ImageNet16-120 dataset prep

Question

ImageNet16-120 dataset prep

abduallahmohamed opened this issue 4 years ago · comments

Hi,

I'm running . /scripts-search/NAS-Bench-201/train-a-net.sh to train a found cell.
And I do have $TORCH_HOME/ILSVRC2012 data ready.
I also ran this prep script ./scripts/prepare.sh
But I do encountered the following error:

Any resolution?

Best

Abduallah Mohamed commented 4 years ago

Thanks!!!

Xuanyi Dong · Answer 1 · Thu Jun 04 2020 03:37:31 GMT+0800 (China Standard Time)

ImageNet16-12 is not ILSVRC2012, while it is a subset of resized version of ImageNet.
My apologies. I should emphasize it in the README: https://github.com/D-X-Y/AutoDL-Projects/blob/master/docs/NAS-Bench-201.md#preparation-and-download . Please see the last sentence of "Preparation and Download", I share the data of ImageNet16-12 on Google Drive, and if you download and put it ImageNet16 into $TORCH_HOME/cifar.python. You should be able to run

Md Hafizur Rahman · Answer 2 · Mon Jan 15 2024 02:16:58 GMT+0800 (China Standard Time)

ImageNet16-12 is not ILSVRC2012, while it is a subset of resized version of ImageNet. My apologies. I should emphasize it in the README: https://github.com/D-X-Y/AutoDL-Projects/blob/master/docs/NAS-Bench-201.md#preparation-and-download . Please see the last sentence of "Preparation and Download", I share the data of ImageNet16-12 on Google Drive, and if you download and put it ImageNet16 into $TORCH_HOME/cifar.python. You should be able to run

I can't find imagenet16-120 dataset in your repo. Could you please help me to find out the dataset?

Xuanyi Dong · Answer 3 · Mon Jan 15 2024 14:34:10 GMT+0800 (China Standard Time)

Can you access this link: https://drive.google.com/drive/folders/1T3UIyZXUhMmIuJLOBMIYKAsJknAtrrO4 and download ImageNet16?

Md Hafizur Rahman · Answer 4 · Mon Jan 15 2024 15:02:20 GMT+0800 (China Standard Time)

Thank you so much for your prompt response. Could you please guide me on how I can read the dataset? Best, Hafizur

…

On Mon, Jan 15, 2024 at 1:34 AM D-X-Y ***@***.***> wrote: Can you access this link: https://drive.google.com/drive/folders/1T3UIyZXUhMmIuJLOBMIYKAsJknAtrrO4 and download ImageNet16? — Reply to this email directly, view it on GitHub <#77 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AU6ONRYZLRIZXWE5LTAIFQDYOTEWZAVCNFSM4NRJ6WHKU5DIOJSWCZC7NNSXTN2JONZXKZKDN5WW2ZLOOQ5TCOBZGEZTQOBSGAYA> . You are receiving this because you commented.Message ID: ***@***.***>

Xuanyi Dong · Answer 5 · Mon Jan 15 2024 15:16:22 GMT+0800 (China Standard Time)

You can have a look at this function: https://github.com/D-X-Y/AutoDL-Projects/blob/main/xautodl/datasets/get_dataset_with_transform.py#L99-L130

call get_datasets("ImageNet16-120", path_to_the_data, -1), and you will get the dataset object

Md Hafizur Rahman · Answer 6 · Mon Jan 15 2024 15:22:48 GMT+0800 (China Standard Time)

Thank you so much.

…

On Mon, Jan 15, 2024 at 2:16 AM D-X-Y ***@***.***> wrote: You can have a look at this function: https://github.com/D-X-Y/AutoDL-Projects/blob/main/xautodl/datasets/get_dataset_with_transform.py#L99-L130 call get_datasets("ImageNet16-120", path_to_the_data, -1), and you will get the dataset object — Reply to this email directly, view it on GitHub <#77 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AU6ONR46CFECD46GQBHOW3DYOTJVDAVCNFSM4NRJ6WHKU5DIOJSWCZC7NNSXTN2JONZXKZKDN5WW2ZLOOQ5TCOBZGE2DINZWGI2Q> . You are receiving this because you commented.Message ID: ***@***.***>