search

anilsathyan7 / Portrait-Segmentation

Real-time portrait segmentation for mobile devices
MIT License
643 stars 133 forks source link

Training dataset for the deconv_bnoptimized_munet.h5 model? #34

Closed SamSamhuns closed 3 years ago

SamSamhuns commented 3 years ago

Just want to premise by saying that this is excellent work @anilsathyan7 .

However, after reading the README, I am still a bit confused about what dataset was used for training the deconv_bnoptimized_munet.h5 model?

I am guessing it was the training data-set at https://drive.google.com/file/d/1UBLzvcqvt_fin9Y-48I_-lWQYfYpt_6J/view?usp=sharing that you have in the README.

But what datasets the img_uint8.npy and msk_uint8.npy files based on, is it the augmented PFCN or AI Segment or the PASCAL VOC Person?

Thanks!

anilsathyan7 commented 3 years ago

I think it was a custom dataset based on pfcn and supervisely.

SamSamhuns commented 3 years ago

Thanks for the reply, so the deconv_bnoptimized_munet.h5 model is trained on the pfcn and supervisely dataset?

anilsathyan7 commented 3 years ago

Yes, pfcn and selected supevisely images augmented with other backgrounds(composting)