使用huggingface模型时报错LocalEntryNotFoundError

在使用huggingface上的模型facebook/detr-resnet-50时，报错：

但是我的代码是这么写的：

from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
from PIL import Image

image = Image.open("image/000000039769.jpg")

processor = DetrImageProcessor.from_pretrained("model_zoo/detr-resnet-50", local_files_only=True)
model = DetrForObjectDetection.from_pretrained("model_zoo/detr-resnet-50", local_files_only=True)

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
            f"Detected {model.config.id2label[label.item()]} with confidence "
            f"{round(score.item(), 3)} at location {box}"
    )

已经将模型下载到本地了，感觉没有用到什么网络，不应该会报这里的错误，仔细检查后，发现是这里：

也就是DETR会使用一个resnet50，在初始化resnet50的时候出现了问题，于是先到官网将对应的参数下载到本地。

然后调整这里的函数，

在其中额外添加参数pretrained_cfg_overlay即可。

backbone = create_model(
	config.backbone,
	pretrained=config.use_pretrained_backbone,
	features_only=True,
	out_indices=(1, 2, 3, 4),
	in_chans=config.num_channels,
    pretrained_cfg_overlay=dict(file='your_path/pytorch_model.bin'),
	**kwargs
)

finally，成功！