temporal_fusion_transformer_pytorch
temporal_fusion_transformer_pytorch copied to clipboard
dehoyosb
Hello, I meet this problem when I run training_tft.ipynb AttributeError: 'TemporalFusionTransformer' object has no attribute 'load_from_metrics' “”“ model = tft.load_from_metrics( weights_path='lightning_logs/version_18/checkpoints/epoch=6.ckpt', tags_csv='lightning_logs/version_18/meta_tags.csv', #on_gpu=True, map_location=None ) ”“” but i didn't find...
when I run: trainer = pl.Trainer(max_nb_epochs = tft.num_epochs, gpus = 1, track_grad_norm = 2, gradient_clip_val = tft.max_gradient_norm, early_stop_callback = early_stop_callback, #train_percent_check = 0.01, #val_percent_check = 0.01, #test_percent_check = 0.01, overfit_pct=0.01,...
In the class TFTDataset(Dataset, ElectricityFormatter): """Dataset Basic Structure for Temporal Fusion Transformer""" def __init__(self, data_df): super(ElectricityFormatter, self).__init__() """ Args: csv_file (string): Path to the csv file with annotations. """ #...
Hello, I meet this problem when I run training_tft.ipynb TypeError: ufunc 'isnan' not supported for the input types, and the inputs could not be safely coerced to any supported types...
While iterating over the test dataloader, getting an error when calling output for a batch: ``` --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in 5 t = target 6 batches...
Thank you for the great work. But when I debugging the example file, I find that the last 24 rows of target (power_usage) in data_input have the same value of...
Would it be possible to include a LICENSE file in this repository so that it is clear what usage of your code is permitted?
