Closed minar09 closed 1 year ago
Hi Minar, Repo-head, Thanks for this great repo (to the repo-head). Any luck with the agnostic image creation? I intuitively think it is a human parser getting the mask and hand labels and masking it out with black, however, an easier opensource reference could really help. Thanks, Arun
Hi @arunsubk , I found a nice function here: https://github.com/NadaAdelMousa/Virtual-Try-on/blob/f8f5ff1adbc44b681563b208ec9510e4182368b7/datasets.py#L68
Thanks for your concern, the data process scripts are updated in https://github.com/OFA-Sys/DAFlow/tree/main/data/data_process
.
Thanks a lot @ShuaiBai623 for the data process scripts, and thanks again for the great work. Could you please also let me know if there are pre-processing code for MPV dataset, you mentioned in the paper? Regards, Arun
The pre-processing script for MPV is the same as VITION.
Hi, thank you very much for your nice repository and for providing the relevant models and data. Can you please share how did you make the agnostic image inputs so that I can test this model on custom images? Thank you.