TensorBoard可视化

tensorboard可以实现在web端显示监听的数据变化。
以mnist手写字识别为例。

下载安装tensorboard

1.直接在pycharm中下载

2.cmd直接pip

监听目录

先到程序的根目录，然后tensorboard --logdir logs,找到网址复制到网页打开，若失败则将网址冒号前改成localhost

在cpu端建立日志summary

current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
log_dir = 'logs/' + current_time
summary_writer = tf.summary.create_file_writer(log_dir) #创建writer,可以喂数据

喂数据给summary

    if step % 100 == 0:#每隔一段时间给train-loss喂数据

        print(step, 'loss:', float(loss))
        with summary_writer.as_default(): 
            tf.summary.scalar('train-loss', float(loss), step=step) #喂scalar数据给loss,x轴step

    # evaluate
    if step % 500 == 0:#每隔一段时间给test-acc喂数据
        total, total_correct = 0., 0

        for _, (x, y) in enumerate(ds_val):  
            # [b, 28, 28] => [b, 784]
            x = tf.reshape(x, (-1, 28*28))
            # [b, 784] => [b, 10]
            out = network(x) 
            # [b, 10] => [b] 
            pred = tf.argmax(out, axis=1) 
            pred = tf.cast(pred, dtype=tf.int32)
            # bool type 
            correct = tf.equal(pred, y)
            # bool tensor => int tensor => numpy
            total_correct += tf.reduce_sum(tf.cast(correct, dtype=tf.int32)).numpy()
            total += x.shape[0]

        print(step, 'Evaluate Acc:', total_correct/total)

        
        # print(x.shape) 
        val_images = x[:25]
        val_images = tf.reshape(val_images, [-1, 28, 28, 1])
        with summary_writer.as_default():
            tf.summary.scalar('test-acc', float(total_correct/total), step=step)#喂数据
            tf.summary.image("val-onebyone-images:", val_images, max_outputs=25, step=step)#喂图片，方式很零散
            
            val_images = tf.reshape(val_images, [-1, 28, 28])
            figure  = image_grid(val_images)
            tf.summary.image('val-images:', plot_to_image(figure), step=step)#人为拼接图片，多张图片以一张传，优先考虑

查看

最上面的图是喂的单张图片，下面是人为组合过后的图片。