Training Error

[gitDawn]

Hi,

I've got some error after ruuning the training with python findFeatures.py -t dataset/train/ which states

Traceback (most recent call last):
File "findFeatures.py", line 35, in
fea_det = cv2.FeatureDetector_create("SIFT")
AttributeError: module 'cv2' has no attribute 'FeatureDetector_create'

Could you publish the packages version you have used for this build so I'll check if I'm using the same opencv version?

Thanks,
Shahar

[willard-yuan]

OpenCV removes the opencv_contrib since the version 3.0. So you need to compile OpenCVwith opencv_contrib. In my opinion, it's a good idea to choose OpenCv 2.X to run the code.

[gregorej]

@gitDawn take a look at my pull request #10. It solves this issue

You will need opencv with opencv_contrib for this.

[Khanjan14]

While training According to descriptor.py we must have equal number of images in both classes which may not be possible for all the database given to you. Here we can count no of images in train folder for both types and than proceed instead of dividing images in first half as class 0 and second half in Class 1.

Thanks.

[chifaa]

hi plz i hav anacanda

and i try to run the code and have that issu

File "C:\Users\wiam\findFeatures.py", line 8, in
import sklearn.external.joblib as extjoblib
ModuleNotFoundError: No module named 'sklearn.external'

[chifaa]

While training According to descriptor.py we must have equal number of images in both classes which may not be possible for all the database given to you. Here we can count no of images in train folder for both types and than proceed instead of dividing images in first half as class 0 and second half in Class 1.

Thanks.

plz how we can do this.im new in python