zhouzypaul/bovw-classifier

Bag of Visual Words (BOVW) classifier for image classification; opencv-python and sklearn implementation

Hi! I am Zhiyuan "Paul" Zhou and I recently graduated from Brown University studying Applied Math & CS. I'm interested in Reinforcement Learning. Come check out my website for more info!

bovw-classifier's Issues

train.py problem

hi

File ".\bovw\train.py", line 35, in
main()
File ".\bovw\train.py", line 20, in main
predictions = classifier.predict(testing_images)
File "C:\RouBot\bovw\bovw\classifier.py", line 62, in predict
hist_features = self.histogram_from_sift(sift_features=sift_features) # get histogram
File "C:\RouBot\bovw\bovw\classifier.py", line 160, in histogram_from_sift
sift_features_of_all_images = np.concatenate(sift_features, axis=0)
File "<array_function internals>", line 5, in concatenate
ValueError: need at least one array to concatenate

i am getting this error when trying train.py

do you know what can cause it ?

issue for train

Traceback (most recent call last):
File "d:/digital-image-processing/bovw-classifier-main/bovw/train.py", line 37, in
main()
File "d:/digital-image-processing/bovw-classifier-main/bovw/train.py", line 19, in main
classifier.fit(training_images, training_classes)
File "d:\digital-image-processing\bovw-classifier-main\bovw\classifier.py", line 44, in fit
self.train_kmeans(sift_features=sift_features)
File "d:\digital-image-processing\bovw-classifier-main\bovw\classifier.py", line 122, in train_kmeans
sift_features=np.concatenate(sift_features, axis=0)
File "<array_function internals>", line 5, in concatenate
ValueError: all the input arrays must have same number of dimensions, but the array at index 0 has 2 dimension(s) and the array at index 49 has 0 dimension(s)

add lever to control number of key points SIFT uses

make cv2 operations batched, and optimized kmeans to make training faster