由於權重未明確定義,我如何將它們傳遞給摘要作者?如何在tf.layers上使用張量板?
對於爲例:
conv1 = tf.layers.conv2d(
tf.reshape(X,[FLAGS.batch,3,160,320]),
filters = 16,
kernel_size = (8,8),
strides=(4, 4),
padding='same',
kernel_initializer=tf.contrib.layers.xavier_initializer(),
bias_initializer=tf.zeros_initializer(),
kernel_regularizer=None,
name = 'conv1',
activation = tf.nn.elu
)
=>
summarize_tensor(
??????
)
謝謝!
Conv2D對象沒有屬性'kernel' –
內核屬性是不存在了,有現在是'權重',但我不確定'tf.summary.histogram(「權重」,conv1_layer.weights)是否足夠。 – juliohm