umitkaanusta
commented
1 year ago +1, Got the exact same error for NHITS and NBEATS.
I'll try to pretrain from scratch using this colab now: https://colab.research.google.com/github/Nixtla/neuralforecast/blob/main/nbs/examples/Transfer_Learning.ipynb#scrollTo=wrdt0JNdMsop
Update: FYI pretraining with the models in the notebook above ends up with sMAPE around ~70 on the AirPassengers dataset. The models they uploaded to HF had much better zero-shot performance
The notebook associated with this repository uses the model 'MQNHITS', which is nowhere to be found. The pretrained models may be based on vanilla NHITS and NBEATS but that isn't working. I don't know what 'h' and 'input_size' was used to train the models. Still, I tried with h=24 with was mentioned somewhere in the notebook, which resulted in another error.
model = NHITS.load_from_checkpoint(checkpoint_path='C://Users//raghu//Downloads//nhits_m4_hourly.ckpt',h=24,input_size=24*3)
AssertionError: max is not in ['MaxPool1d', 'AvgPool1d']
If I try to pass 'MaxPool1d' in another argument for pooling then too, there is an error
RuntimeError: Error(s) in loading state_dict for NBEATS: Missing key(s) in state_dict: "blocks.0.layers.0.weight", "blocks.0.layers.0.bias", "blocks.0.layers.1.weight", "blocks.0.layers.1.bias",
And so on Same kinda error with NBEATS as well.
So, just let me know if this project is updated and working