如何在tensorflow上可视化学习过滤器

Question

与Caffe框架类似,可以在CNN训练期间观察学习过滤器,并通过输入图像进行卷积,我想知道是否可以使用TensorFlow进行同样的操作？

可以在此链接中查看Caffe示例:

http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/00-classification.ipynb

感谢你的帮助!

Answer 1

要在Tensorboard中查看几个conv1过滤器,您可以使用此代码(适用于cifar10)

# this should be a part of the inference(images) function in cifar10.py file

# conv1
with tf.variable_scope('conv1') as scope:
  kernel = _variable_with_weight_decay('weights', shape=[5, 5, 3, 64],
                                       stddev=1e-4, wd=0.0)
  conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
  biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
  bias = tf.nn.bias_add(conv, biases)
  conv1 = tf.nn.relu(bias, name=scope.name)
  _activation_summary(conv1)

  with tf.variable_scope('visualization'):
    # scale weights to [0 1], type is still float
    x_min = tf.reduce_min(kernel)
    x_max = tf.reduce_max(kernel)
    kernel_0_to_1 = (kernel - x_min) / (x_max - x_min)

    # to tf.image_summary format [batch_size, height, width, channels]
    kernel_transposed = tf.transpose (kernel_0_to_1, [3, 0, 1, 2])

    # this will display random 3 filters from the 64 in conv1
    tf.image_summary('conv1/filters', kernel_transposed, max_images=3)

我还写了一个简单的要点,在网格中显示所有64个conv1过滤器.