search

ndrplz / dreyeve

[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.
https://arxiv.org/pdf/1705.03854.pdf
MIT License
99 stars 33 forks source link

Pre-trained coarse weights for segmentation branch? #14

Closed ryanwang522 closed 4 years ago

ryanwang522 commented 4 years ago

Hi,

I'm currently working on this project to reproduce the gaze prediction by the pre-trained model from this work (I just need inferencing).

And I just found that there are no pre-trained weights of the coarse part of the segmentation branch. That is, it seems that the weight file w_up2_conv4_new.h5 is only used in the image and optical flow branch.

https://github.com/ndrplz/dreyeve/blob/5ba32174dff8fdbb5644b1cc8ecd2752308c06ce/experiments/train/models.py#L123-L125

My question is, does the segmentation branch supposed to be no pre-trained coarse weight? (If not, where could I get the pre-trained coarse weights for segmentation branch?)

Thanks for your time!

ryanwang522 commented 4 years ago

Oops, sorry for the stupid question...

The following code will load whole pre-trained weights as it supposed to. https://github.com/ndrplz/dreyeve/blob/5ba32174dff8fdbb5644b1cc8ecd2752308c06ce/experiments/predict_on_cineca/predict_dreyeve_sequence.py#L116