete entities without text name.: 100%|█| 17535/17535 [00:00<00:00, 2904245.80 total entity not in text : 0 max number of filter entities : 4364 954 convert text to examples: 100%|████████| 14951/14951 [00:00<00:00, 85863.27it/s] 100%|███████████████████████████████████| 14951/14951 [00:02<00:00, 5965.58it/s] delete entities without text name.: 100%|█| 20466/20466 [00:00<00:00, 2953910.04 total entity not in text : 0 max number of filter entities : 4364 954 convert text to examples: 100%|███████| 14951/14951 [00:00<00:00, 554834.32it/s] 100%|███████████████████████████████████| 14951/14951 [00:02<00:00, 6126.98it/s] LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

| Name | Type | Params

0 | model | UnimoKGC | 237 M 1 | loss_fn | LabelSmoothSoftmaxCEV1 | 0

35.1 M Trainable params 202 M Non-trainable params 237 M Total params 950.540 Total estimated model params size (MB) Validation sanity check: 50%|██████████ | 1/2 [00:01<00:01, 1.37s/it]Traceback (most recent call last): File "main.py", line 152, in main() File "main.py", line 134, in main trainer.fit(lit_model, datamodule=data) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 499, in fit self.dispatch() File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 546, in dispatch self.accelerator.start_training(self) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 73, in start_training self.training_type_plugin.start_training(trainer) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 114, in start_training self._results = trainer.run_train() File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 607, in run_train self.run_sanity_check(self.lightning_module) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 864, in run_sanitycheck , eval_results = self.run_evaluation(max_batches=self.num_sanity_val_batches) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 713, in run_evaluation for batch_idx, batch in enumerate(dataloader): File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 630, in next data = self._next_data() File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1325, in _next_data return self._process_data(data) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data data.reraise() File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/_utils.py", line 694, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 1. Original Traceback (most recent call last): File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch return self.collate_fn(data) File "/media/kemove/16T/Jupyter/MKGformer/MKGformer/MKG/data/data_module.py", line 168, in call aux_img = aux_processor(images=aux_img, return_tensors='pt')['pixel_values'].squeeze() File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/models/clip/processing_clip.py", line 103, in call image_features = self.image_processor(images, return_tensors=return_tensors, kwargs) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/image_processing_utils.py", line 494, in call return self.preprocess(images, kwargs) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/models/clip/image_processing_clip.py", line 332, in preprocess images = [self.normalize(image=image, mean=image_mean, std=image_std) for image in images] File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/models/clip/image_processing_clip.py", line 332, in images = [self.normalize(image=image, mean=image_mean, std=image_std) for image in images] File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/models/clip/image_processing_clip.py", line 217, in normalize return normalize(image, mean=mean, std=std, data_format=data_format, **kwargs) File "/home/kemove/anaconda3/envs/MKG/lib/python3.8/site-packages/transformers/image_transforms.py", line 356, in normalize raise ValueError(f"mean must have {num_channels} elements if it is an iterable, got {len(mean)}") ValueError: mean must have 1 elements if it is an iterable, got 3

[njcx-ai]

Thank you very much for your interest in our project. We have not encountered the same problem before. In this case, we suggest you double-check whether there might be any errors in the parameter passing.

[zxlzr]

hi, have you solved your issue yet?

[Larry-Liu02]

hi, have you solved your issue yet?

Solved it due to the fb15k-237-image and wn18-images folders having some pure white and black images.

[zxlzr]

OK