Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dataset #14

Open
tailororrr opened this issue Jul 27, 2021 · 13 comments
Open

dataset #14

tailororrr opened this issue Jul 27, 2021 · 13 comments

Comments

@tailororrr
Copy link

The link to download the dataset is not available now, is there any way to download it?

@bl0
Copy link
Owner

bl0 commented Jul 27, 2021

Hi, thanks a lot for your interest in our work.
There are copyright issues and we cannot reshare the dataset.
I suggest you follow the instruction on the official website to download the ImageNet dataset.

@JulieCarlon
Copy link

Dear authors, the checkpoints that you provide seem broken. Could you check them please? Thanks a lot!

@bl0
Copy link
Owner

bl0 commented Aug 24, 2021

Hi, I checked the onedrive link and it works normally.
image

@JulieCarlon
Copy link

Hi, I checked the onedrive link and it works normally.
image

I mean that when I download these .tar files, I cannot unzip them. I tried different ways to unzip them but I failed. So I think these files may be broken. I hope you can try to download and unzip them to see if they can be used.

@impiga
Copy link
Collaborator

impiga commented Aug 24, 2021

Hi, the shared checkpoints are NOT tar files, but pre-trained weights. Sorry for the misleading postfix.
We can load these pre-trained weights in this way:
image

@JulieCarlon
Copy link

Hi, the shared checkpoints are NOT tar files, but pre-trained weights. Sorry for the misleading postfix.
We can load these pre-trained weights in this way:
image

thank you so much!!

@gkgo
Copy link

gkgo commented Nov 30, 2021

Hello, thank you very much for sharing. I'm a beginner, and I encountered a problem when reproducing your code.
usage: few-shot script [-h] --config CONFIG [--supp SUPP]
few-shot script: error: the following arguments are required: --config
I checked it for a long time but didn't solve it. If you can see it, can you tell me what the problem is?

@impiga
Copy link
Collaborator

impiga commented Dec 1, 2021

HI, @gkgo . Thanks for your interest in this work.
Could you share the command you used with us to reproduce the error?

@gkgo
Copy link

gkgo commented Dec 1, 2021

I really appreciate your reply. The problem I encountered is:
屏幕截图 2021-12-01 182422

@impiga
Copy link
Collaborator

impiga commented Dec 1, 2021

I really appreciate your reply. The problem I encountered is: 屏幕截图 2021-12-01 182422

Do you use a command like this:

python main.py --config [CONFIGFILENAME] \
    --supp [SUPPLEMENTSTRING] \
    method.backbone [BACKBONE] \
    method.image_size [IMAGESIZE] \
    method.metric_params.margin [MARGIN] \
    [OPTIONARG]

@gkgo
Copy link

gkgo commented Dec 1, 2021

I used it in cmd under Windows, but there will be such an error:
屏幕截图 2021-12-01 183433

@impiga
Copy link
Collaborator

impiga commented Dec 1, 2021

We have not tested our code under Windows and you could have a try.

In addition, you need to replace "[CONFIGFILENAME]" "[SUPPLEMENTSTRING]" ... with specific values. This folder provides some examples.

As you are using Windows, you need to delete all "\" in the running command. For example, you can modify this script as

python main.py --config configs/miniImagenet/exp_neg-cosine.yml --supp 1-shot_resnet12 train.adam_params.weight_decay 1e-4 method.metric_params.margin -0.02 train.drop_rate 0.1 train.dropblock_size 5 method.backbone resnet12 method.image_size 84

@ContestantsD
Copy link

We have not tested our code under Windows and you could have a try.

In addition, you need to replace "[CONFIGFILENAME]" "[SUPPLEMENTSTRING]" ... with specific values. This folder provides some examples.

As you are using Windows, you need to delete all "" in the running command. For example, you can modify this script as

python main.py --config configs/miniImagenet/exp_neg-cosine.yml --supp 1-shot_resnet12 train.adam_params.weight_decay 1e-4 method.metric_params.margin -0.02 train.drop_rate 0.1 train.dropblock_size 5 method.backbone resnet12 method.image_size 84

Dear author, how can I use your checkpoints with the scripts ? your instructions is too concise to follow.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants