-
1) Currently ck-caffe repo has a set of packages for ImageNet LMDB
```
imagenet-2012-val-lmdb-224
imagenet-2012-val-lmdb-227
imagenet-2012-val-lmdb-256
```
and more can be added in future. All t…
-
If you change the data set, for example now the data set has 47 classes, what else to do but change nb_classes to 47 in main_finetune. Because only modify this final precision is not too high, I am no…
-
hello, after learning repp, I have questions that what is imagenet_vid_groundtruth_motion_iou.mat and how can I make it when I use my custom dataset.
-
### Version
1.40.0.dev20240628
### Describe the bug.
Hi,
I am testing the throughput of DALI (v1.40.0.dev20240628) when reading TFRecords via S3 and I am obtaining unexpectedly poor results.
…
-
Hi I am looking to train this tokenizer on a sign language dataset CSL-Daily so that I can compress video frames into 32 tokens.
However, I am not getting very good results (attached below). I would…
-
# Paper Information
- **Paper Title**: MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
- **Paper URL**: https://arxiv.org/pdf/2406.05927
- **Paper au…
-
hi @kaiyuyue
i see the [lines](https://github.com/kaiyuyue/nxtp/blob/main/src/encoding.py#L115-L119) in `encoding.py`, for what reason to miss these samples? for imagenet-1k dataset, many categories…
-
Hi, thanks for the interesting work.
I'm playing a bit with the code on a simple single-class dataset of 256x256 images, and I've modified basic things (imagenet hardcoded numbers, etc...).
I'm …
-
* Name of dataset: tiny-imagenet
* URL of dataset: http://cs231n.stanford.edu/tiny-imagenet-200.zip
* License of dataset: Not mentioned
* Short description of dataset and use case(s): Tiny ImageNet…
-
In Table 3 & 4, is the same dataset used during pre-training and fine-tuning? Or does the fine-tuning only happened on ImageNet-1k dataset?