Seohyun Back

icon indicating a website link https://becxer.github.io icon indicating an email [email protected]

icon company Samsung Research & KAIST icon location Seoul, Korea icon location Most interested in deep-learning, especially for NLP. Research Engineer at Samsung Research AI Center. Concurrently, Ph.D. Candidate at KAIST.

Results 8 comments of Seohyun Back

Datasets

Hi, Im struggling with running the code. Do I have to convert manually from LMDB to "image/txt" files? Or could you provide the exact datasets (or link) in form of...

Datasets

Thank you!

Failed to reproduce the results in the paper when training from the scratch

Thanks for the response! I have an additional question about this. (1) When configuring batch, did you do random sampled without considering the ratio from the list of images from...

Python backend - fauxpilot-copilot_proxy failed to connect to all addresses

fastertransformer and py-model are not working here too

Python backend - fauxpilot-copilot_proxy failed to connect to all addresses

In my case, disabling the http proxy in the container resolves the problem!

Python backend - fauxpilot-copilot_proxy failed to connect to all addresses

In my case, due to the environment being restricted by proxy for security, I set an internal proxy for building Dockerfiles like > ENV http_proxy xxx.xx.xx.xx But I forgot to...

Random Selection while batch learning

Test response

Does synthdog data has MiT or afl-3.0 license?

https://huggingface.co/datasets/naver-clova-ix/synthdog-en/commit/b1efaecf0a2b002ac3c86ea33df7ffc250a17d24 Some pull request showing afl-3.0 license for the data. Is it correct?