Mahalanobis distance calculation matrix is not working and throwing these errors

[harshnandwana]

python src/demo.py --img_path 1000_F_26800115_YlmErNLIVZeNZXPzUc3z4GAD1gGkVABu.jpg --cfg /app/mmpretrain/work_dirs/beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_beit-base-p16_8xb256-amp-coslr-300e_in1k.py --checkpoint pretrain/epoch_19.pth --fc outputs/fc.pkl --id_train_feature outputs/imagenet_train.pkl --id_val_feature outputs/imagenet_train.pkl --methods Mahalanobis
=> Loading model
/root/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1639180588308/work/aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Loads checkpoint by local backend from path: pretrain/epoch_19.pth
=> Loading image
=> Extracting feature
Extracted Feature: (1, 768)
w.shape=(8192, 768), b.shape=(8192,)
image path: 1000_F_26800115_YlmErNLIVZeNZXPzUc3z4GAD1gGkVABu.jpg
=> Loading features
feature_id_train.shape=(91710, 768), feature_id_val.shape=(91710, 768)
=> Computing logits...
=> Computing softmax...
Computing classwise mean feature: 0%| | 0/1000 [00:00<?, ?it/s]
Traceback (most recent call last):
File "src/demo.py", line 305, in
main()
File "src/demo.py", line 263, in main
fs = feature_id_train[train_labels == i]
IndexError: boolean index did not match indexed array along dimension 0; dimension is 91710 but corresponding boolean dimension is 200000

[JulietLJY]

This is due to a mismatch in shapes between your image_train.pkl and the Image_list. This may be because your ImageNet dataset is incomplete, resulting in a dimension of 91710 instead of 200k. To use Mahalanobis, you can choose to:

1. Use our preprocessed image_train.pkl, which matches our provided datalists/imagenet2012_train_random_200k.txt.
2. Use your custom Image_list, which needs to match the Image_train.pkl you are using.