linux ubuntu tensorflow.keras加载模型报错（代码自动下载模型）：
代码：

from omegaconf import OmegaConf
cfg = OmegaConf.from_dotlist([f"model.model_name={model_name}", f"model.img_size={img_size}"])
from tensorflow.keras import applications
base_model = getattr(applications, cfg.model.model_name)(
        include_top=False,
        input_shape=(cfg.model.img_size, cfg.model.img_size, 3),
        pooling="avg")

报错：

Traceback (most recent call last):
  File "demo.py", line 137, in <module>
    main()
  File "demo.py", line 93, in main
    model = get_model(cfg)
  File "/home/user1/pjs/frvt/deb-age/open_models/age-gender-estimation/src/factory.py", line 11, in get_model
    pooling="avg"
  File "/home/user1/miniconda3/envs/py377/lib/python3.7/site-packages/tensorflow/python/keras/applications/efficientnet.py", line 618, in EfficientNetB3
    **kwargs)
  File "/home/user1/miniconda3/envs/py377/lib/python3.7/site-packages/tensorflow/python/keras/applications/efficientnet.py", line 406, in EfficientNet
    file_hash=file_hash)
  File "/home/user1/miniconda3/envs/py377/lib/python3.7/site-packages/tensorflow/python/keras/utils/data_utils.py", line 282, in get_file
    raise Exception(error_msg.format(origin, e.errno, e.reason))
Exception: URL fetch failure on https://storage.googleapis.com/keras-applications/efficientnetb3_notop.h5: None -- [Errno -2] Name or service not known

解决：手动下载这个模型（https://storage.googleapis.com/keras-applications/efficientnetb3_notop.h5），放到 ~/.keras/models/（也即/home/user1/.keras/models/）目录下即可。

https://blog.csdn.net/zkp_987/article/details/81590539