基于tensorflow的鸢尾花Iris分类实战

最新推荐文章于 2022-12-25 17:45:03 发布

Weiyaner

最新推荐文章于 2022-12-25 17:45:03 发布

阅读量726

点赞数

分类专栏：机器学习项目文章标签： tensorflow 分类 python

本文链接：https://blog.csdn.net/weixin_42327752/article/details/123136341

版权

机器学习项目专栏收录该内容

3 篇文章 2 订阅

订阅专栏

导包

import os
import six.moves.urllib.request as request
import tensorflow as tf
from matplotlib import pyplot as plt

# Check that we have correct TensorFlow version installed
tf_version = tf.__version__
print("TensorFlow version: {}".format(tf_version))

TensorFlow version: 2.8.0

导入数据

获取数据文件目录

# 获取当前工作目录
PATH = os.getcwd()
# Fetch and store Training and Test dataset files
PATH_DATASET = PATH + os.sep + "dataset"
FILE_TRAIN = PATH_DATASET + os.sep + "iris_training.csv"
FILE_TEST = PATH_DATASET + os.sep + "iris_test.csv"
URL_TRAIN = "https://download.tensorflow.org/data/iris_training.csv"
URL_TEST = "https://download.tensorflow.org/data/iris_test.csv"

column_names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species']
feature_names = column_names[:-1]
label_name = column_names[-1]
class_names = ['Iris setosa', 'Iris versicolor', 'Iris virginica']

csv文件转为dataset

def get_dataset(file_path):
    dataset = tf.data.experimental.make_csv_dataset(
        file_path,
        batch_size=12, # 为了示例更容易展示，手动设置较小的值
        column_names=column_names,
        label_name=label_name,
        na_value="?",
        num_epochs=1,
        ignore_errors=True)
    return dataset
train_file_path = FILE_TRAIN
test_file_path = FILE_TEST
train_dataset = get_dataset(train_file_path)
test_dataset = get_dataset(test_file_path)

list(train_dataset.take(1).as_numpy_iterator())
# for i in raw_train_data.take(1):
#     print(i)

[(OrderedDict([('sepal_length',
                array([6.3, 6.7, 6.3, 6.4, 5.2, 5.6, 7.7, 5. , 6.9, 5.6, 4.7, 7.2],
                      dtype=float32)),
               ('sepal_width',
                array([3.3, 3. , 3.4, 3.1, 2.7, 2.5, 3. , 3. , 3.1, 2.7, 3.2, 3. ],
                      dtype=float32)),
               ('petal_length',
                array([4.7, 5.2, 5.6, 5.5, 3.9, 3.9, 6.1, 1.6, 4.9, 4.2, 1.6, 5.8],
                      dtype=float32)),
               ('petal_width',
                array([1.6, 2.3, 2.4, 1.8, 1.4, 1.1, 2.3, 0.2, 1.5, 1.3, 0.2, 1.6],
                      dtype=float32))]),
  array([1, 2, 2, 2, 1, 1, 2, 0, 1, 1, 0, 2])),

特征，标签分割

features, labels = next(iter(train_dataset)) # 第一个批次
print("EXAMPLES: \n", examples, "\n")
print("LABELS: \n", labels)

EXAMPLES: 
 OrderedDict([('120', <tf.Tensor: shape=(12,), dtype=float32, numpy=
array([6.1, 6.2, 5.8, 5.6, 5.8, 6.4, 6.1, 5.7, 5.7, 4.6, 5.2, 6.3],
      dtype=float32)>), ('4', <tf.Tensor: shape=(12,), dtype=float32, numpy=
array([2.8, 2.8, 4. , 2.7, 2.7, 2.8, 2.9, 3.8, 2.8, 3.1, 2.7, 2.3],
      dtype=float32)>), ('setosa', <tf.Tensor: shape=(12,), dtype=float32, numpy=
array([4.7, 4.8, 1.2, 4.2, 4.1, 5.6, 4.7, 1.7, 4.5, 1.5, 3.9, 4.4],
      dtype=float32)>), ('versicolor', <tf.Tensor: shape=(12,), dtype=float32, numpy=
array([1.2, 1.8, 0.2, 1.3, 1. , 2.1, 1.4, 0.3, 1.3, 0.2, 1.4, 1.3],
      dtype=float32)>)]) 

LABELS: 
 tf.Tensor([2 0 0 1 0 2 1 0 0 1 1 0], shape=(12,), dtype=int32)

plt.scatter(features['petal_length'],
            features['sepal_length'],
            c=labels,
            cmap='viridis')

plt.xlabel("Petal length")
plt.ylabel("Sepal length")
plt.show()

请添加图片描述

dataset打包成二维数组

def pack_features_vector(features, labels):
    features = tf.stack(list(features.values()), axis=1)
    return features, labels

train_dataset = train_dataset.map(pack_features_vector)
train_dataset
list(train_dataset.take(1).as_numpy_iterator())

<MapDataset element_spec=(TensorSpec(shape=(None, 4), dtype=tf.float32, name=None), TensorSpec(shape=(None,), dtype=tf.int32, name=None))>

features, labels = next(iter(train_dataset))
print(features)
print(labels)

tf.Tensor(
[[6.5 3.  5.8 2.2]
 [4.6 3.2 1.4 0.2]
 [6.3 2.5 5.  1.9]
 [6.5 3.  5.2 2. ]
 [4.8 3.1 1.6 0.2]
 [5.8 2.7 4.1 1. ]
 [5.  3.  1.6 0.2]
 [5.7 3.  4.2 1.2]
 [5.8 2.7 5.1 1.9]
 [6.  2.9 4.5 1.5]
 [4.8 3.4 1.6 0.2]
 [5.5 3.5 1.3 0.2]], shape=(12, 4), dtype=float32)
 ![请添加图片描述](https://img-blog.csdnimg.cn/d0427ee3c582400ea396f138fc52c800.png?x-oss-process=image/watermark,type_d3F5LXplbmhlaQ,shadow_50,text_Q1NETiBAV2VpeWFuZXI=,size_20,color_FFFFFF,t_70,g_se,x_16)

tf.Tensor([2 0 0 1 0 2 1 0 0 1 1 0], shape=(12,), dtype=int32)

建立模型----三层感知机模型

model = tf.keras.Sequential([
  tf.keras.layers.Dense(10, activation=tf.nn.relu, input_shape=(4,)),  # input shape required
  tf.keras.layers.Dense(10, activation=tf.nn.relu),
  tf.keras.layers.Dense(3)
])

tf.nn.softmax(predictions[:5])

<tf.Tensor: shape=(5, 3), dtype=float32, numpy=
array([[0.34744287, 0.23620045, 0.41635668],
       [0.36335322, 0.21712378, 0.419523  ],
       [0.30681884, 0.23011816, 0.46306297],
       [0.46609837, 0.13207382, 0.40182784],
       [0.28325418, 0.28049824, 0.43624762]], dtype=float32)>

print("Prediction: {}".format(tf.argmax(predictions, axis=1)))
print("    Labels: {}".format(labels))

Prediction: [2 2 2 0 2 2 2 2 2 0 2 2]
    Labels: [1 1 2 0 2 1 2 2 1 0 1 1]

模型训练

损失函数和梯度函数

loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

def loss(model, x, y, training):
    y_ = model(x, training=training)
    return loss_object(y_true=y, y_pred=y_)

Loss test: 1.1089719533920288

def grad(model, inputs, targets):
    with tf.GradientTape() as tape:
        loss_value = loss(model, inputs, targets, training=True)
    return loss_value, tape.gradient(loss_value, model.trainable_variables)

模型过程

## Note: Rerunning this cell uses the same model variables
optimizer = tf.keras.optimizers.SGD(learning_rate=0.01)
# Keep results for plotting
train_loss_results = []
train_accuracy_results = []

num_epochs = 201

for epoch in range(num_epochs):
    epoch_loss_avg = tf.keras.metrics.Mean()
    epoch_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()

  # Training loop - using batches of 32
    for x, y in train_dataset:
    # Optimize the model
        loss_value, grads = grad(model, x, y)
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

        # Track progress
        epoch_loss_avg.update_state(loss_value)  # Add current batch loss
        # Compare predicted label to actual label
        # training=True is needed only if there are layers with different
        # behavior during training versus inference (e.g. Dropout).
        epoch_accuracy.update_state(y, model(x, training=True))

  # End epoch
    train_loss_results.append(epoch_loss_avg.result())
    train_accuracy_results.append(epoch_accuracy.result())

if epoch % 50 == 0:
    print("Epoch {:03d}: Loss: {:.3f}, Accuracy: {:.3%}".format(epoch,
                                                                epoch_loss_avg.result(),
                                                                epoch_accuracy.result()))

Epoch 000: Loss: 0.946, Accuracy: 69.167%
Epoch 050: Loss: 0.283, Accuracy: 93.333%
Epoch 100: Loss: 0.141, Accuracy: 96.667%
Epoch 150: Loss: 0.121, Accuracy: 99.167%
Epoch 200: Loss: 0.091, Accuracy: 97.500%

Acc-epoch曲线

fig, axes = plt.subplots(2, sharex=True, figsize=(12, 8))
fig.suptitle('Training Metrics')

axes[0].set_ylabel("Loss", fontsize=14)
axes[0].plot(train_loss_results)

axes[1].set_ylabel("Accuracy", fontsize=14)
axes[1].set_xlabel("Epoch", fontsize=14)
axes[1].plot(train_accuracy_results)
plt.show()

在这里插入图片描述

验证集评估模型

test_dataset = test_dataset.map(pack_features_vector)

test_accuracy = tf.keras.metrics.Accuracy()

for (x, y) in test_dataset:
  # training=False is needed only if there are layers with different
  # behavior during training versus inference (e.g. Dropout).
    logits = model(x, training=False)
    prediction = tf.argmax(logits, axis=1, output_type=tf.int32)
    test_accuracy(prediction, y)

print("Test set accuracy: {:.3%}".format(test_accuracy.result()))

Test set accuracy: 96.667%

查看下预测值和标签

tf.stack([y,prediction],axis=1)

<tf.Tensor: shape=(6, 2), dtype=int32, numpy=
array([[1, 1],
       [0, 0],
       [1, 1],
       [2, 2],
       [1, 1],
       [1, 1]])>

测试

predict_dataset = tf.convert_to_tensor([
    [5.1, 3.3, 1.7, 0.5,],
    [5.9, 3.0, 4.2, 1.5,],
    [6.9, 3.1, 5.4, 2.1]
])

# training=False is needed only if there are layers with different
# behavior during training versus inference (e.g. Dropout).
predictions = model(predict_dataset, training=False)

for i, logits in enumerate(predictions):
    class_idx = tf.argmax(logits).numpy()
    p = tf.nn.softmax(logits)[class_idx]
    name = class_names[class_idx]
    print("Example {} prediction: {} ({:4.1f}%)".format(i, name, 100*p))

Example 0 prediction: Iris setosa (99.3%)
Example 1 prediction: Iris versicolor (97.9%)
Example 2 prediction: Iris virginica (82.2%)

Weiyaner

关注

0
点赞
踩
1

收藏

觉得还不错? 一键收藏
打赏
0
评论
基于tensorflow的鸢尾花Iris分类实战

导包import osimport six.moves.urllib.request as requestimport tensorflow as tffrom matplotlib import pyplot as plt# Check that we have correct TensorFlow version installedtf_version = tf.__version__print("TensorFlow version: {}".format(tf_version))
复制链接

扫一扫