Open Kunjal1999 opened 1 year ago
Can you please give the relevant versions of python, tensorflow and keras for loading the models? I am getting issues like:
ValueError Traceback (most recent call last)
[<ipython-input-57-ac2ef0a3374e>](https://localhost:8080/#) in <cell line: 70>()
158 # OldModel = load_model('/content/drive/MyDrive/tf/20200427_Phase4_FromScratch_Gender_IncepResN_lr01_AllIn.h5')
159 #OldModel = keras.models.load_model((path),custom_objects={'Model':hub.Model})
--> 160 ldModel = load_model('/content/drive/MyDrive/tf/20200427_Phase4_FromScratch_Gender_IncepResN_lr01_AllIn.h5')
161 print(OldModel)
162 layer_names = [layer.name for layer in OldModel.layers]
2 frames
[/usr/local/lib/python3.10/dist-packages/keras/saving/legacy/serialization.py](https://localhost:8080/#) in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
366 )
367 if cls is None:
--> 368 raise ValueError(
369 f"Unknown {printable_module_name}: '{class_name}'. "
370 "Please ensure you are using a `keras.utils.custom_object_scope` "
ValueError: Unknown layer: 'Model'. Please ensure you are using a `keras.utils.custom_object_scope` and that this object is included in the scope. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.
Please see https://github.com/Chaogan-Yan/BrainImageNet/blob/master/local/Dockerfile
tensorflow:1.13.1-py3-jupyter
Hello, Can you please provide the code for loading the pretrained models and training the loaded model on a custom dataset (i.e. transfer learning)?