Mert Kilickaya

Where is the Model Zoo

5

I wonder if anyone converted pre-trained Caffe (or any else) models like AlexNet, VGG, HYBRID to ConvNet.js format? If not, how could it be possible?

Hello! Thanks for the nice work. In my experiments solely using LogRatioLoss leads to much inferior results for pose recognition. When I combine it with binary triplet loss then I...

Big chunks of data

1

Hi! Thanks a lot for the very clear and understandable code and repository. One small comment I can add is maybe this repo can benefit from a warning that extracted...

Difficulty In Reproducing The Paper Results (e.g., Table 4., BYOL reported 66%, measured <<60%)

13

Hi, Thanks a lot for your amazing work and releasing the code. I am trying to reproduce your **[Table 4](https://arxiv.org/pdf/2112.04215.pdf)** for sometime. I directly use the code and the scripts...

Object Category IDs do not align neither with *2014 nor *2017

9

Hello As the dataset does not provide automatically the object class annotation but object class ID, I try to get the object class name from mscoco annotations, however object class...

I have a bunch of text files, where some of the lines are empty. Now I've seen that, when trying to extract skip-thought vectors, It shuts down without extracting features...

Hello! Many thanks for collecting this amazing resource. Is there any plan to support [detectron2](https://detectron2.readthedocs.io/en/latest/tutorials/datasets.html) framework for ease of evaluation?

How is the warping performed to generate the synthetic training set?

1

Hello! Thanks for your great work as well as the inference code. Two questions please: 1) What transformation(s) did you use to generate synthetic warping on MS-COCO images? 2) Will...