Lorenzo Stella

Hi, what is the layout of `target` you're providing? With `DeepVAREstimator` and `target_dim=1` you should have something like ``` { "target": [[1.0, 2.0, 3.0, ...]], } ``` Note the double...

Setting `one_dim_target=False` in `ListDataset` solves it, but then another issue occurs: ``` ValueError: Deferred initialization failed because shape cannot be inferred. MXNetError: Error in operator deepvartrainingnetwork0_broadcast_minimum1: [11:15:20] ../src/operator/numpy/../tensor/elemwise_binary_broadcast_op.h:67: Check failed:...

@baniasbaabe an easier way to set up the data using `PandasDataset` ```python import pandas as pd from gluonts.dataset.pandas import PandasDataset df = pd.read_csv( "https://archive.ics.uci.edu/ml/machine-learning-databases/00374/energydata_complete.csv", index_col="date", parse_dates=True, ) train_time = "2016-05-10...

Reduced to the following ```python import pandas as pd import numpy as np from gluonts.mx.model.deepvar import DeepVAREstimator from gluonts.mx import Trainer TARGET_DIM = 1 training_data = [ { "start": pd.Period("2012-03-04",...

> Do you know what the problem exactly is? I can also look into it Not really, I couldn't look into it yet. My guess is there is some conditional...

@Nrebin does this ☝️ answer your question?

@gorold I believe the issue is that the layout of the forecast array should be different: `(num_stat, time, dimensions)` instead of `(num_stat, dimensions, time)` as you have it. This can...

> Perhaps an assertion can be made in the get_metrics_per_ts function that inputs are univariate. Thanks for the further inspection. I agree, that would be the fix here

> TFT seems to have a bug in version 0.11 Does the example work in 0.10?

As @esbraun pointed out, this is because TFT expects a different schema than what `PandasDataset` provides. Cc @jaheba this is something that fits in the whole schema story. Should we...