h3lio5 / episodic-lifelong-learning Goto Github PK

Hi,
I am running this work and I found a couple of minor mistakes (that was taken care of) and a major issue with the sampling process. While sampling the dictionary data structure, what should be the output?

Line 93 of the main.py

content, attn_masks, labels = memory.sample(sample_size=64)

I sampled from the dictionary items and I am getting 4 tuples as output while expected output should be: content, attn_mask, label.
Let me know if my sampling procedure matches the desired one. I am neglecting the fourth tuple altogether.

Thanks!

Hi,

I am trying to run this model. While at the Training stage, I received the following error:
usage: main.py [-h] [--batch_size BATCH_SIZE] [--mode MODE] [--order ORDER] [--epochs EPOCHS] [--model_path MODEL_PATH] [--memory_path MEMORY_PATH] main.py: error: argument --epochs: invalid int value: 'any_number'

I am wondering if anyone has the same issue like this. Or, any thoughts?
Thank you!

Hi,

I am trying to run this model. While at the inference stage, I received the following AttributeError:

Traceback (most recent call last):
  File "main.py", line 273, in <module>
    model = MbPAplusplus(model_state=model_state)
  File "/home/sandstone/code/continual_learning/replay_baselines/episodic-lifelong-learning-master/models/MbPAplusplus.py", line 118, in __init__
    self.base_weights = self.classifier.parameters().clone().detach().to("cuda" if torch.cuda.is_available() else "cpu")
AttributeError: 'generator' object has no attribute 'clone'

I am wondering if anyone has the same issue like this. Or, any thoughts?

Thank you!