我试图按照facenet article中的说明训练三联网。
我通过计算正距离（锚点 - 正数）小于负距离（锚点 - 负数）然后除以三元组总数的三元组来计算验证集的准确度。批次。
我得到了很好的结果：99％的准确率。但是，当我使用我的模型嵌入来对图像进行分类时（我拍摄一张未知图像并进行比较 - 使用欧几里德距离 - 使用一些标记图像） - 最多只有20％的结果是正确的。
我做错了什么？
您可以在下面找到我的详细实施。
生成三胞胎
在生成三联体之前，我已经使用dlib （CASIA和LFW）对齐并裁剪了训练和测试集，因此每个面部的主要元素（眼睛，没有，嘴唇） ）位置几乎相同。
为了生成三联体，我随机选择一个包含40个或更多图像的CASIA文件夹，然后我选择40个锚点，每个锚点具有相应的正图像（随机挑选但与锚点不同）。然后我为每个锚定阳性对选择一个随机阴性。
三胞胎丢失
这是我的三重损失功能：
def triplet_loss(d_pos, d_neg):
print("d_pos "+str(d_pos))
print("d_neg "+str(d_neg))
margin = 0.2
loss = tf.reduce_mean(tf.maximum(0., margin + d_pos - d_neg))
return loss
这些是我的正距离（锚点和正面之间）和负距离（锚点和负面距离之间）。
**model1** = embeddings generated for the anchor image
**model2** = embeddings generated for the positive image
**model3** = embeddings generated for the negative image
变量成本是我在每一步计算的损失。
d_pos_triplet = tf.reduce_sum(tf.square(model1 - model2), 1)
d_neg_triplet = tf.reduce_sum(tf.square(model1 - model3), 1)
d_pos_triplet_acc = tf.sqrt(d_pos_triplet + 1e-10)
d_neg_triplet_acc = tf.sqrt(d_neg_triplet + 1e-10)
d_pos_triplet_test = tf.reduce_sum(tf.square(model1_test - model2_test), 1)
d_neg_triplet_test = tf.reduce_sum(tf.square(model1_test - model3_test), 1)
d_pos_triplet_acc_test = tf.sqrt(d_pos_triplet_test + 1e-10)
d_neg_triplet_acc_test = tf.sqrt(d_neg_triplet_test + 1e-10)
cost = triplet_loss(d_pos_triplet, d_neg_triplet)
cost_test = triplet_loss(d_pos_triplet_test, d_neg_triplet_test)
然后我逐个嵌入并测试损失是否为正 - 因为0丢失意味着网络无法学习（正如facenet文章中所述，我必须选择半硬三胞胎）
input1,input2, input3, anchor_folder_helper, anchor_photo_helper, positive_photo_helper = training.next_batch_casia(s,e) #generate complet random
s = i * batch_size
e = (i+1) *batch_size
input1,input2, input3, anchor_folder_helper, anchor_photo_helper, positive_photo_helper = training.next_batch_casia(s,e) #generate complet random
lly = 0;
'''counter which helps me generate the same number of triplets each batch'''
while lly < len(input1):
input_lly1 = input1[lly:lly+1]
input_lly2 = input2[lly:lly+1]
input_lly3 = input3[lly:lly+1]
loss_value = sess.run([cost], feed_dict={x_anchor:input_lly1, x_positive:input_lly2, x_negative:input_lly3})
while(loss_value[0]<=0):
''' While the generated triplet has loss 0 (which means dpos - dneg + margin < 0) I keep generating triplets. I stop when I manage to generate a semi-hard triplet. '''
input_lly1,input_lly2, input_lly3, anchor_folder_helper, anchor_photo_helper, positive_photo_helper = training.cauta_hard_negative(anchor_folder_helper, anchor_photo_helper, positive_photo_helper)
loss_value = sess.run([cost], feed_dict={x_anchor:input_lly1, x_positive:input_lly2, x_negative:input_lly3})
if (loss_value[0] > 0):
_, loss_value, distance1_acc, distance2_acc, m1_acc, m2_acc, m3_acc = sess.run([accum_ops, cost, d_pos_triplet_acc, d_neg_triplet_acc, model1, model2, model3], feed_dict={x_anchor:input_lly1, x_positive:input_lly2, x_negative:input_lly3})
tr_acc = compute_accuracy(distance1_acc, distance2_acc)
if math.isnan(tr_acc) and epoch != 0:
print('tr_acc %0.2f' % tr_acc)
pdb.set_trace()
avg_loss += loss_value
avg_acc +=tr_acc*100
contor_i = contor_i + 1
lly = lly + 1
这是我的模型 - 请注意，当我应用L2规范化时，我的准确度会显着下降（也许我做错了）：
def siamese_convnet(x):
w_conv1_1 = tf.get_variable(name='w_conv1_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 1, 64])
w_conv1_2 = tf.get_variable(name='w_conv1_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 64, 64])
w_conv2_1 = tf.get_variable(name='w_conv2_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 64, 128])
w_conv2_2 = tf.get_variable(name='w_conv2_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 128, 128])
w_conv3_1 = tf.get_variable(name='w_conv3_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 128, 256])
w_conv3_2 = tf.get_variable(name='w_conv3_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 256, 256])
w_conv3_3 = tf.get_variable(name='w_conv3_3', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 256, 256])
w_conv4_1 = tf.get_variable(name='w_conv4_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 256, 512])
w_conv4_2 = tf.get_variable(name='w_conv4_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 512, 512])
w_conv4_3 = tf.get_variable(name='w_conv4_3', initializer=tf.contrib.layers.xavier_initializer(), shape=[1, 1, 512, 512])
w_conv5_1 = tf.get_variable(name='w_conv5_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 512, 512])
w_conv5_2 = tf.get_variable(name='w_conv5_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[3, 3, 512, 512])
w_conv5_3 = tf.get_variable(name='w_conv5_3', initializer=tf.contrib.layers.xavier_initializer(), shape=[1, 1, 512, 512])
w_fc_1 = tf.get_variable(name='w_fc_1', initializer=tf.contrib.layers.xavier_initializer(), shape=[5*5*512, 2048])
w_fc_2 = tf.get_variable(name='w_fc_2', initializer=tf.contrib.layers.xavier_initializer(), shape=[2048, 1024])
w_out = tf.get_variable(name='w_out', initializer=tf.contrib.layers.xavier_initializer(), shape=[1024, 128])
bias_conv1_1 = tf.get_variable(name='bias_conv1_1', initializer=tf.constant(0.01, shape=[64]))
bias_conv1_2 = tf.get_variable(name='bias_conv1_2', initializer=tf.constant(0.01, shape=[64]))
bias_conv2_1 = tf.get_variable(name='bias_conv2_1', initializer=tf.constant(0.01, shape=[128]))
bias_conv2_2 = tf.get_variable(name='bias_conv2_2', initializer=tf.constant(0.01, shape=[128]))
bias_conv3_1 = tf.get_variable(name='bias_conv3_1', initializer=tf.constant(0.01, shape=[256]))
bias_conv3_2 = tf.get_variable(name='bias_conv3_2', initializer=tf.constant(0.01, shape=[256]))
bias_conv3_3 = tf.get_variable(name='bias_conv3_3', initializer=tf.constant(0.01, shape=[256]))
bias_conv4_1 = tf.get_variable(name='bias_conv4_1', initializer=tf.constant(0.01, shape=[512]))
bias_conv4_2 = tf.get_variable(name='bias_conv4_2', initializer=tf.constant(0.01, shape=[512]))
bias_conv4_3 = tf.get_variable(name='bias_conv4_3', initializer=tf.constant(0.01, shape=[512]))
bias_conv5_1 = tf.get_variable(name='bias_conv5_1', initializer=tf.constant(0.01, shape=[512]))
bias_conv5_2 = tf.get_variable(name='bias_conv5_2', initializer=tf.constant(0.01, shape=[512]))
bias_conv5_3 = tf.get_variable(name='bias_conv5_3', initializer=tf.constant(0.01, shape=[512]))
bias_fc_1 = tf.get_variable(name='bias_fc_1', initializer=tf.constant(0.01, shape=[2048]))
bias_fc_2 = tf.get_variable(name='bias_fc_2', initializer=tf.constant(0.01, shape=[1024]))
out = tf.get_variable(name='out', initializer=tf.constant(0.01, shape=[128]))
x = tf.reshape(x , [-1, 160, 160, 1]);
conv1_1 = tf.nn.relu(conv2d(x, w_conv1_1) + bias_conv1_1);
conv1_2= tf.nn.relu(conv2d(conv1_1, w_conv1_2) + bias_conv1_2);
max_pool1 = max_pool(conv1_2);
conv2_1 = tf.nn.relu( conv2d(max_pool1, w_conv2_1) + bias_conv2_1 );
conv2_2 = tf.nn.relu( conv2d(conv2_1, w_conv2_2) + bias_conv2_2 );
max_pool2 = max_pool(conv2_2)
conv3_1 = tf.nn.relu( conv2d(max_pool2, w_conv3_1) + bias_conv3_1 );
conv3_2 = tf.nn.relu( conv2d(conv3_1, w_conv3_2) + bias_conv3_2 );
conv3_3 = tf.nn.relu( conv2d(conv3_2, w_conv3_3) + bias_conv3_3 );
max_pool3 = max_pool(conv3_3)
conv4_1 = tf.nn.relu( conv2d(max_pool3, w_conv4_1) + bias_conv4_1 );
conv4_2 = tf.nn.relu( conv2d(conv4_1, w_conv4_2) + bias_conv4_2 );
conv4_3 = tf.nn.relu( conv2d(conv4_2, w_conv4_3) + bias_conv4_3 );
max_pool4 = max_pool(conv4_3)
conv5_1 = tf.nn.relu( conv2d(max_pool4, w_conv5_1) + bias_conv5_1 );
conv5_2 = tf.nn.relu( conv2d(conv5_1, w_conv5_2) + bias_conv5_2 );
conv5_3 = tf.nn.relu( conv2d(conv5_2, w_conv5_3) + bias_conv5_3 );
max_pool5 = max_pool(conv5_3)
fc_helper = tf.reshape(max_pool5, [-1, 5*5*512]);
fc_1 = tf.nn.relu( tf.matmul(fc_helper, w_fc_1) + bias_fc_1 );
fc_2 = tf.nn.relu( tf.matmul(fc_1, w_fc_2) + bias_fc_2 );
output = tf.matmul(fc_2, w_out) + out
#output = tf.nn.l2_normalize(output, 0) THIS IS COMMENTED
return output
我的模型以独立于框架的方式：
conv 3x3 (1, 64)
conv 3x3 (64,64)
max_pooling
conv 3x3 (64, 128)
conv 3x3 (128, 128)
max_pooling
conv 3x3 (128, 256)
conv 3x3 (256, 256)
conv 3x3 (256, 256)
max_pooling
conv 3x3 (256, 512)
conv 3x3 (512, 512)
conv 1x1 (512, 512)
max_pooling
conv 3x3 (256, 512)
conv 3x3 (512, 512)
conv 1x1 (512, 512)
max_pooling
fully_connected(128)
fully_connected(128)
output(128)
答案 0 :(得分：1)
当你的L2规范化应该是典型的时候，它是特征性的。