Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tf.keras and tfp.tfp.layers. are not compatible #1829

Open
devspatron opened this issue Aug 6, 2024 · 1 comment
Open

tf.keras and tfp.tfp.layers. are not compatible #1829

devspatron opened this issue Aug 6, 2024 · 1 comment

Comments

@devspatron
Copy link

hello fellow developers, it appears that the tf.keras and tfp.tfp.layers. are not compatible
i have this code="
**num_inducing_points = 40
model = tf.keras.Sequential([
tf.keras.layers.InputLayer(input_shape=[1], dtype=x.dtype),
tf.keras.layers.Dense(1, kernel_initializer='ones', use_bias=False),
tfp.layers.VariationalGaussianProcess(
num_inducing_points=num_inducing_points,
kernel_provider=RBFKernelFn(dtype=x.dtype),
event_shape=[1],
inducing_index_points_initializer=tf.constant_initializer(
np.linspace(*x_range, num=num_inducing_points,
dtype=x.dtype)[..., np.newaxis]),
unconstrained_observation_noise_variance_initializer=(
tf.constant_initializer(
np.log(np.expm1(1.)).astype(x.dtype))),
),
])

//Do inference.
batch_size = 32
loss = lambda y, rv_y: rv_y.variational_loss(
y, kl_weight=np.array(batch_size, x.dtype) / x.shape[0])
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.01), loss=loss)
model.fit(x, y, batch_size=batch_size, epochs=1000, verbose=False)

//Make predictions.
yhats = [model(x_tst) for _ in range(100)]**
"

and i get the following
error output=
"**:7: UserWarning: layer.add_variable is deprecated and will be removed in a future version. Please use the layer.add_weight() method instead.
self._amplitude = self.add_variable(
:12: UserWarning: layer.add_variable is deprecated and will be removed in a future version. Please use the layer.add_weight() method instead.
self._length_scale = self.add_variable(


ValueError Traceback (most recent call last)

in <cell line: 2>()
1 num_inducing_points = 40
----> 2 model = tf.keras.Sequential([
3 tf.keras.layers.InputLayer(input_shape=[1], dtype=x.dtype),
4 tf.keras.layers.Dense(1, kernel_initializer='ones', use_bias=False),
5 tfp.layers.VariationalGaussianProcess(

1 frames

/usr/local/lib/python3.10/dist-packages/keras/src/models/sequential.py in add(self, layer, rebuild)
93 layer = origin_layer
94 if not isinstance(layer, Layer):
---> 95 raise ValueError(
96 "Only instances of keras.Layer can be "
97 f"added to a Sequential model. Received: {layer} "

ValueError: Only instances of keras.Layer can be added to a Sequential model. Received: <tensorflow_probability.python.layers.distribution_layer.VariationalGaussianProcess object at 0x7acd5e77fc70> (of type <class 'tensorflow_probability.python.layers.distribution_layer.VariationalGaussianProcess'>)**"

@UnVerano
Copy link

UnVerano commented Sep 6, 2024

ME either!! It was ok when i ran in August, but now it dosen't. Even though it was the same.. I got the same error w/ u

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants