everytime i try to start training, save a new name, it keeps saving, always "saving label" and when i checked the console, it said the websocket is already in closing. how do i fix it? thank you.

I am not sure if this is an issue with my install or not but my server is unable to access ws://localhost:8888/predict. It looks like there is no socket server listening. Do you know what I may have missed or how to fix this? From what I have read it looks like Tornado is handling the sockets.

From Google Chrome's error console

WebSocket connection to 'ws://localhost:8888/predict' failed: Connection closed before receiving a handshake response 

I am also seeing this in the console

WebSocket is already in CLOSING or CLOSED state. 

OpenCV Error: Assertion failed (ssize.area() > 0) in resize, file /usr/local/opencv/modules/imgproc/src/imgwarp.cpp, line 1824
Traceback (most recent call last):
File "server.py", line 121, in
main()
File "server.py", line 114, in main
opencv.train()
File "/home/petaoctet/Desktop/facerec/opencv.py", line 86, in train
images, labels = load_images_from_db()
File "/home/petaoctet/Desktop/facerec/opencv.py", line 78, in load_images_from_db
cv_image = cv2.resize(cv_image, (100,100))
cv2.error: /usr/local/opencv/modules/imgproc/src/imgwarp.cpp:1824: error: (-215) ssize.area() > 0 in function resize

after model trained
then i open http://localhost:8888/
but only display title, nothing else
is it any problem??

I have a small issue with setting up the system. I think the database is the issue. I don't seem to be getting anything on the DB. I'm constantly getting an error saying "sqlite3.OperationalError: no such table: label"

Please help me.

When i set up the system and then load localhost:8888 on the broser, the page opens and it notifies me saying it doesn't recognize me. So i enter my name and click ok. I get a few exceptions caught in the terminal.

The error is in the line gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) //opencv.py", line 23.
The directory is created but there is no images in the directory in the images folder.

Please look into this matter

In the function called load_images_to_db(path): I receive an error message as follow above:

in load_images_to_db  label.save()
AttributeError: 'tuple' object has no attribute 'save'

Can anyone help me?

[E 140101 23:45:19 websocket:306] Uncaught exception in /harvesting
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/tornado/websocket.py", line 303, in wrapper
return callback(_args, *_kwargs)
File "server.py", line 55, in on_message
self.process(image)
File "server.py", line 94, in process
result = opencv.Image(label=label).persist(cv_image)
File "/root/School/Face/face-recognition-server-master/opencv.py", line 159, in persist
cropped = to_grayscale(crop_faces(cv_image, faces))
File "/root/School/Face/face-recognition-server-master/opencv.py", line 41, in crop_faces
return img[y:y+h,x:x+w]
File "/usr/local/lib/python2.7/dist-packages/PIL/Image.py", line 512, in getattr
raise AttributeError(name)
AttributeError: getitem

When I ran the program, it showed me all the info including 'saving paths..' then I encountered this error,

 OpenCV Error: Bad argument (Empty training data was given. You'll need more than one sample to learn a model.) in train, file /io/opencv_contrib/modules/face/src/fisher_faces.cpp, line 71
Traceback (most recent call last):
  File "server.py", line 121, in <module>
    main()
  File "server.py", line 114, in main
    opencv.train()
  File "/home/sashank/face-recognition-server/opencv.py", line 89, in train
    model.train(images,labels)
cv2.error: /io/opencv_contrib/modules/face/src/fisher_faces.cpp:71: error: (-5) Empty training data was given. You'll need more than one sample to learn a model. in function train

Turns out, the images and labels lists are empty.
Checked the 'load_images_from_db()' function and I figured that this code, doesn't even run -

try:
        cv_image = cv2.imread(image.path, cv2.IMREAD_GRAYSCALE)
        cv_image = cv2.resize(cv_image, (100,100))
        images.append(np.asarray(cv_image, dtype=np.uint8))
        labels.append(label.id)
      except IOError, (errno, strerror):
       print "IOError({0}): {1}".format(errno, strerror)

That's because it isn't entering the for image in label.image_set: loop!

I have no idea whats wrong and I'm struggling with this from a long time. The only changes I made to the original code are,
Changed label.save() to label[0].save() and image.save() to image[0].save() since I was encountering the

image.save()
AttributeError: 'tuple' object has no attribute 'save'

and image = Image.get_or_create(path=path, label = label) to image = Image.get_or_create(path=path) since i was having this error -

cursor.execute(sql, params or ())
peewee.OperationalError: near ",": syntax error

Really require help with this. Thanks a lot.

Once a face is added, it keeps showing that particular face. How to add a new face?

[E 140101 23:41:21 websocket:306] Uncaught exception in /predict
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/tornado/websocket.py", line 303, in wrapper
return callback(_args, *_kwargs)
File "server.py", line 55, in on_message
self.process(image)
File "server.py", line 104, in process
result = opencv.predict(cv_image)
File "/root/School/Face/face-recognition-server-master/opencv.py", line 100, in predict
cropped = to_grayscale(crop_faces(cv_image, faces))
File "/root/School/Face/face-recognition-server-master/opencv.py", line 41, in crop_faces
return img[y:y+h,x:x+w]
File "/usr/local/lib/python2.7/dist-packages/PIL/Image.py", line 512, in getattr
raise AttributeError(name)
AttributeError: getitem