When running the notebook, the MovingMNISTDataset dataloader will be called, and the way to create dictionary 'data' is based on the key of the input .npz file, however, the original dataset downloaded from http://www.cs.toronto.edu/~nitish/unsupervised_video/ seems not to have the key 'clips'. Is it possible for you to share your splitted dataset somehow? Thx!
When running the notebook, the MovingMNISTDataset dataloader will be called, and the way to create dictionary 'data' is based on the key of the input .npz file, however, the original dataset downloaded from http://www.cs.toronto.edu/~nitish/unsupervised_video/ seems not to have the key 'clips'. Is it possible for you to share your splitted dataset somehow? Thx!