AttributeError:模块“keras.utils”没有使用分段模型的属性“get\u file”

Question

我正在尝试使用分段模型，但无法修复此错误。我找过这个特殊的 一个，但找不到答案。我正在使用pycharm，此错误与此特定代码行相关联 主干='resnet34'

model1 = sm.Unet(BACKBONE, weights=None,
                 encoder_weights='imagenet',
                 classes=num_classes,
                 activation='softmax',
                 decoder_block_type = 'upsampling') 

这也是第83次。我在文档中搜索，显然tensorflow keras等的版本满足要求。我真的不知道该怎么做，因为我真的尝试了多种组合来安装和卸载所有东西，以便让这段代码正常工作。感谢大家的帮助和时间！下面是完整的错误，希望能对您有所帮助

    `Traceback (most recent call last):
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\main.py", line 83, in <module>
        model1 = sm.Unet('resnet34', weights=None,
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\segmentation_models\__init__.py", line 34, in wrapper
        return func(*args, **kwargs)
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\segmentation_models\models\unet.py", line 221, in Unet
        backbone = Backbones.get_backbone(
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\segmentation_models\backbones\backbones_factory.py", line 103, in get_backbone
        model = model_fn(*args, **kwargs)
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\classification_models\models_factory.py", line 78, in wrapper
        return func(*args, **new_kwargs)
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\classification_models\models\resnet.py", line 314, in ResNet34
        return ResNet(
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\classification_models\models\resnet.py", line 280, in ResNet
        load_model_weights(model, model_params.model_name,
      File "C:\Users\Giulia\PycharmProjects\multiclass_new\venv\lib\site- 
   packages\classification_models\weights.py", line 25, in load_model_weights
        weights_path = keras_utils.get_file(
    AttributeError: module 'keras.utils' has no attribute 'get_file'

Answer 1

您可以尝试：

import segmentation_models as sm

sm.set_framework('tf.keras')

sm.framework()

在谷歌colab上为我工作