tipletselectlayer - computing the distance against the anchor image

[identidata]

When you calculate the dot product between the anchor feature and all positive features, you are calculating the product between the first image of anchor layer (total 10 images, using a batch of 30 as in your example) and all images of the positive layer.

archor_feature = bottom[0].data[0]
        for i in range(self.triplet):
            positive_feature = bottom[0].data[i+self.triplet]
            a_p = archor_feature - positive_feature
            ap = np.dot(a_p,a_p)
            aps[i+self.triplet] = ap

You repeat a similar procedure between the first image in the anchor layer and all images in the negative layer:

for i in range(self.triplet):
            negative_feature = bottom[0].data[i+self.triplet*2]
            a_n = archor_feature - negative_feature
            an = np.dot(a_n,a_n)
            ans[i+self.triplet*2] = an

I am not sure if there is a away around it, but what are all the other images in the anchor layer used for? (in your example 9 images, from image 1 to image 9)? nothing?

[PramuPerera]

If there are 9 images, first three (self.triplet==3 here) are used as anchors (anchor is given by the positive_feature variable).
Note that positive feature is changing at every iteration.
a_p = archor_feature - positive_feature subtracts the positive feature from the whole batch.
ap = np.dot(a_p,a_p) calculates the l2 distance.

[gitrobin]

but the second and third anchors are useless?