Comments (11)
actually fix is easy:
face_image = feelings_faces[result[0].tolist().index(max(result[0]))]
.tolist()
is the fix ;-)
Now I have to figure out why it always think that I am happy...
from emotion-recognition-neural-networks.
:+1 I am curious, how do you know your webcam loads? I use a Macbook Pro and the camera light never turn on and I get the same error are yours.
from emotion-recognition-neural-networks.
@AlainPilon Your model is probably not loaded ~Or you are a real happy guy hehe
from emotion-recognition-neural-networks.
~Or you are a real happy guy
:-)
I did manage to make it output some other emotion but they had so be very contrived (as in I had to do some pretty bad acting to get them). I will do more tests this week.
from emotion-recognition-neural-networks.
yeah i managed to eventually find out the same fix with the tolist() feature.
I find the code run in such a way that the first emotion it sees is what it likes to stick with i have an alternative version of the code trained with a different CNN that give a faster changing response to emotions, though sometimes its get a bit silly jumping between two , even when you try your hardest to keep the same face.
from emotion-recognition-neural-networks.
@paulkirkland probably need to change to a LTSM to keep track of the last emotion to make it "stick". But that is out of my comfort zone for now ;-)
from emotion-recognition-neural-networks.
@paulkirkland Maybe without training a different network, you can take that output, as a noisy detection, and use mean shift, or kalman filtering to reduce the noise.
from emotion-recognition-neural-networks.
@paulkirkland sir can you kindly share your model and code that overcame this issue. It will be very helpful
from emotion-recognition-neural-networks.
Hi @paulkirkland, I have also gotten this problem long time. Could you please help me to solve this problem. How can I fix this point. Thank you very much.
from emotion-recognition-neural-networks.
data[np.argmax(labels[i]), result[0].index(max(result[0]))] += 1
AttributeError: 'numpy.ndarray' object has no attribute 'index'
Solution??
from emotion-recognition-neural-networks.
The baseline predictions are the historical averages
baseline_preds = test_features.index('averages')
AttributeError: 'numpy.ndarray' object has no attribute 'index'
whats is the solution?
from emotion-recognition-neural-networks.
Related Issues (20)
- Indentation error HOT 1
- License HOT 1
- plot_emotion_matrix.py 'PolyCollection' has no attributes 'get_axes()' HOT 5
- How to run it on juputer notebook? HOT 1
- why my predict always are angry HOT 3
- How to solve the problem about data_set_fer2013.npy etc. HOT 3
- cvs_to_numpy HOT 4
- Help - Dataset Access HOT 2
- No module named constants
- error while parsing dataset HOT 2
- Validating Model HOT 3
- why i can not use Nvidia GPU server for training? Can anybody tell me how to train it on GPU ? because on CPU its very slow. HOT 4
- Error when running cvs_to_numpy.py HOT 2
- emotion result varies between 2 iteration for the same image HOT 2
- ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[18432,3072] HOT 2
- ValueError: Cannot feed value of shape (48, 48, 1) for Tensor u'InputData/X:0', which has shape '(?, 48, 48, 1)'
- Change the readme part for cvs_to_numpy.py
- what do I need to change if need to work only on four emotions??
- Weights
- why the results i had predicted always are ‘fearful’? 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 emotion-recognition-neural-networks.