CloserLookFewShot

CloserLookFewShot copied to clipboard

test.py _ classifier.weight

1

hello, very nice work~ I am running the demo with CUB data, however, in test stage, an error happend:(And I found that the code just updated a day ago~) Traceback...

BoostMom

Can't reach specified accuracy on CUB dataset ResNet10

8

Getting around 80.78 (85.17 in paper) % accuracy on 5 shot , ResNet10 baseline++ with augmentation on. **Command used to train** : ```python train.py --dataset CUB --model ResNet10 --method baseline++...

Puneet2000

Model Selection for Baseline and Baseline++ Training with Base Classes

1

Hi there, If I have the right understanding that for the baseline and baseline++ model trained with base classes, in the paper reported results the model used is the epoch399...

tao0420

Does the learning rate always stay the same (default 0.001 in the Adam optimizer)?

1

Does the learning rate always stay the same (default 0.001 in the Adam optimizer)? If not, could you tell me how you set in your experiments? Thanks!

eezywu

Did you use weight decay for ResNet backbone to get the results in your paper?

1

eezywu

can't reach the accuracy as report

17

I have train your code with loss_type = 'dist' & train_aug（baseline++）,but the 5 shot accuracy on mini-imagenet is only 56%,much lower than your report(66%)，could you give a resonable explaination?

KaleidoZhouYN

experiments over tiered ImageNet dataset

1

Hi, I wanted to know if you had run baseline/baseline++ over the tiered ImageNet dataset. If so, can you share the performance results over it also?

a7b23

pytorch version

4

Hi, It is a nice work. Now I am facing some problems when running your code. So I want to make sure that I use the same pytorch as you....

mileyan

RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 21 and 7 in dimension 1 at /opt/conda/conda-bld/pytorch_1549635019666/work/aten/src/TH/generic/THTensorMoreMath.cpp:1307

deppep

Why the batch_size is 16 in baseline and baseline++ ,Can I change the value to 128 or 256?

1

SongyiGao