1996scarlet / laser-eye Goto Github PK

i don't have gpu, can run?
error:
File "/mxnet/symbol/symbol.py", line 1629, in simple_bind
raise RuntimeError(error_msg)
RuntimeError: simple_bind error. Arguments:
data: (1, 3, 64, 64)
[16:24:29] /tmp/build/80754af9/libmxnet_1564766659613/work/src/storage/storage.cc:119: Compile with USE_CUDA=1 to enable GPU usage

can you tell me the reason？？？？？

1. python gaze_laser.py "asset/flame.mp4"
2. Press the 's' key on the keyboard.

Could you provide the details of training the ConvNets for iris segmentation? I cannot find the any information about the training datasets in the paper. Thank you very much~

报错：softmax_label is not presented。
请问该如何解决？
万分感谢！

Hi,

1. are the theta and phi values in radian or degrees?
2. what are the conventions for positive and negative?
   [+] up
   [ -] down
   [+] right
   [ -] left ?

Hi,
a quick question - is your technique applicable for estimating the gaze direction of each eye(left and right gaze vector separately)?

My Tensorflow version is 1.14.
But I got error as follows.

Laser-Eye-master\service\iris_localization.py", line 63, in get_mesh
self.interpreter.set_tensor(self.input_details[0]["index"], image)

return _tensorflow_wrap_interpreter_wrapper.InterpreterWrapper_SetTensor(self, i, value)
ValueError: Cannot set tensor: Got tensor of type STRING but expected type FLOAT32 for input 0, name: input_1

What is the tensorflow version?

Thanks for your help.

@1996scarlet In the paper "Realtime and Accurate 3D Eye Gaze Capture
with DCNN-based Iris and Pupil Segmentation" you have mentioned a separate FC branch in IRIS segmentation model to classify the eye as close and open.
I am not able to find that branch in your shared model here https://github.com/1996scarlet/Laser-Eye/blob/master/weights/iris-symbol.json

Hey can we have a map of the index of iris pls ? ty

Hello @1996scarlet,
The demo looks really impressive!! and I am really curious to re-implement this work again
Could you share what data you used to train the iris and pupil segmentation?

I am using python 3.11 64 bit .While installing
pip install opencv-python
pip install tensorflow
and
pip install mxnet
the mxnet throw error "Could not build wheels for numpy, which is required to install pyproject.toml-based projects"
numpy version 1.24.3 is installed .

Which version of opencv-python for cv2 , tensorflow,mxnet is compatible for numpy 1.24.3? Or Should I downgrade numpy version?
Building wheel to numpy is take too much time.

I can't find the file video_gaze_test.py.
Where is MobileAlignmentorModel and CabAlignmentorModel?

Thanks in advance

any pytorch version?

python video_gaze_test.py提示

Laser-Eye-master/face_detector.py", line 235
return getattr(self, f'_{mode}_wrapper')(detach)
SyntaxError: invalid syntax

why???