tensorboard-理解tensorboard IMAGE标签

Question

我正在使用 tensorboard 可视化我的火车图像（cifar10 数据集）。但是 TensorBoard 向我展示了一些非常奇怪的图像。下面是屏幕截图。

the strange images

这里是一些相关的代码。注意DISPLAY_STEP是10，BATCH_SIZE是64。

x = tf.placeholder(tf.float32, shape=[None, N_FEATURES], name='x')
x_image = tf.reshape(x, [-1, 32, 32, 3])
tf.summary.image('input', x_image, max_outputs=BATCH_SIZE)
y = tf.placeholder(tf.float32, [None, N_CLASSES], name='labels')

'''There is other code.'''

with tf.Session() as sess:
    sess.run(init)
    summary_writer = tf.summary.FileWriter('./cifar10_model/6', graph=tf.get_default_graph())
    for i in range(TRAINING_EPOCHS):
        batch_x, batch_y = cifar10.train.next_batch(BATCH_SIZE)
        if i % DISPLAY_STEP == 0:
            s = sess.run(merged_summary, feed_dict={x: batch_x, y: batch_y})
            summary_writer.add_summary(s, i)
        sess.run(train_step, feed_dict={x: batch_x, y: batch_y})

谁能告诉我这是怎么回事？提前致谢。

Answer 1

看起来 cifar 图像没有正确整形。 According to the dataset website:

data -- a 10000x3072 numpy array of uint8s. Each row of the array stores a 32x32 colour image. The first 1024 entries contain the red channel values, the next 1024 the green, and the final 1024 the blue. The image is stored in row-major order, so that the first 32 entries of the array are the red channel values of the first row of the image.

您应该确保这个 3072 长的数组已正确重塑。

tensorboard-理解tensorboard IMAGE标签

tensorboard-Understanding tensorboard IMAGE tag

tensorflow

tensorboard