nayeem8527 / live-facial-recognition Goto Github PK

I meet some problem when i use classifier.py to train new dataset, as below:
"
Number of classes: 1
Number of images: 30
labels:
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]

error:
Training classifier
Traceback (most recent call last):
File "classifier.py", line 176, in
main(parse_arguments(sys.argv[1:]))
File "classifier.py", line 102, in main
model.fit(emb_array, labels)
File "/home/yview/.local/lib/python2.7/site-packages/sklearn/svm/base.py", line 150, in fit
y = self._validate_targets(y)
File "/home/yview/.local/lib/python2.7/site-packages/sklearn/svm/base.py", line 525, in _validate_targets
" class" % len(cls))
ValueError: The number of classes has to be greater than one; got 1 class
"

The new dataset locate at the same dir as:
./dataset
|__ thomas
|__thomas_0001.jpg
|__thomas_0002.jpg
...
|__thomas_00030.jpg
The command as below:
python classifier.py --image_size 160 --batch_size 30 TRAIN dataset models/20170511-185253.pb thomas

i think classifier.py can not read the labels from the dataset.
how can i do to make classifier.py read the labels correctly?

hi, may i know your computer specification to get 17fps?

hi, i just check train_classifier.py, is face alignment required before training the classifier?