search

soeaver / Parsing-R-CNN

Parsing R-CNN for Instance-Level Human Analysis
MIT License
298 stars 35 forks source link

Pretrained Resnext weights and demo #11

Open Naman-ntc opened 4 years ago

Naman-ntc commented 4 years ago

Hi @soeaver, Thank you for releasing the excellent codebase. I wanted to ask if you would be releasing weights for your state of art model with ResNext101 backend (for CIHP or MHP datasets). I am also willing to train the ResNext backend model, could you please share the corresponding yaml config file with the recommended hyperparameters for that model.

Secondly, I wanted to ask if you have a demo code available which could be run on a custom dataset. Thanks,

iamrishab commented 3 years ago

One thing you can do is to change the backbone in the yaml file and train the model from scratch. Also, you can copy some weights from the given pretrained imagenet checkpoint of ResNeXt-101.

BACKBONE:
  CONV_BODY: "resnext"
ignitemylife commented 3 years ago

@iamrishab Thank u for your reply! I wonder if it's convient for u to share the trained model using resnext101 as backbone for us to test and align ourselves' results. and @Naman-ntc have u trained and got the model？

abhigoku10 commented 2 years ago

@iamrishab can you share your weight file on the google drive , thansk in adavance