RuntimeError: view size is not compatible with input tensor's size and stride

[lhduc94]

Thank you for your repo. When I run the script python 1_train_predictor.py --data nyc_taxi --filename nyc_taxi.pkl . It raises an Error

Traceback (most recent call last):
  File "1_train_predictor.py", line 320, in <module>
    train(args,model,train_dataset,epoch)
  File "1_train_predictor.py", line 228, in train
    loss1 = criterion(outSeq1.view(args.batch_size,-1), targetSeq.view(args.batch_size,-1))
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Could you please review it. Thank you

[chickenbestlover]

The script works in my environment: python 3.6 pytorch 1.4

(jmpark_py36) rit@rit:/media/rit/HDD/Engineering/RNN-Time-series-Anomaly-Detection$ python 1_train_predictor.py --data nyc_taxi --filename nyc_taxi.pkl

=> Start training from scratch
-----------------------------------------------------------------------------------------
Namespace(augment=True, batch_size=64, bptt=50, clip=10, data='nyc_taxi', device='cuda', dropout=0.2, emsize=32, epochs=400, eval_batch_size=64, filename='nyc_taxi.pkl', log_interval=10, lr=0.0002, model='LSTM', nhid=32, nlayers=2, prediction_window_size=10, pretrained=False, res_connection=False, resume=False, save_fig=False, save_interval=10, seed=1111, teacher_forcing_ratio=0.7, tied=False, weight_decay=0.0001)
-----------------------------------------------------------------------------------------
| epoch   1 |    10/   31 batches | ms/batch 52.9033 | loss  2.21 
| epoch   1 |    20/   31 batches | ms/batch 46.2340 | loss  2.01 
| epoch   1 |    30/   31 batches | ms/batch 46.1436 | loss  2.00 
-----------------------------------------------------------------------------------------
| end of epoch   1 | time:  1.84s | valid loss 1.9104 | 

Please specify your environment.

[lhduc94]

It worked, thank you.