gmvandeven / brain-inspired-replay Goto Github PK

It seems that using this option makes x_the same as x in train_a_batch. Why should we replay the current data?

Hi, I want to ask about the pre-trained models. The paper says you pre-train on cifar10, but the default pre-trained model, in the store/models/ file, C3-5×16-bn, seems a model of pre-training on cifar100. I have run main_pretrain.py on cifar10 to change the pre-trained model and it worked worse than the default. Did you use pre-trained model of cifar100 rather than cifar10 on paper's experiments?

Hi,
When I ran compare_permMNIST100_bir.py, and set --seed=12 --n-seeds=5.
Then an error occureed,

File "/media/wuya/DATA/Code/continual_learning/brain-inspired-replay/options.py", line 350, in set_defaults
args.xdg_prop = 0. if args.scenario=="task" and args.xdg_prop is None else args.xdg_prop
AttributeError: 'Namespace' object has no attribute 'xdg_prop'

I don't know where to set xdg_prop, can you tell me how to do it?
Thank you very much!

Hi, I am learning on your codes for a week and I have run several experiments so far. I have some questions.

1. The setting of 'scenario='task'' works well, but the other one of 'scenario=class' is what I am confused with :
   For example, if I set a setting: 'expri..=splitMNIST, tasks=5, scenario=class ' , the result is "-task1: xx. xx -task2: xx. xx task3: xx. xx -task4: xx. xx -task5: xx. xx". I don't understand what it means as the result format is the same with 'scenario=task'. Does the classifier uses single-head or multi-head for class-IL ?

2. In my experiments, EWC, SI, LwF had no effect on class-IL , all forgot. Is it normal?

Best regard

Hi, I refer to Fig 4 of the main paper, where it states "As a control, also shown is a variant of generative replay whereby the networks are reinitialized before each new task/episode". By reinitialization, does this mean that if we have that model after trained on task1, if we have to train on the next task, then we create a "brand new" model with the exact same architecture and retrain? If it is, then how different will it be from retraining from the current model? Is it likely that there will be no difference in performance with and without reinitialization for other cases because I tried on other types of dataset and the 2 curves kind of overlap rather than show one is better than the other?

Hi GMvandeVen, the model will be saved after run
./main_cl.py --experiment=splitMNIST --scenario=class --replay=generative --brain-inspired --pdf

is there any command to load trained model and use the model to predict?

Hi is it possible to allow an option for users to input their own dataset into the model rather than the default CIFAR10 and MNIST? If not, is there a minimal way that we can modify the scripts to accommodate our own datasets, especially inputs that are not image based , eg 1D arrays? Thanks!!!

Hello,

Sorry to bug you, but I think I am unable to reproduce the results.

Check out my notebook,
https://colab.research.google.com/drive/1g55JOiJnFRsTB7kjqkJO9YykTy1JDHhm?usp=sharing

I am trying to reproduce results on Class-IL for EWC and LWF for 10 tasks. I saw in your article that for 10 classes LWF and EWC get higher accuracy than I am able to achieve. Am I doing something wrong?

Great work though!

When I run the experiments, it displays as follows:

| Task: 3/5 | training loss: 0.407 | training precision: 0.992 |: 100%|███████████████████████████████████| 2000/2000 [08:37<00:00, 3.87it/s]

On-the-fly visdom plots also show precision as y-axis but the title of the plot is average accuracy.

Can you please clarify on that? I have seen same confusion in the code of your other repo: https://github.com/GMvandeVen/continual-learning

Perhaps related to 9afa20f, I get:

./compare_MNIST_hyperParams.py --scenario=task --seed=11                 #--> Fig. S1 (top)
Traceback (most recent call last):
  File "./compare_MNIST_hyperParams.py", line 62, in <module>
    args = handle_inputs()
  File "./compare_MNIST_hyperParams.py", line 37, in handle_inputs
    options.set_defaults(args, **kwargs)
  File "/home/fcyb/projects/brain-inspired-replay/options.py", line 350, in set_defaults
    args.xdg_prop = 0. if args.scenario=="task" and args.xdg_prop is None else args.xdg_prop
AttributeError: 'Namespace' object has no attribute 'xdg_prop'

Seems in hyper compare mode, xdg_prop is never defined?

Hi, I am really amazed by the number of options that are being provided in the code to run the experiments. I was wondering how to run the baselines, that is, Joint Training and None [simple sequential learning], as mentioned in the article. What is the code and the parameters to run these baseline algorithms seperately, like we can run algorithms like GR, LWF, etc?