DeepLabCutをGoogle colab上で動かす KeyErrorの解決法

Question

前提・実現したいこと

DeepLabCutというツールをGoogle colab上のGPUで動かそうと考えています。
以下のサイトを参考にGoogle colab上で順に実行していったのですが、deeplabcut.create_training_dataset(path_config_file)
を実行したところでエラーメッセージが発生してしまいました。

参考サイト：https://qiita.com/riichirohira/items/b92723278ba92fb42db9

発生している問題・エラーメッセージ

KeyError                             Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2897             try:
-> 2898                 return self._engine.get_loc(casted_key)
   2899             except KeyError as err:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'TS'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)


<ipython-input-7-b29a52be26d9> in <module>()
----> 1 deeplabcut.create_training_dataset(path_config_file)

/usr/local/lib/python3.7/dist-packages/deeplabcut/generate_training_dataset/trainingsetmanipulation.py in create_training_dataset(config, num_shuffles, Shuffles, windows2linux, userfeedback, trainIndices, testIndices, net_type, augmenter_type)
    765         if Data is None:
    766             return
--> 767         Data = Data[scorer]  # extract labeled data
    768 
    769         # loading & linking pretrained models

/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py in __getitem__(self, key)
   2903         if is_single_key:
   2904             if self.columns.nlevels > 1:
-> 2905                 return self._getitem_multilevel(key)
   2906             indexer = self.columns.get_loc(key)
   2907             if is_integer(indexer):

/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py in _getitem_multilevel(self, key)
   2953     def _getitem_multilevel(self, key):
   2954         # self.columns is a MultiIndex
-> 2955         loc = self.columns.get_loc(key)
   2956         if isinstance(loc, (slice, np.ndarray)):
   2957             new_columns = self.columns[loc]

/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/multi.py in get_loc(self, key, method)
   2702 
   2703         if not isinstance(key, tuple):
-> 2704             loc = self._get_level_indexer(key, level=0)
   2705             return _maybe_to_slice(loc)
   2706 

/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/multi.py in _get_level_indexer(self, key, level, indexer)
   2967         else:
   2968 
-> 2969             code = self._get_loc_single_level_index(level_index, key)
   2970 
   2971             if level > 0 or self.lexsort_depth == 0:

/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/multi.py in _get_loc_single_level_index(self, level_index, key)
   2635             return -1
   2636         else:
-> 2637             return level_index.get_loc(key)
   2638 
   2639     def get_loc(self, key, method=None):

/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2898                 return self._engine.get_loc(casted_key)
   2899             except KeyError as err:
-> 2900                 raise KeyError(key) from err
   2901 
   2902         if tolerance is not None:

KeyError: 'TS'

該当のソースコード

deeplabcut.create_training_dataset(path_config_file)

試したこと

configファイルの中を書き換えたり、ファイル名に含まれる「TS」を書き変え、一から実行しなおしてみました。

補足情報（FW/ツールのバージョンなど）

ここにより詳細な情報を記載してください。