Closed rugrag closed 4 years ago
The labels are sorted with the filenames. You can find the details at the following code: https://github.com/clovaai/rebias/blob/fcd9cc754c7f3f6858256aad78f748e11f00bc42/datasets/imagenet.py#L121-L139
I agree with your idea; sharing the csv file seems a nice idea for many users. It will be uploaded in a week.
@rugrag I just added 9class_imagenet_val.csv to the main branch. https://github.com/clovaai/rebias/blob/master/clusters/9class_imagenet_val.csv
In [1]: import pandas as pd
In [2]: pd.read_csv('clusters/9class_imagenet_val.csv')
Out[2]:
path category cluster1 cluster2 cluster3
0 n01641577/ILSVRC2012_val_00001652.JPEG frog 1 5 3
1 n01641577/ILSVRC2012_val_00003748.JPEG frog 0 8 4
2 n01641577/ILSVRC2012_val_00004613.JPEG frog 6 8 0
3 n01641577/ILSVRC2012_val_00004945.JPEG frog 5 5 3
4 n01641577/ILSVRC2012_val_00005045.JPEG frog 5 5 3
... ... ... ... ... ...
2095 n02655020/ILSVRC2012_val_00043777.JPEG fish 7 6 7
2096 n02655020/ILSVRC2012_val_00044313.JPEG fish 1 8 0
2097 n02655020/ILSVRC2012_val_00044946.JPEG fish 7 4 7
2098 n02655020/ILSVRC2012_val_00045811.JPEG fish 5 5 5
2099 n02655020/ILSVRC2012_val_00049696.JPEG fish 7 4 5
[2100 rows x 5 columns]
If you have any other question, please don't hesitate to bother me.
Dear Authors, Thanks for sharing your code. I would like to reproduce the 9 class Imagenet clustering: I saw your .pth checkpoints but there is no reference to images and I am not sure whether I am considering the very same split as yours.
Could you please share a .csv file with filenames and associated cluster labels?
Thanks in advance