Пример кода уже разбивает набор данных на наборы обучения и проверки.
И я не думаю, что это имеет какое-либо отношение к заголовку в CSV.
training_targets, training_examples = parse_labels_and_features(mnist_dataframe[:7500])
validation_targets, validation_examples = parse_labels_and_features(mnist_dataframe[7500:10000])
Таким образом, обучающий код находится здесь отдельно.
import pandas as pd
import tensorflow as tf
from tensorflow.python.data import Dataset
import numpy as np
mnist_df = pd.read_csv("https://download.mlcc.google.com/mledu-datasets/mnist_train_small.csv",sep=",",header=None)
mnist_df = mnist_df.head(10000)
dataset = mnist_df[:7500]
labels = dataset[0]
print ( labels.shape )
# DataFrame.loc index ranges are inclusive at both ends.
features = dataset.loc[:, 1:784]
print ( features.shape )
# Scale the data to [0, 1] by dividing out the max value, 255.
features = features / 255
def create_training_input_fn(feature, label, batch_size, num_epochs=None, shuffle=True):
"""A custom input_fn for sending MNIST data to the estimator for training.
Args:
features: The training features.
labels: The training labels.
batch_size: Batch size to use during training.
Returns:
A function that returns batches of training features and labels during
training.
"""
def _input_fn(num_epochs=None, shuffle=True):
# Input pipelines are reset with each call to .train(). To ensure model
# gets a good sampling of data, even when number of steps is small, we
# shuffle all the data before creating the Dataset object
idx = np.random.permutation(feature.index)
raw_features = {"pixels": feature.reindex(idx)}
raw_targets = np.array(label[idx])
ds = Dataset.from_tensor_slices((raw_features, raw_targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data.
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
return _input_fn
my_optimizer = tf.train.AdagradOptimizer(learning_rate=0.03)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
model = tf.estimator.LinearClassifier(feature_columns=set([tf.feature_column.numeric_column('pixels', shape=784)]),
n_classes=10,
optimizer=my_optimizer,
config=tf.estimator.RunConfig(keep_checkpoint_max=1))
model.train(input_fn=create_training_input_fn(features, labels, batch_size=10),steps=1000)
Аналогично, у вас есть функция для подготовки набора проверки для прогнозирования.Вы можете использовать этот шаблон как есть.
Но если вы разбиваете фрейм данных, используя train_test_split
, вы можете попробовать это.
X_train, X_test = train_test_split(mnist_df, test_size=0.2)
Вы должны повторить следующую процедуру для X_test
а также для получения функций проверки и меток.
X_train_labels = X_train[0]
print ( X_train_labels.shape )
# DataFrame.loc index ranges are inclusive at both ends.
X_train_features = X_train.loc[:, 1:784]
print ( X_train_features.shape )
# Scale the data to [0, 1] by dividing out the max value, 255.
X_train_features = X_train_features / 255