首页 > 解决方案 > 当输入时我只有两个文件(即在测试时)时如何处理三元组丢失

问题描述

我正在实现一个连体网络,在其中我知道如何通过将输入分成三部分(这是一个手工制作的特征向量)然后在训练时计算它来选择锚点、正数和负数来计算三元组损失。

anchor_output = ...  # shape [None, 128]
positive_output = ...  # shape [None, 128]
negative_output = ...  # shape [None, 128]

d_pos = tf.reduce_sum(tf.square(anchor_output - positive_output), 1)
d_neg = tf.reduce_sum(tf.square(anchor_output - negative_output), 1)

loss = tf.maximum(0., margin + d_pos - d_neg)
loss = tf.reduce_mean(loss)

但问题是,在测试时,我只有两个正面和负面的文件,然后我将如何处理(三胞胎,因为我需要一个锚文件,但我的应用程序只拍一张照片并与数据库中的比较,所以只有两个在这种情况下的文件),我搜索了很多,但没有人提供处理这个问题的代码,只有实现三元组丢失的代码,但不是整个场景。我不想使用对比损失

标签: kerasdeep-learninglstmtensorflow-estimatorloss-function

解决方案


在 CIFAR 10 上带有测试代码的 Colab 笔记本: https ://colab.research.google.com/drive/1VgOTzr_VZNHkXh2z9IiTAcEgg5qr19y0

总体思路:

from tensorflow import keras
from tensorflow.keras.layers import *
from tensorflow.keras.models import Model
from tensorflow.keras import backend as K

img_width = 128
img_height = 128
img_colors = 3

margin = 1.0

VECTOR_SIZE = 32

def triplet_loss(y_true, y_pred):
  """ y_true is a dummy value that should be ignored

      Uses the inverse of the cosine similarity as a loss.
  """
  anchor_vec = y_pred[:, :VECTOR_SIZE]
  positive_vec = y_pred[:, VECTOR_SIZE:2*VECTOR_SIZE]
  negative_vec = y_pred[:, 2*VECTOR_SIZE:]
  d1 = keras.losses.cosine_proximity(anchor_vec, positive_vec)
  d2 = keras.losses.cosine_proximity(anchor_vec, negative_vec)
  return K.clip(d2 - d1 + margin, 0, None)


def make_image_model():
  """ Build a convolutional model that generates a vector
  """
  inp = Input(shape=(img_width, img_height, img_colors))
  l1 = Conv2D(8, (2, 2))(inp)
  l1 = MaxPooling2D()(l1)
  l2 = Conv2D(16, (2, 2))(l1)
  l2 = MaxPooling2D()(l2)
  l3 = Conv2D(16, (2, 2))(l2)
  l3 = MaxPooling2D()(l3)
  conv_out = Flatten()(l3)
  out = Dense(VECTOR_SIZE)(conv_out)
  model = Model(inp, out)
  return model

def make_siamese_model(img_model):
  """ Siamese model input are 3 images base, positive, negative
      output is a dummy variable that is ignored for the purposes of loss
      calculation.
  """
  anchor = Input(shape=(img_width, img_height, img_colors))
  positive = Input(shape=(img_width, img_height, img_colors))
  negative = Input(shape=(img_width, img_height, img_colors))
  anchor_vec = img_model(anchor)
  positive_vec = img_model(positive)
  negative_vec = img_model(negative)
  vecs = Concatenate(axis=1)([anchor_vec, positive_vec, negative_vec])
  model = Model([anchor, positive, negative], vecs)
  model.compile('adam', triplet_loss)
  return model

img_model = make_image_model()
train_model = make_siamese_model(img_model)
img_model.summary()
train_model.summary()

###
train_model.fit(X, dummy_y, ...)

img_model.save('image_model.h5')

###
# In order to use the model
vec_base = img_model.predict(base_image)
vec_test = img_model.predict(test_image)

比较 和 的余弦相似度,vec_basevec_test确定基础和测试是否在可接受的标准内。


推荐阅读