search

gnina / models

Trained caffe models
82 stars 23 forks source link

What is your model architecture? #2

Closed xuzhang5788 closed 6 years ago

xuzhang5788 commented 6 years ago

In your paper, you said "five 3 × 3 × 3 convolutional layers with rectified linear activation units alternating with max pooling layers". Is it possible to show a picture of each layer's parameters?

Your model with the mashes 48x48x48 in 34 channels. It is a huge model. How big of your memory is? In total, how many parameters of your model? I am interested in your model details. Many thanks.

dkoes commented 6 years ago

I believe you are referring to the initial model that was optimized in the JCIM paper. Slide 22 of this presentation shows a diagram of it: http://bits.csb.pitt.edu/files/CNN_Scoring_ACS_March_2017.pd

f

xuzhang5788 commented 6 years ago

Thank you very much.

SanFran-Me commented 1 year ago

I believe you are referring to the initial model that was optimized in the JCIM paper. Slide 22 of this presentation shows a diagram of it: http://bits.csb.pitt.edu/files/CNN_Scoring_ACS_March_2017.pd

f

Hello, I also want to see the slide in this link but it is 404 Not Found now...

dkoes commented 1 year ago

You are missing the f in pdf.