样本选取的理想情况：
模型想要达到的效果：
a minimal number of exemplars of any one identity is present in each mini-batch
单个个体的全部样本必须存在于每个mini-batch中
In our experiments we sample the training data such that around 40 faces are selected per identity per minibatch. Additionally, randomly sampled negative faces are added to each mini-batch.
每个mini-batch中每个个体有40张图片，先组成A-P对，然后再随机抽取负样本到mini-batch中组成（A,P,N)三元组。
Instead of picking the hardest positive, we use all anchor-positive pairs in a mini-batch while still selecting the hard negatives. We found in practice that the all anchor-positive method was more stable and converged slightly faster（收敛更快） at the beginning of training
所有的A-P对和满足条件的A-N对
具体过程：
先从训练数据集中抽样出一组图片到mini-batch中，计算这些图片在当时的网络模型中得到的embedding，保存在emb_array当中。
每个mini-batch有多类图，每类图有多张
（A,N)需满足的条件：
all_neg = np.where(neg_dists_sqr-pos_dist_sqr<alpha)[0] # VGG Face三元组的选取
def select_triplets(embeddings, nrof_images_per_class, image_paths, people_per_batch, alpha):
""" Select the triplets for training
"""
trip_idx = 0
#某个人的图片的embedding在emb_arr中的开始的索引
emb_start_idx = 0
num_trips = 0
triplets = []
# VGG Face: Choosing good triplets is crucial and should strike a balance between
# selecting informative (i.e. challenging) examples and swamping training with examples that
# are too hard. This is achieve by extending each pair (a, p) to a triplet (a, p, n) by sampling
# the image n at random, but only between the ones that violate the triplet loss margin. The
# latter is a form of hard-negative mining, but it is not as aggressive (and much cheaper) than
# choosing the maximally violating example, as often done in structured output learning.
#遍历每一个人
for i in xrange(people_per_batch):
#这个人有多少张图片
nrof_images = int(nrof_images_per_class[i])
#遍历第i个人的所有图片
for j in xrange(1,nrof_images):
#第j张图的embedding在emb_arr 中的位置
a_idx = emb_start_idx + j - 1
#第j张图跟其他所有图片的欧氏距离
neg_dists_sqr = np.sum(np.square(embeddings[a_idx] - embeddings), 1)
#遍历每一对可能的(anchor,postive)图片，记为(a,p)吧
for pair in xrange(j, nrof_images): # For every possible positive pair.
#第p张图片在emb_arr中的位置
p_idx = emb_start_idx + pair
#(a,p)之前的欧式距离
pos_dist_sqr = np.sum(np.square(embeddings[a_idx]-embeddings[p_idx]))
#同一个人的图片不作为negative，所以将距离设为无穷大
neg_dists_sqr[emb_start_idx:emb_start_idx+nrof_images] = np.NaN
#all_neg = np.where(np.logical_and(neg_dists_sqr-pos_dist_sqr<alpha, pos_dist_sqr<neg_dists_sqr))[0] # FaceNet selection
#其他人的图片中有哪些图片与a之间的距离-p与a之间的距离小于alpha的
all_neg = np.where(neg_dists_sqr-pos_dist_sqr<alpha)[0] # VGG Face selecction
#所有可能的negative
nrof_random_negs = all_neg.shape[0]
#如果有满足条件的negative
if nrof_random_negs>0:
#从中随机选取一个作为n
rnd_idx = np.random.randint(nrof_random_negs)
n_idx = all_neg[rnd_idx]
# 选到(a,p,n)作为三元组
triplets.append((image_paths[a_idx], image_paths[p_idx], image_paths[n_idx]))
#print('Triplet %d: (%d, %d, %d), pos_dist=%2.6f, neg_dist=%2.6f (%d, %d, %d, %d, %d)' %
# (trip_idx, a_idx, p_idx, n_idx, pos_dist_sqr, neg_dists_sqr[n_idx], nrof_random_negs, rnd_idx, i, j, emb_start_idx))
trip_idx += 1
num_trips += 1
emb_start_idx += nrof_images
np.random.shuffle(triplets)
return triplets, num_trips, len(triplets)从数据集中选择图片，组成一个batch
#从数据集中进行抽样图片，参数为训练数据集，每一个batch抽样多少人，每个人抽样多少张
def sample_people(dataset, people_per_batch, images_per_person):
#总共应该抽样多少张 默认：people_per_batch：45 images_per_person：40
nrof_images = people_per_batch * images_per_person
#数据集中一共有多少人的图像
nrof_classes = len(dataset)
#每个人的索引
class_indices = np.arange(nrof_classes)
#随机打乱一下
np.random.shuffle(class_indices)
i = 0
#保存抽样出来的图像的路径
image_paths = []
#抽样的样本是属于哪一个人的，作为label
num_per_class = []
sampled_class_indices = []
# Sample images from these classes until we have enough
# 不断抽样直到达到指定数量
while len(image_paths)<nrof_images:
#从第i个人开始抽样
class_index = class_indices[i]
#第i个人有多少张图片
nrof_images_in_class = len(dataset[class_index])
#这些图片的索引
image_indices = np.arange(nrof_images_in_class)
np.random.shuffle(image_indices)
#从第i个人中抽样的图片数量
nrof_images_from_class = min(nrof_images_in_class, images_per_person, nrof_images-len(image_paths))
idx = image_indices[0:nrof_images_from_class]
#抽样出来的人的路径
image_paths_for_class = [dataset[class_index].image_paths[j] for j in idx]
#图片的label
sampled_class_indices += [class_index]*nrof_images_from_class
image_paths += image_paths_for_class
#第i个人抽样了多少张
num_per_class.append(nrof_images_from_class)
i+=1
return image_paths, num_per_class