paddlepaddle使用笔记2------VisulDL

痛定思痛。 2022-01-11 05:43 337阅读 0赞

## 1、参考教程 ##

[https://blog.csdn.net/qq\_33200967/article/details/86532831][https_blog.csdn.net_qq_33200967_article_details_86532831]

## 2、使用pip安装 ##

使用pip安装非常简单，只要一条命令就够了，如下：

pip3 install --upgrade visualdl

在与paddlepaddle相同的虚拟环境下安装

![20190619180305327.png][]

测试一下是否安装成功了，运行一个例子下载日志文件：

# 在当前位置下载一个日志
    vdl_create_scratch_log

![20190619180356899.png][]

然后再输入，启动VisualDL并加载这个日志信息：

visualdl --logdir=scratch_log/ --port=8080

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70][]

然后在浏览器上输入：

http://127.0.0.1:8080

即可看到一个可视化的界面，如下：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 1][]

##  ##

## 3、查看自己训练的模型 ##

从来自教程的代码：[https://www.jiqizhixin.com/articles/2019-03-04][https_www.jiqizhixin.com_articles_2019-03-04]

import paddle
    import paddle.fluid as fluid
    from visualdl import LogWriter
    
    
    # 构建一个LeNet-5网络
    def lenet_5(img, label):
        conv1 = fluid.nets.simple_img_conv_pool(
            input=img,
            filter_size=5,
            num_filters=20,
            pool_size=2,
            pool_stride=2,
            act="relu")
        conv1_bn = fluid.layers.batch_norm(input=conv1)
        conv2 = fluid.nets.simple_img_conv_pool(
            input=conv1_bn,
            filter_size=5,
            num_filters=50,
            pool_size=2,
            pool_stride=2,
            act="relu")
        predition = fluid.layers.fc(input=conv2, size=10, act="softmax", param_attr="fc_w")
        cost = fluid.layers.cross_entropy(input=predition, label=label)
        avg_cost = fluid.layers.mean(cost)
        acc = fluid.layers.accuracy(input=predition, label=label)
        return avg_cost, acc
    
    img = fluid.layers.data(name="img", shape=[1, 28, 28], dtype="float32")
    label = fluid.layers.data(name="label", shape=[1], dtype="int64")
    avg_cost, acc = lenet_5(img, label)
    train_reader = paddle.batch(paddle.dataset.mnist.train(), batch_size=64)
    optimizer = fluid.optimizer.Adam(learning_rate=0.001)
    optimizer.minimize(avg_cost)
    place = fluid.CPUPlace()
    feeder = fluid.DataFeeder(feed_list=[img, label], place=place)
    exe = fluid.Executor(place)
    
    log_writter = LogWriter("./vdl_log", sync_cycle=10)
    with log_writter.mode("train") as logger:
        # 分别用两个scalar来记录loss和accuracy的趋势
        scalar_loss = logger.scalar(tag="loss")
        scalar_accuracy = logger.scalar(tag="accuracy")
        # 用histogram来记录fc层的参数分布变化趋势
        histogram = logger.histogram(tag="histogram", num_buckets=50)
    
    exe.run(fluid.default_startup_program())
    step = 0
    epochs = 5
    param_name = "fc_w"
    for i in range(epochs):
        for batch in train_reader():
            cost, accuracy, param = exe.run(
                feed=feeder.feed(batch),
                fetch_list=[avg_cost.name, acc.name, param_name])
            step += 1
            # 将数据写入记录中
            scalar_loss.add_record(step, cost)
        scalar_accuracy.add_record(step, accuracy)
        histogram.add_record(step, param.flatten())
        print("epoch %d: step %d, acc is %.2f%% and loss is %.2f" % (i, step, accuracy * 100, cost))
        # 保存模型到model_save目录中，接着可以用visualdl --model_pb model_save来加载该模型
        fluid.io.save_inference_model(dirname="model_save", feeded_var_names=[img.name], target_vars=[avg_cost, acc],
                                      executor=exe)

运行代码，直到进程自然终止

然后在终端，进入虚拟环境，进入vdl\_log所在的文件夹，运行代码

visualdl --logdir=vdl_log/ --port=8080

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 2][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 3][]

我的vdl\_log文件夹在book/note10里面，所以在终端也要进入note10文件夹

否则需要在 --logdir的路径中输入绝对路径

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 4][]

在网页中可以看到本次训练的效果

[https_blog.csdn.net_qq_33200967_article_details_86532831]: https://blog.csdn.net/qq_33200967/article/details/86532831
[20190619180305327.png]: /images/20220111/a2a8383402b642da858c7c8ee6caa94c.png
[20190619180356899.png]: /images/20220111/f9970bcc22c143108a934923240bd80b.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70]: /images/20220111/f9a3a09b5925409593d1759a123360e6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 1]: /images/20220111/ac9da73e58e84715a8dc4a435a06d69b.png
[https_www.jiqizhixin.com_articles_2019-03-04]: https://www.jiqizhixin.com/articles/2019-03-04
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 2]: /images/20220111/fd560a2060c049ed80048ec4c24433c5.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 3]: /images/20220111/eb14afd1b95c407fb20f57b51d01d253.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0RpYW5hX1o_size_16_color_FFFFFF_t_70 4]: /images/20220111/3a328a0d16cb426b94f7f6ecf8faf044.png