Code for PCA about sd-dino

[develop-productivity]

This is Code reference abrove in extractor_sd.py

[Junyi42]

Hi, thank you for your interest in our project. I'd be happy to clarify the code behavior:

The inference code is designed for a batch_size of 1 for simplicity, hence N is always 1, and tensor[0] is equivalent to tensor.squeeze(0). This doesn't discard any other samples since there is only one sample in the batch.

For PCA implementation, please note that the implementation of the PCA used in our default setting is actually the co_pca function in utils_correspondence.py. The pca_process function here is retained for completeness but may not be the one used in our default setting.

Feel free to ask if you have any more questions. Thank you!

[develop-productivity]

Hi, thank you for your interest in our project. I'd be happy to clarify the code behavior:

The inference code is designed for a batch_size of 1 for simplicity, hence N is always 1, and tensor[0] is equivalent to tensor.squeeze(0). This doesn't discard any other samples since there is only one sample in the batch.

For PCA implementation, please note that the implementation of the PCA used in our default setting is actually the co_pca function in utils_correspondence.py. The pca_process function here is retained for completeness but may not be the one used in our default setting.

Feel free to ask if you have any more questions. Thank you!

Thank you for your patient explanation, I will continue to study this work carefully.