Revision history [back]

let's go down your list:

1: no, it will try to make as many negative samples as it can from that, based on a slidinng window using your positive size

2: yes, correct , if your positive images actually are that way.

3: yes.

4: that's kinda complicated. since the "boosting" part of the training algo will shuffle some of your "positives" to the "negative" side -- allow some space there, (e.g., have 20% more actual positives in your vec file, than given to "-numPositives"

let's go down your list:

1: no, it will try to make as many negative samples as it can from that, based on a slidinng sliding window using your positive size

2: yes, correct , if your positive images actually are that way.

3: yes.

4: that's kinda complicated. since the "boosting" part of the training algo will shuffle some of your "positives" to the "negative" side -- allow some space there, (e.g., have 20% more actual positives in your vec file, than given to "-numPositives"

let's go down your list:

1: no, it will try to make as many negative samples as it can from that, based on a sliding window using your positive size

2: yes, correct , if your positive images actually are that way.

3: yes.yes. (well, let's say "same" for both, whatever your window-size is)

4: that's kinda complicated. since the "boosting" part of the training algo will shuffle some of your "positives" to the "negative" side -- allow some space there, (e.g., have 20% more actual positives in your vec file, than given to "-numPositives"

let's go down your list:

1: no, it will try to make as many negative samples as it can from that, based on a sliding window using your positive sizesize

(just know, that it's a bad idea to feed 20 10k negative imgs showing plant leaves, while you're trying to pick a car on a street, -- choose wisely here.)

2: yes, correct , if your positive images actually are that way.

3: yes. (well, let's say "same" for both, whatever your window-size is)

4: that's kinda complicated. since the "boosting" part of the training algo will shuffle some of your "positives" to the "negative" side -- allow some space there, (e.g., have 20% more actual positives in your vec file, than given to "-numPositives"

let's go down your list:

1: no, it will try to make as many negative samples as it can from that, based on a sliding window using your positive size size, moving sequentially AND multiscale (fixed scale step to differentiate enough) over your input image.

(just know, that it's a bad idea to feed 20 10k negative imgs showing plant leaves, while you're trying to pick a car on a street, -- choose wisely here.)here.) Agreed to this, make sure your negative dataset is representative to your problem or be prepared to collect millions of samples...

2: yes, correct , if your positive images actually are that way.

3: yes. (well, let's say "same" for both, whatever your window-size is)

4: that's kinda complicated. since the "boosting" part of the training algo will shuffle some of your "positives" to the "negative" side -- allow some space there, (e.g., have 20% more actual positives in your vec file, than given to "-numPositives"