Unable to save models (--save-models: save trained models)

[andreadaou]

Hello @mmasana ,

I appreciate your amazing and extremely helpful work.

Is it possible to save the trained models after incremental learning? The code is not working when putting save_models as True. Appreciate your help!

!python3 -u src/main_incremental.py --approach bic --num-exemplars 2000 --save-models True

============================================================================================================
Arguments =
	approach: bic
	batch_size: 64
	clipping: 10000
	datasets: ['cifar100']
	eval_on_train: False
	exp_name: None
	fix_bn: False
	gpu: 0
	gridsearch_tasks: -1
	keep_existing_head: False
	last_layer_analysis: False
	log: ['disk']
	lr: 0.1
	lr_factor: 3
	lr_min: 0.0001
	lr_patience: 5
	momentum: 0.0
	multi_softmax: False
	nc_first_task: None
	nepochs: 200
	network: resnet32
	no_cudnn_deterministic: False
	num_tasks: 4
	num_workers: 4
	pin_memory: False
	pretrained: False
	results_path: ../results
	save_models: True
	seed: 0
	stop_at_task: 0
	use_valid_only: False
	warmup_lr_factor: 1.0
	warmup_nepochs: 0
	weight_decay: 0.0
============================================================================================================
Approach arguments =
	T: 2
	lamb: -1
	num_bias_epochs: 200
	val_exemplar_percentage: 0.1
============================================================================================================
Exemplars dataset arguments =
	exemplar_selection: random
	num_exemplars: 2000
	num_exemplars_per_class: 0
============================================================================================================
Traceback (most recent call last):
  File "src/main_incremental.py", line 316, in <module>
    main()
  File "src/main_incremental.py", line 178, in main
    assert len(extra_args) == 0, "Unused args: {}".format(' '.join(extra_args))
AssertionError: Unused args: True

[mmasana]

Hi @andreadaou ,

happy to hear that you enjoy our work! The argument --save-models does not require of the True afterwards. I believe that's why you get the error, and if you run the command as !python3 -u src/main_incremental.py --approach bic --num-exemplars 2000 --save-models , it should work fine.

[andreadaou]

Oh okay! Thank you!!!

Hi @andreadaou ,

happy to hear that you enjoy our work! The argument --save-models does not require of the True afterwards. I believe that's why you get the error, and if you run the command as !python3 -u src/main_incremental.py --approach bic --num-exemplars 2000 --save-models , it should work fine.