In the file model/backbone/resnet.py, there are only ResNet18 and ResNet34, but in model/der.py, ResNet50 is referenced. When I change the configuration to lucir.yaml in run_trainer.py and run it, an error occurs.

Hi there,

I'm new to the field of continual learning and have been exploring various toolkits to deepen my understanding. Recently, I came across your LibContinual repository and noticed many similarities with another toolkit I'm familiar with, PyCIL (https://github.com/G-U-N/PyCIL).

While going through both repositories, I couldn't help but notice that significant portions of the code in LibContinual appear to be very similar, if not identical, to those in PyCIL. Below are some examples with screenshots for reference:

(Left: PyCIL, Right: LibContinual)

https://github.com/G-U-N/PyCIL/blob/a9b1ec8e3dbbe143cb72b008d7c8f946629d55b1/utils/inc_net.py#L138

(Left: PyCIL, Right: LibContinual)

https://github.com/G-U-N/PyCIL/blob/a9b1ec8e3dbbe143cb72b008d7c8f946629d55b1/models/ewc.py#L210

(It seems the indentation is directly copied from PyCIL LOL)

(Left: PyCIL, Right: LibContinual)

It seems like renaming the functions into a similar one...

These similarities raise some important questions:

Is it necessary to reinvent the wheel by creating a new repository that largely replicates the functionality and code of PyCIL?
Shouldn't there be proper acknowledgment and attribution to PyCIL, considering the significant overlap in code? This includes but is not limited to:

1. Including PyCIL's original MIT License.
2. Including commit history from PyCIL.
3. Featuring the original authors of PyCIL in the License and Contributor sections.
4. Respect for the original authors and adherence to open-source principles are vital for the community. Proper attribution not only honors the work done by the PyCIL authors but also fosters a collaborative and respectful open-source environment.

Looking forward to your thoughts on this matter.

I noticed that u apply the code below to define a transformer on dataset Cifar-100, using STD = [0.2009, 0.1984, 0.2023].
However, as far as I know, the standard deviation for Cifar-100 is [0.2675, 0.2565, 0.2761].
Is it a mistake or on purpose? Please let me know. Thx, and nice work!!

MEAN = [0.5071,  0.4866,  0.4409]
STD = [0.2009,  0.1984,  0.2023]

common_trfs = [transforms.ToTensor(),
             transforms.Normalize(mean=MEAN, std=STD)]

resnet_train_transform = transforms.Compose([
  transforms.RandomCrop(32, padding=4),
  transforms.RandomHorizontalFlip(),
  transforms.ColorJitter(brightness=63 / 255),
  *common_trfs
])