Comments (6)
@Ar4enal face_mask: 25 x 25 binary matrix.
from eye-tracker.
@hugochan 谢谢博主。
还有一个问题,就是在预测时feed_dict里传入参数的时候提示我还需要传入pos的数据,但是这是我要预测的坐标,请问怎么更改代码能得出预测的gaze坐标?或者我这个是错的?十分感谢(^▽^)
a = graph.get_tensor_by_name("eye_left:0")
b = graph.get_tensor_by_name("eye_right:0")
c = graph.get_tensor_by_name("face:0")
d = graph.get_tensor_by_name("face_mask:0")
e = graph.get_tensor_by_name("pos:0")
......
feed_dict = {a:left_eye, b:right_eye, c:face, d:face_grid}
res = sess.run(e,feed_dict)
from eye-tracker.
@Ar4enal
eye_left, eye_right, face, face_mask, pred = val_ops
pred_pos = session.run(pred, feed_dict={eye_left: batch_val_data[0], eye_right: batch_val_data[1], face: batch_val_data[2], face_mask: batch_val_data[3]})
from eye-tracker.
@hugochan 因为我预测的是一张图片jpg格式,而不是文中的val_ops,请问pred怎么初始化?其它四个参数我已经处理好了
#pred = graph.get_tensor_by_name("Add_5:0")
#pred = graph.get_tensor_by_name("Variable_13:0")
我试了这几个,但是结果都是有正有负的,类似如下
[array([ 0.14147238, -0.20125845], dtype=float32)]
怎么能得出预测的x,y坐标呢?多谢博主
from eye-tracker.
@Ar4enal 你可以参考这里,做一个反过程,把network output转化为实际坐标。
from eye-tracker.
@hugochan 好的,谢谢,我已经解决了
from eye-tracker.
Related Issues (20)
- Thanks for the wonderful code for eye tracking and detection,and I want to know how to prepare own dataset into the *.npz file, HOT 1
- 请教下数据集合中y的含义? HOT 3
- python code to extract face, left eye, right eye and face grid from multiple images HOT 1
- Prediction of itracker_nets HOT 1
- 关于标签y HOT 2
- What is train_y and val_y in dataset? HOT 6
- How i can train the dataset HOT 1
- What is the tensorflow version required for this Eye-Tracker HOT 3
- I have a question regarding input_data HOT 1
- Dropout in Eye-Tracker
- Link for smaller dataset
- enquiry of nature of smaller data set
- 如何使用gazecapture数据集进行训练 HOT 1
- about http://hugochan.net/download/eye_tracker_train_and_val.npz HOT 2
- Training on Custom Dataset HOT 4
- about the better prediction error HOT 4
- Hi,hugochan! Thanks for your excellent work, I am a green hand of DL, There for I am asking for your help, could you share your preproccessing codes with me?Because I want to process the original data to the format just like your smaller dataset is, but I have no idea with it. Thank in advance! HOT 1
- using the trained model HOT 23
- how to use? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from eye-tracker.