Error while loading model

[jmsweng]

Attempting to load a model using the --load_model_num parameter added to the first usage example

python train.py --gpu 0 --data cylinder --num_sensors 8 --training_frames 50 --cons False --seed 123 --enc_preproc 16 --dec_num_latent_channels 16 --enc_num_latent_channels 16 --num_latents 256 --dec_preproc_ch 16 --test False

returns the following error:

Traceback (most recent call last):
  File "C:\Users\jmswe\Documents\Senseiver-main\train.py", line 79, in <module>
    main()
  File "C:\Users\jmswe\Documents\Senseiver-main\train.py", line 36, in main
    model = model.load_from_checkpoint(model_loc,
  File "C:\Users\jmswe\mambaforge\lib\site-packages\pytorch_lightning\utilities\model_helpers.py", line 121, in wrapper
    raise TypeError(
TypeError: The classmethod `Senseiver.load_from_checkpoint` cannot be called on an instance. Please call it on the class type and make sure the return value is used.

Changing line 36 in train.py from

model = model.load_from_checkpoint(model_loc, **encoder_config, **decoder_config, **data_config)

to

model = Senseiver.load_from_checkpoint(model_loc, **encoder_config, **decoder_config, **data_config)

appears to fix the problem.