如何在張量流上可視化學習的過濾器

Question

與Caffe框架類似，在CNN訓練期間可以觀看學習的過濾器，並與輸入圖像進行卷積，我想知道TensorFlow是否可以這樣做？

可以在以下鏈接中查看Caffe示例：

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

感謝您的幫助！

Answer 1

要在Tensorboard中僅看到幾個conv1過濾器，可以使用此代碼（它適用於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)

我還編寫了一個簡單的要點，以在網格中顯示所有64個conv1過濾器。