Share it with your friends Like

Thanks! Share it with your friends!


This video contains stepwise implementation for training dataset of “Face Emotion Recognition or Facial Expression Recognition” using Transfer Learning in Tensorflow-Keras API

(00:00:00) concepts
(00:23:01) installation
(00:30:52) implementation
(1:15:08) Live Webcame demo



exam form says:

Can you provide me code for calculating and displaying accuracy of detection

AlexAMVs「運命」 says:

Hey there, great work! For some reason even though the code runs, in the live video it shows the rectangle around my face and it constantly writes happy while in the jupyter it writes "face not detected"…Maybe you can help me out :/

Gayatri Duwarah says:

Where to find weizmann dataset

Ryuk xDD says:

+rep man goodwork

George Danilenko says:

For some reason, when I come to the actual training part, my accuracy starts only at about 17 percent. And then after training for 150 epochs, I've only been able to get the accuracy up to about 32 percent. Any suggestions of what could possibly be going wrong?

Nidhi Prakash says:

can u tell me which algorithm have u used in this project for facial emotion recognition

mehmet hakan yuksekkaya says:

I always see the same output from neural network. How many input and hidden layer units do i have to use?

Merve Özdaş says:

thank you for your video,but I took an error in fit function. ValueError: Input 0 is incompatible with layer model_6: expected shape=(None, 224, 224, 3), found shape=(None, 50, 50, 1) I couldn't fix that

aameena mohammadi says:

Hello sir,
While training the model i.e., using the fit method it started running and gave a Resource exhausted error.
Plzzz help me out how to solve this error.


Can we have Github Link for This Code? There is not any Link in the Description.

Davide Raffo says:

Where we can find the code?

Davide Raffo says:

Very interesting!

sashinka kumarage says:

Sir, can you explain how to test the model using whole testing dataset?

Seun says:

Please did you use any algorithm to train the data

Robot Dream says:

Hi Nice explain. Can you share the code?

Seun says:

I am getting this error: warnings.warn('Custom mask layers require a config and must override ' when I try to save the model. Please help

Deepali Jain says:

Video is really helpful ,but i am getting this error ,somepne pls solve this out if possible


error Traceback (most recent call last)
<ipython-input-72-3393e2781669> in <module>
—-> 1 faces = faceCascade.detectMultiScale(gray,1.1,4)
2 for x,y,w,h in faces:
3 roi_gray = gray[y:y+h, x:x+w]
4 roi_color = frame[y:y+h, x:x+w]
5 cv2.rectangle(frame, (x, y), (x+w, y+h),(0,255,0),2) ##BGR

error: OpenCV(4.5.2) C:UsersrunneradminAppDataLocalTemppip-req-build-kuwfz3h3opencvmodulesobjdetectsrccascadedetect.cpp:1689: error: (-215:Assertion failed) !empty() in function 'cv::CascadeClassifier::detectMultiScale'


faces = faceCascade.detectMultiScale(gray,1.1,4)
for x,y,w,h in faces:
roi_gray = gray[y:y+h, x:x+w]
roi_color = frame[y:y+h, x:x+w]
cv2.rectangle(frame, (x, y), (x+w, y+h),(0,255,0),2) ##BGR
facess = faceCascade.detectMultiScale(roi_gray)
if len(facess) == 0:
print("face not detected")
for (ex,ey,ew,eh) in facess:
face_roi = roi_color[ey: ey+eh, ex:ex+ew]

Paras Chauhan says:

sir can I get a link for the code!!!

Reshu Agarwal says:

would have been easy if you could have shared the code.


thanks for your information but when run :


NameError: name 'face_roi' is not defined

could you help me sir…?

Jahongir Ibrohimov says:

Thank you so much , you must teaching programming!!!!!

Benya Jamiu says:

Good lecture

Hasnain Hawlader says:

please share dataset

Nayeem Haider says:

Please make a video of emotion recognition based on bio/physiological data

Rajat Paul says:

i guess you must make video on Human emotions recognition

Write a comment


DARPA SUPERHIT 2021 Play Now!Close


(StoneBridge Mix)

Play Now!