Need to load full model in order to do transfer learning.

[arianaa30]

Nice work. I was trying to simply run python main.py with the video path, but got this error:

video-summarization-develop\src\net\netarch.py", line 104, in _load_yolo_model raise ValueError('Need to load full model in order to do ' ValueError: Need to load full model in order to do transfer learning. Run script again with desired TL config and weight file to generate model.

Is there anything missing?

[oshadaamila]

Thank you for the interest in our work, You need to add a pre-trained YOLO model to the source folder in order to make the code run. A compatible model trained on coco dataset can be found here.

Add it to the source folder and then change the 120th line in the src/net/netparams.py as below
replace IN_MODEL = "coco_model.h5" with IN_MODEL = "file name of your model with extension"

[arianaa30]

Thanks for the hint. Now it goes further, but this error. Looks like there is a problem with the way you load models in Keras. Are you sure it works?!

Folder Creating Process Started
Process Finished Successfully
Traceback (most recent call last):
  File "main.py", line 98, in <module>
    run()
  File "main.py", line 46, in run
    location_to_store_shot_frames
  File "C:\Users\user\Downloads\video-summarization-develop\src\objects_identifier_of_frames.py", line 20, in generate_object_list_of_frames
    return YOLO().predict(input_frames_path)
  File "C:\Users\user\Downloads\video-summarization-develop\src\yolo\model.py", line 17, in __init__
    self.model = self.yolo_arch.get_model()
  File "C:\Users\user\Downloads\video-summarization-develop\src\net\netarch.py", line 76, in get_model
    yolo_model = self._load_yolo_model()
  File "C:\Users\user\Downloads\video-summarization-develop\src\net\netarch.py", line 100, in _load_yolo_model
    model = load_model(self.in_model_name, compile=False)
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\lib\site-packages\keras\engine\saving.py", line 419, in load_model
    model = _deserialize_model(f, custom_objects, compile)
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\lib\site-packages\keras\engine\saving.py", line 221, in _deserialize_model
    model_config = f['model_config']
  File "C:\Users\user\AppData\Local\Continuum\anaconda3\lib\site-packages\keras\utils\io_utils.py", line 302, in __getitem__
    raise ValueError('Cannot create group in read only mode.')
ValueError: Cannot create group in read only mode.