一個簡單的Tensorflow圖片分類器，資料集是iris資料集。兩個指令碼premade_estimator.py分類器指令碼、iris_data.py處理資料的指令碼。

#iris_data.py 下載資料集，並且處理資料集


import pandas as pd
import tensorflow as tf

# iris資料集的下載URL
TRAIN_URL = "http://download.tensorflow.org/data/iris_training.csv"
TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"
 


# iris資料集5個列的命名規則
CSV_COLUMN_NAMES = ['SepalLength', 'SepalWidth',
                    'PetalLength', 'PetalWidth', 'Species']

#花朵分成三個類
SPECIES = ['Setosa', 'Versicolor', 'Virginica']

# 下載資料集返回資料集的檔案所在路徑，預設~/.keras/datasets目錄下
def maybe_download():
    train_path = tf.keras.utils.get_file(TRAIN_URL.split('/'
 
)[-1], TRAIN_URL)
    # print(train_path)
    test_path = tf.keras.utils.get_file(TEST_URL.split('/')[-1], TEST_URL)
    # print(test_path)
    return train_path, test_path

# 讀取iris資料集的csv檔案，並且製作（X,Y）形式的訓練集和驗證集
def load_data(y_name='Species'):
    """Returns the iris dataset as (train_x, train_y), (test_x, test_y)."""
 

    train_path, test_path = maybe_download()

    train = pd.read_csv(train_path, names=CSV_COLUMN_NAMES, header=0)
    train_x, train_y = train, train.pop(y_name)

    test = pd.read_csv(test_path, names=CSV_COLUMN_NAMES, header=0)
    test_x, test_y = test, test.pop(y_name)

    return (train_x, train_y), (test_x, test_y)


# 訓練集輸入
def train_input_fn(features, labels, batch_size):
    """An input function for training"""
    # Convert the inputs to a Dataset.
    dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))

    # Shuffle, repeat, and batch the examples.
    dataset = dataset.shuffle(1000).repeat().batch(batch_size)

    # Return the dataset.
    return dataset

# 驗證集輸入
def eval_input_fn(features, labels, batch_size):
    """An input function for evaluation or prediction"""
    features=dict(features)
    if labels is None:
        # No labels, use only features.
        inputs = features
    else:
        inputs = (features, labels)

    # Convert the inputs to a Dataset.
    dataset = tf.data.Dataset.from_tensor_slices(inputs)

    # Batch the examples
    assert batch_size is not None, "batch_size must not be None"
    dataset = dataset.batch(batch_size)

    # Return the dataset.
    return dataset


# The remainder of this file contains a simple example of a csv parser,
#     implemented using a the `Dataset` class.

# `tf.parse_csv` sets the types of the outputs to match the examples given in
#     the `record_defaults` argument.
CSV_TYPES = [[0.0], [0.0], [0.0], [0.0], [0]]

def _parse_line(line):
    # Decode the line into its fields
    fields = tf.decode_csv(line, record_defaults=CSV_TYPES)

    # Pack the result into a dictionary
    features = dict(zip(CSV_COLUMN_NAMES, fields))

    # Separate the label from the features
    label = features.pop('Species')

    return features, label


def csv_input_fn(csv_path, batch_size):
    # Create a dataset containing the text lines.
    dataset = tf.data.TextLineDataset(csv_path).skip(1)

    # Parse each line.
    dataset = dataset.map(_parse_line)

    # Shuffle, repeat, and batch the examples.
    dataset = dataset.shuffle(1000).repeat().batch(batch_size)

    # Return the dataset.
    return dataset

Premade_estimator.py指令碼分析如下

"""An Example of a DNNClassifier for the Iris dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import tensorflow as tf

import iris_data


parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
                    help='number of training steps')

def main(argv):
    args = parser.parse_args(argv[1:])

    # Fetch the data
    (train_x, train_y), (test_x, test_y) = iris_data.load_data()

    # Feature columns describe how to use the input.
    my_feature_columns = []
    for key in train_x.keys():
        my_feature_columns.append(tf.feature_column.numeric_column(key=key))

    # Build 2 hidden layer DNN with 10, 10 units respectively.
    classifier = tf.estimator.DNNClassifier(
        feature_columns=my_feature_columns,
        # Two hidden layers of 10 nodes each.
        hidden_units=[10, 10],
        # The model must choose between 3 classes.
        n_classes=3)

    # Train the Model.
    classifier.train(
        input_fn=lambda:iris_data.train_input_fn(train_x, train_y,
                                                 args.batch_size),
        steps=args.train_steps)

    # Evaluate the model.
    eval_result = classifier.evaluate(
        input_fn=lambda:iris_data.eval_input_fn(test_x, test_y,
                                                args.batch_size))

    print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))

    # Generate predictions from the model
    expected = ['Setosa', 'Versicolor', 'Virginica']
    predict_x = {
        'SepalLength': [5.1, 5.9, 6.9],
        'SepalWidth': [3.3, 3.0, 3.1],
        'PetalLength': [1.7, 4.2, 5.4],
        'PetalWidth': [0.5, 1.5, 2.1],
    }

    predictions = classifier.predict(
        input_fn=lambda:iris_data.eval_input_fn(predict_x,
                                                labels=None,
                                                batch_size=args.batch_size))

    template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')

    for pred_dict, expec in zip(predictions, expected):
        class_id = pred_dict['class_ids'][0]
        probability = pred_dict['probabilities'][class_id]

        print(template.format(iris_data.SPECIES[class_id],
                              100 * probability, expec))


if __name__ == '__main__':
    tf.logging.set_verbosity(tf.logging.INFO)
    tf.app.run(main)

執行premade_estimator.py指令碼，可以得到如下的結果

可以看出訓練出的模型對predict_x中的三種影象做出了很好的分類。