Breaking News: Grepper is joining You.com. Read the official announcement!

custom tensorflow model

Innocent Iguana answered on April 25, 2024 Popularity 3/10 Helpfulness 7/10

answer custom tensorflow model

custom tensorflow model

Comment

### NOTE: This uses tensorflow estimator API
import numpy as np

# Define feature columns 
col_1 = tf.feature_column.numeric_column("col_1")
col_2 = tf.feature_column.numeric_column("col_2")

# Define the list of feature columns
feature_list = [col_1, col_2]

# Map the features and labels of input data
def input_fn():
	features = {'col_1':np.array(df['col_1']), 
                'col_2':np.array(df['col_2'])}
	labels = np.array(df["target"])
	return features, labels

# Deep Learning Regression with tensorflow
model = tf.estimator.DNNRegressor(feature_columns=feature_list, hidden_units=[2,2])
model.train(input_fn, steps=1)

# Linear Regression with tensorflow
model = tf.estimator.LinearRegressor(feature_columns=feature_list)
model.train(input_fn, steps=2)

# Deep Learning Classification with tensorflow
model1 = tf.estimator.DNNClassifier(feature_columns=feature_list, hidden_units=[32, 16, 8], n_classes=4)
model.train(input_fn, steps=20)

Popularity 3/10 Helpfulness 7/10 Language python

Source: Grepper

Tags: model python tensorflow

Link to this answer
Share Copy Link

Contributed on Apr 25 2024

Innocent Iguana

0 Answers Avg Quality 2/10

custom tensorflow model

Contents

More Related Answers

custom tensorflow model

Grepper

Documentation

Social

Legal

Contact

Oops, You will need to install Grepper and log-in to perform this action.