TensorFlow2.0:如何为numpy矩阵输入创建feature_columns
TensorFlow2.0:如何为numpy矩阵输入创建feature_columns
提问于 2021-02-27 07:46:47
我知道如何在Tensorflow 1.x (link here)中做到这一点。
但是对于TensorFlow2.0，如何为numpy矩阵创建feature_columns？
import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import tensorflow as tf
X = iris['data']
y = iris['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
ds_train = tf.data.Dataset.from_tensor_slices((X_train, y_train))
ds_test = tf.data.Dataset.from_tensor_slices((X_test, y_test))
model = CustomModel(feature_columns, num_classes=y_train.shape[1])
model.compile()
model.compile('adam', loss='categorical_crossentropy', metrics='accuracy')根据CustomModel的文档字符串，请求feature_columns: The Tensorflow feature columns for the dataset.
我使用sklearn中的虹膜数据集作为示例。我知道tensorflow2.0有一个虹膜数据集。如果我使用这个数据集，我就不会有这个问题。但这不是重点。我想知道如何创建特征列以馈送到tensorflow模型中，因为我已经有了numpy矩阵。
回答 1
Stack Overflow用户
发布于 2021-03-21 10:58:42
TensorFlow documentation提供了我们通常需要的所有示例。如果您想创建增强的树模型，还有另一个article
我使用这个数据集只是为了说明如何使用Pandas dataframe来创建tf.data
import tensorflow as tf
import pandas as pd
from sklearn.model_selection import train_test_split
seaflow_train = pd.read_csv(
"~/PycharmProjects/TensorFlow2/seaflow_21min.csv")
print(seaflow_train.head())
print(seaflow_train.columns)
seaflow_train['target'] = seaflow_train['pop']
seaflow_train = seaflow_train.drop(columns=['file_id', 'cell_id', 'time', 'd1', 'd2'])
train, test = train_test_split(seaflow_train, test_size=0.2)
train, val = train_test_split(train, test_size=0.2)
# A utility method to create a tf.data dataset from a Pandas Dataframe
def df_to_dataset(dataframe, shuffle=True, batch_size=32):
dataframe = dataframe.copy()
labels = dataframe.pop('target')
ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
if shuffle:
ds = ds.shuffle(buffer_size=len(dataframe))
ds = ds.batch(batch_size)
return ds
batch_size = 5 # A small batch sized is used for demonstration purposes
train_ds = df_to_dataset(train, batch_size=batch_size)
val_ds = df_to_dataset(val, shuffle=False, batch_size=batch_size)
test_ds = df_to_dataset(test, shuffle=False, batch_size=batch_size)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/66394174
复制相关文章
相似问题
腾讯云开发者
Copyright © 2013 - 2026 Tencent Cloud. All Rights Reserved. 腾讯云 版权所有
深圳市腾讯计算机系统有限公司 ICP备案/许可证号：粤B2-20090059 
粤公网安备44030502008569号
腾讯云计算（北京）有限责任公司 京ICP证150476号 | 京ICP备11018762号