Tensorflow分割操作

Question

我正在尝试量化Tensorflow中卷积运算的输出。我的卷积层输出的形状是（1,38,38,64）。我有一个矢量（形状是（1,64））来量化每个滤波器输​​出。有64个滤波器，每个滤波器应该用矢量量化器量化。我试过除法操作，但结果不正确。我能做什么？

conv_op=convolve(img, filt)
q_standard = [[16, 11, 10, 16, 124, 140, 151, 161],
          [12, 12, 14, 19, 126, 158, 160, 155],
          [14, 13, 16, 24, 140, 157, 169, 156],
          [14, 17, 22, 29, 151, 187, 180, 162],
          [18, 22, 37, 56, 168, 109, 103, 177],
          [24, 35, 55, 64, 181, 104, 113, 192],
          [49, 64, 78, 87, 103, 121, 120, 101],
          [72, 92, 95, 98, 112, 100, 103, 199]]
weight_quantization = tf.get_variable('weight_quantization',initializer=tf.reshape(q_standard, [1, 64, -1, 1]))
quantized= tf.divide(conv_op,weight_quantization)

with tf.Session() as sess:
    initd=tf.global_variables_initializer()
    sess.run(initd)
    sess.run(quantized)
    print(quantized.eval())