KeyError: 'train' for a dataset which doesn't have train folder, how to split?

[vidyap-xgboost]

I've gone through tutorials for updating hyper parameters, especially this https://github.com/Tessellate-Imaging/monk_v1/blob/master/study_roadmaps/1_getting_started_roadmap/5_update_hyperparams/2_data_params/4)%20Play%20around%20with%20train-val%20splits.ipynb to split my dataset into train and validation. But I couldn't get anything like that so I took this Classifier to start training my classifier from scratch.

When I run the below code:

gtf.Default(dataset_path="/content/drive/My Drive/Data/zalando/zalando",
            model_name="resnet152_v2", 
            freeze_base_network=True,
            num_epochs=2)

I keep getting this error.

Dataset Details
    Train path:     /content/drive/My Drive/Data/zalando/zalando
    Val path:       None
    CSV train path: None
    CSV val path:   None
    Label Type:     single

Dataset Params
    Input Size:   224
    Batch Size:   4
    Data Shuffle: True
    Processors:   2
    Train-val split:   0.7

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-10-ca95f2c1dd79> in <module>()
      2             model_name="resnet152_v2",
      3             freeze_base_network=True,
----> 4             num_epochs=2)

9 frames
/content/monk_v1/monk/gluon/finetune/level_1_dataset_base.py in set_dataset_dataloader(self, test)
    116 
    117 
--> 118                 self.system_dict["dataset"]["params"]["num_train_images"] = len(image_datasets["train"]);
    119                 self.system_dict["dataset"]["params"]["num_val_images"] = len(image_datasets["val"]);
    120 

KeyError: 'train'

Where did I go wrong?

Environment: Google Colab

[vidyap-xgboost]

Surprisingly, this didn't happen when I first ran the code, it happened only when I factory reset the runtime, this started happening.

[EDIT]
When I ran the above code for the first time, I was in /content/mydrive/My Drive/Data/ folder, could that be the reason? If so, how do I resolve this by not changing into that directory?

[EDIT]
I changed to that folder and tried it again, its the same error. I am lost as to how this error suddenly occurred when it didn't occur the first time.

[UPDATE]
It's working again now after downloading the dataset again. I think it's probably the path or dataset problem.

[abhi-kumar]

Thank you for the detailed analysis on debugging the error