search

anilsathyan7 / Portrait-Segmentation

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

Regarding each model #18

Closed Nerdyvedi closed 4 years ago

Nerdyvedi commented 4 years ago

Hi, Thank you so much for uploading such a wonderful work.

I am getting a little confused as to which refers to which model?

I have the following questions

  1. Is the model described in train.py the same as bilinear_fin_munet.h5 ? How did you get the .tflite model from this? When I export the train.py model I am getting a different architecture.

  2. Which model does Model 1 , Model 2 and Model 3 refer to? Can you tell their corresponding saved models ?

Thank you

anilsathyan7 commented 4 years ago
  1. See the portrait_segmentation notebook for full code. There are two model variants in this case i.e conv block with resize bilinear and conv block with transpose convolutions.
  2. See the corresponding saved models in the models folders. You can check them by model specifications as described in the subsections. Model1 : transpose_seg Model2: mnv3_seg Model3: prisma_seg