Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improving content #14

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Improving content #14

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dea6866
Update README.md
12345407 Oct 1, 2020
ff69c43
Update README.md
12345407 Oct 1, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,15 @@ We soon plan to add other useful scripts, such as:
* Our useful modifications over Caffe - the image augmentation layer, and triplet accuracy layer to aid the training of Visnet

## Visnet Architecture
The visual development of hand-centered receptive fields in a neural network model of the primate visual system trained with experimentally recorded human gaze changes

VisNet is a Convolutional Neural Network (CNN) trained using triplet based deep ranking paradigm. It contains a deep CNN modelled after the VGG-16 network, coupled with parallel shallow convolution layers in order to capture both high-level and low-level image details simultaneously.
![img](https://drive.google.com/uc?export=view&id=0B4toQpysgMLVd09nNEJEVWc4VmM)





## Training
In order to train you need a set of triplets <q,p,n>. For compatibility with Caffe's ImageData layer, you need 3 sets of triplet files (one each for q, p and n). The lines in those files should correspond to triplets, i.e. line#i in each file should correspond to the i'th triplet.

Expand Down