推理报错

[MengTanOwn]

按照 readme的方式准备的环境，进行inference 报错： Traceback (most recent call last): File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 175, in convert_to_tensors tensor = as_tensor(value) File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 149, in as_tensor return torch.tensor(value) RuntimeError: Could not infer dtype of numpy.float32 During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/mnt/localdisk/tanm/nltk_data/backup_llm/Table-LLaVA/llava/eval/model_vqa.py", line 112, in eval_model(args) File "/mnt/localdisk/tanm/nltk_data/backup_llm/Table-LLaVA/llava/eval/model_vqa.py", line 59, in eval_model image_tensor = image_processor.preprocess(image, return_tensors='pt',padding=True)['pixel_values'][0] File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/site-packages/transformers/models/clip/image_processing_clip.py", line 337, in preprocess return BatchFeature(data=data, tensor_type=return_tensors) File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 78, in init self.convert_to_tensors(tensor_type=tensor_type) File "/mnt/localdisk/tanm/miniconda/envs/table_llava/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 181, in convert_to_tensors raise ValueError( ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

[SpursGoZmy]

可能是我上传的llava代码版本太新了，和老版本相比有改动，然后sh脚本对应的是老脚本，我后面修正一下，感谢同学发现的问题。