CVPR19_Incremental_Learning

CVPR19_Incremental_Learning copied to clipboard

Thanks for sharing the code with the community. Using exact suggested parameters, running on CIFAR100, the top-1 accuracy doesn't exceed %37 while the paper is claiming at least %57 performance...

nlrahimi

RamMohan112

where is mimic score? In the paper Equation(5), author mentioned mimic score as an transformation of distillation loss. However I can't find it in the code.

1

talentCODE

Acctype = float]: block: [0,0,0], thread: [4,0,0] Assertion `t >= 0 && t < n_classes` failed.

2

bug information : Epoch: 0, LR: [0.1] Train set: 196, Train Loss: 3.4775 Acc: 9.5960 /opt/conda/conda-bld/pytorch_1556653215914/work/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int,...

yangzhaonan18

_, term_width = os.popen('stty size', 'r').read().split() ValueError: not enough values to unpack (expected 2, got 0)

yunshuo

Hi, I was able to successfully trained the model and want to test it on a separate test set. However, when I load the saved checkpoint, the output layer only...

igygi

Can you please share the 'list of the class directories' used for the ImageNet-100 experiment. Or the original sequence in ImageNet-1000 which was used for sampling and shuffling.

sud0301

Adaptive weight of the LC loss

4

Hello, I found the calculation of the adaptive weight of less-forget constraint different from the description in the paper. Did I misunderstand this part or miss some details? https://github.com/hshustc/CVPR19_Incremental_Learning/blob/e5a90aed7640f3b00e5b1a8dfb5376c1628bfe6a/cifar100-class-incremental/class_incremental_cosine_cifar100.py#L207

wonda

Where can we find the supplementary material? Thanks.

xialeiliu

Hello, I want to change the number of classes in first group. Use cifar100, let the number of classes in first group is 10, and then train the 90 classes...

raygoah