christopher5106.github.io

I am working on implementing YOLO v2 and 3 for object detection on a custom dataset. While YOLO v2 and 3 use something like 5 or so anchor boxes, I generally have maybe 50-100 detections each image. My sense is that if there are only 5 anchor boxes, then there are at most 5 detections per image right? So I was trying to understand if I needed to adjust the number of anchor boxes to my dataset.

My questions is, does the number of anchor boxes need to be larger than the maximum count of bounding boxes in any training image? That way, I would never run into detections where there is no corresponding anchor box. Is that the right way of thinking about adapting YOLO?

If my intuition is correct then would I need to do k-means to cluster the bounding boxes in the ground truth images and set the anchor box coordinates. Then I would use the usual regression method as specified in this blog post.

Thanks for any help that anyone can provide.

I am trying to learn deep learning, I have stumbled on one exercise here

It is first warm-up exercise. I am stuck. For constant sequence of small lengths(2,3) it solves it no problem. However when I try whole sequence of 50. it stops at 50% accuracy, which is basically random guess.

According to here it is too big flat space ant cant find gradient to solve it. So i tried approach of continuously increasing length ans saving model each time (2,5,10,15,20,30,40,50).It seems it does not generalise well, as if i type bigger sequence then what I learned it on, it fails.

According to here it should be easy problem. I cant figure it out. There is used some different LSTM architecture hoverer.

And one solution here to exactly same problem says it works with Adagrad optimizer and learning rate of 0.5.

I am unsure about one bit at time, if I am feeding it right in first place. I hope I got it right.

And for variable length, i tried and failed miserably.

Code:

Following this question and this tutorial I've create a simple net just like the tutorial but with 100X100 images and first convolution kernel of 11X11 and pad=0.

I understand that the formula is : (W−F+2P)/S+1 and in my case dimension became [51X51X3] (3 is channel of rgb) but the number 96 popup in my net diagram and as this tutorial said it is third dimension of the output, in other hand , my net after first conv became [51X51X96]. I couldn't figure out , how the number 96 calculated and why.

Isn't the network convolution layer suppose to pass throw three color channel and the output should be three feature map? How come its dimension grow like this? Isn't it true that we have one kernel for each channel ? How this one kernel create 96(or in the first tutorial, 256 or 384) feature map ?

I am trying to evaluate the training function of the Watson visual Recognition API. Has anyone some experience with costumizing classifers for Visual Recognition? I have some expierence myself with training the classifier and found some infomation in this blog: http://christopher5106.github.io/computer/vision/2016/12/23/ibm-watson-bluemix-visual-api-to-create-custom-classifier.html

What I really would like to know is how much pictures do I need of an object to classify it with an accuracy of 75%? How long does it take to get such a result?

Thank you in advance for your help.