Models: how to use tf.feature_column with tf.keras.Model

[wendongqu]

Please go to Stack Overflow for help and support:

http://stackoverflow.com/questions/tagged/tensorflow

Also, please understand that many of the models included in this repository are experimental and research-style code. If you open a GitHub issue, here is our policy:

1. It must be a bug, a feature request, or a significant problem with documentation (for small docs fixes please send a PR instead).
2. The form below must be filled out.

Here's why we have that policy: TensorFlow developers respond to issues. We want to focus on work that benefits the whole community, e.g., fixing bugs and adding features. Support only helps individuals. GitHub also notifies thousands of people when issues are filed. We want them to see you communicating an interesting problem, rather than being redirected to Stack Overflow.

---

System information

• What is the top-level directory of the model you are using:
• Have I written custom code (as opposed to using a stock example script provided in TensorFlow):
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
• TensorFlow installed from (source or binary):
• TensorFlow version (use command below):
• Bazel version (if compiling from source):
• CUDA/cuDNN version:
• GPU model and memory:
• Exact command to reproduce:

You can collect some of this information using our environment capture script:

https://github.com/tensorflow/tensorflow/tree/master/tools/tf_env_collect.sh

You can obtain the TensorFlow version with

python -c "import tensorflow as tf; print(tf.GIT_VERSION, tf.VERSION)"

Describe the problem

Describe the problem clearly here. Be sure to convey here why it's a bug in TensorFlow or a feature request.

Source code / logs

Include any logs or source code that would be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached. Try to provide a reproducible test case that is the bare minimum necessary to generate the problem.

[wendongqu]

there is a nice example in https://www.tensorflow.org/alpha/tutorials/keras/feature_columns
on how to use tf.feature_column with tf.keras. But that model is using Sequential

model = tf.keras.Sequential([
feature_layer,
layers.Dense(128, activation='relu'),
layers.Dense(128, activation='relu'),
layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])

model.fit(train_ds,
validation_data=val_ds,
epochs=5)

How would you do it with tf.kears.Model?
Ideally, I would like to have

ipt=tf.keras.layers.Input(?? not sure what I should put in here if I want to use densefeature next?)
x=tf.keras.layers.DenseFeatures(feature_columns)(ipt)
x=tf.keras.layers.Dense(1)(x)

model=tf.kears.Model(input=ipt, output=x)

How can you make this work?

thank you!

[littlebeandog]

there is a nice example in https://www.tensorflow.org/alpha/tutorials/keras/feature_columns
on how to use tf.feature_column with tf.keras. But that model is using Sequential

model = tf.keras.Sequential([
feature_layer,
layers.Dense(128, activation='relu'),
layers.Dense(128, activation='relu'),
layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])

model.fit(train_ds,
validation_data=val_ds,
epochs=5)

How would you do it with tf.kears.Model?
Ideally, I would like to have

ipt=tf.keras.layers.Input(?? not sure what I should put in here if I want to use densefeature next?)
x=tf.keras.layers.DenseFeatures(feature_columns)(ipt)
x=tf.keras.layers.Dense(1)(x)

model=tf.kears.Model(input=ipt, output=x)

How can you make this work?

thank you!

Do u figure out how to get this work? thx

[1007530194]

Feature Columns and the keras functional API https://blog.csdn.net/n1007530194/article/details/104043984

[ravikyram]

@wendongqu

Is this still an issue.Please, close this thread if your issue was resolved. Thanks!

[ravikyram]

Automatically closing due to lack of recent activity. Please update the issue when new information becomes available, and we will reopen the issue. Thanks!