ValueError: not enough values to unpack (expected 4, got 3)

I use this command: python .\train.py -c .\config.json but gives the following error. I did not change anything.

Using TensorFlow backend.
valid_annot_folder not exists. Spliting the trainining set.
Seen labels:    {}

Given labels:   ['raccoon']
Some labels have no annotations! Please revise the list of labels in the config.json.
Traceback (most recent call last):
  File ".\train.py", line 280, in <module>
    _main_(args)
  File ".\train.py", line 182, in _main_
    config['model']['labels']
ValueError: not enough values to unpack (expected 4, got 3)

I changed config.json with config_raccoon.json file by renaming it as config.json to use.

[smilexu1982]

delete your ‘.pkl’ file

[animikhaich]

I am able to successfully run using the same dataset,see the output I am getting below valid_annot_folder not exists. Splitting the training set. Seen labels: {‘raccoon’: 217} Given labels: [‘raccoon’] Training on: [‘raccoon’] You can run the code in a IDE like spyder adn debug to see what is causing issue I have created colab notebook which you can check. It runs fine only issue is I am getting memory error which is due to colab not allocating sufficient memory . It runs fine on Kaggle Kernal https://colab.research.google.com/drive/1ZxKLmeN-EzB2QCaORX3pBr5AvPuJ-YVd#scrollTo=idsJ6njALsGr

I am having the same problem but I can’t understand your solution can you explain it please?

Please refer to this: https://github.com/experiencor/keras-yolo3/issues/243#issuecomment-583768111