Xingyi Yang
Xingyi Yang
not know your specific application. But default should somehow be `5e-5 * bs_size`
Thanks again for this nice paper
`import h5py import numpy as np hf = h5py.File('./3dshapes.h5', 'r') print(hf) values_to_save = {"images": hf['images'].reshape([10,10,10,8,4,15,64,64,3]), "labels": hf['labels']} np.savez('look-at-object-room_floor-hueXwall-hueXobj-hueXobj-sizeXobj-shapeXview-azi.nzp', **values_to_save) `
Dear @ycliu93 , Thank you so much for your interest in our work. I will address each of your question below: 1. I just comment out the `mmcv` version requirement...
Dear @AmirEstiri ， You error seems to be a mmcv error, rather than an error of this repo. Please visit the mmcv documents (https://mmcv.readthedocs.io/en/latest/) for how to install it. Besides,...
Dear @JackqqWang, Thank you for your interest. The `get_rep.py` script typically processes the configs for pre-trained models, computes the feature embeddings, and saves them as a `.pth` file. You can...
Dear @Aris-z, Thank you so much for expressing interest in our work. It seems that you are encountering an ImageNet version issue. In older versions of ImageNet, data split files...
Dear @xuelexuebuhui I believe that is the problem associate with `mmcls` data loader. Please see you imagenet dataset folder and make sure the subfolder of `data/imagenet/val` is indeed there. Best
Dear @xuelexuebuhui , We mainly use imagenet to extract feature and comparing models. You need to download it yourself. There are a lot of guideline/tutorial for downloading this very well-known...
Any updates？