spacetimeformer

spacetimeformer copied to clipboard

ValueError: SyncBatchNorm layers only work with GPU modules

2

Looks like the GPU in colab is not being engaged. Tried using A100, V100, T4 GPU, and TPU hardware settings in colab. command: `python train.py spacetimeformer mnist --embed_method spatio-temporal --local_self_attn...

LundinMachine

`configure_optimizers` must include a monitor when a `ReduceLROnPlateau` scheduler is used. For example: {"optimizer": optimizer, "lr_scheduler": scheduler, "monitor": "metric_to_track"}

2

when using “python ./spacetimeformer/train.py spacetimeformer mnist --embed_method spatio-temporal --local_self_attn full --local_cross_attn full --global_self_attn full --global_cross_attn full --run_name mnist_spatiotemporal --context_points 10 --gpus 0” it occurs this problem： ```python Traceback (most recent...

pdy265

MisconfigurationException: `configure_optimizers` must include a monitor when a `ReduceLROnPlateau` scheduler is used

5

(spacetimeformer) adewdev@bootedeagle:~/Devtools/PyWS0/spacetimeformer-main-original/spacetimeformer$ python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100 --d_ff 400 --enc_layers 5 --dec_layers 5 --l2_coeff 1e-3 --dropout_ff .2 --dropout_emb .1 --d_qk 20 --d_v 20 --n_heads 6...

adewdev

Unable to reproduce results for spacetimeformer

2

I am using the following command that is provided by this repo (only difference is the batch_size) python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100 --d_ff 400 --enc_layers...

TayyabaZainab0807

Huggingface Integration

1

Hi, is it possible to implement this transformer in huggingface's transformer lib as well? Is there a plan for it in the near future?

wangyifan

making modifications to train.py a model from stock data

BeastOrchestra

Upon using python train.py lstnet solar_energy --context_points 168 --target_points 24 --run_name spatiotemporal_al_solar --batch_size 25: test/loss 0.11 test/mae. 1.82 test/mape 19922692 test/mse 12.67 test/norm_mae 0.18 test/norm_mse. 0.11 test/smape. 1.417 question1: why...

TayyabaZainab0807

AttributeError: module 'tqdm' has no attribute 'auto'

9

When I run the following command ```bash python train.py linear ettm1 --context_points 288 --target_points 96 --run_name linear_ettm1_regression --gpus 0 --use_seasonal_decomp --linear_window 288 --data_path /path/to/ETTm1.csv ``` I get this error >...

PeterAyad

Memory requirements to replicate on Pems-Bay

2

Thanks to the authors for the great work and for sharing the code! I am interested in replicating the results on Pems-Bay before trying the model on a custom dataset...

steve3nto

Average of different prediction horizons as a metric?

3

Hello Authors, Could you please clarify the usage of the average of different prediction horizons as a benchmarking metric? Why was it used, and how to justify the validity of...

santoshatchi