Giter Club home page Giter Club logo

Comments (5)

YanDongchao avatar YanDongchao commented on September 10, 2024 1

Check issue #2. Might it be this is something that solves your problem?

Unable to solve it. After debugging for a long time, maybe your part of the code changed. Maybe could you please help upload the processed data "data.unpaired_clean.pkl" and "data.val_clean.pkl"

from gazenet.

m14k0s avatar m14k0s commented on September 10, 2024 1

Hi!

I had the same problem but was able to run it after debugging. I was able to run it with Python 3.5 with minor changes to make it compatible from Python 2.7. The problem that the script has is with the path of the dataset, the original one is in line 133 fdir_mat = 'EyeMovementDetectorEvaluation/annotated_data/images' but in the repository the path has changed to EyeMovementDetectorEvaluation/annotated_data/originally uploaded data/images you have to change that line. To make it work correctly I have followed the following steps, I hope this helps you.

git clone https://github.com/r-zemblys/gazeNet.git
cd gazeNet
mkdir etdata
cd etdata
git clone https://github.com/richardandersson/EyeMovementDetectorEvaluation.git
cd ../utils_lib/data_prep

Now you need to change in line 133 from fdir_mat = 'EyeMovementDetectorEvaluation/annotated_data/images' to fdir_mat = 'EyeMovementDetectorEvaluation/annotated_data/originally uploaded data/images'. If you run it in Python 3 you need to adapt the code.

Now you can run the script

 python tt_split.py --root=../../etdata

by changing the root path the script will store the files in the etdata folder and running it directly in the data_prep folder avoids the ETData module loading problem.

Finally, if you get an error in line 272 change it to

data_copy = data.copy()  
for part in data_copy.keys():

PS: If after an error you run the code again it is important that you remove the gazeNet_data and lund2013_npy folders from the etdata folder or the script will throw an error.

from gazenet.

YanDongchao avatar YanDongchao commented on September 10, 2024

Reading data
Train/test split
Number of trials: 20
Number of subjects: 4
Number of images: 4
Cleaning data
Traceback (most recent call last):
File "/gazeNet/utils_lib/data_prep/tt_split.py", line 210, in
_data = np.load(d['fpath'])
File "/anaconda3/envs/gazeNet/lib/python2.7/site-packages/numpy/lib/npyio.py", line 384, in load
fid = open(file, "rb")
IOError: [Errno 2] No such file or directory: '../../etdata/lund2013_npy/TH38_img_Europe_labelled_RA.npy'

from gazenet.

r-zemblys avatar r-zemblys commented on September 10, 2024

Check issue #2. Might it be this is something that solves your problem?

from gazenet.

NilZebra avatar NilZebra commented on September 10, 2024

Hi there!
I'm experiencing the exact same problem and I'm unfortunately unable to debug this myself. Could you maybe look into that or upload the processed data like YanDongchao suggested?
Many thanks!

from gazenet.

Related Issues (5)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.