# QNode inside Keras layer
**URL:** https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335
**Category:** PennyLane Help
**Created:** [February 7, 2020, 4:57pm UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335 "2020-02-07T16:57:17Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@Matthias\_Rosenkranz](https://discuss.pennylane.ai/u/Matthias_Rosenkranz)
#### Post date: [February 7, 2020, 4:57pm UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/1 "2020-02-07T16:57:17Z")
Hi,
I’ve recently started using pennylane. Thanks for the great tool!
I am trying (unsuccessfully) to build a custom Keras layer in TensorFlow 2 that includes a QNode. The goal is to use QNodes in a “standard” TensorFlow 2 workflow, i.e. define a Keras model, compile and fit. The Keras model should first process input data via a classical NN, then feed it into the parameters of a quantum circuit (all inside the model).
My first attempt failed due to `AttributeError: 'Tensor' object has no attribute 'numpy'`, which seems to be related to pennylane assuming eager mode but Keras assuming that layers can be both executed as a graph and in eager.
Then I tried using `dynamic=True` in the layer init to tell Keras that the layer only works with eager, but this fails with `NotImplementedError:` in Keras.
My attempts are on Colab:
[https://colab.research.google.com/drive/1OFxeEG2RSXyoX56lnhL7h7Pj4MzYFDCC](https://colab.research.google.com/drive/1OFxeEG2RSXyoX56lnhL7h7Pj4MzYFDCC)
Would you mind having a look? I am not sure if I am doing something wrong or if my use case is just not supported.
Many thanks,
Matthias
---
### Author:  [@josh](https://discuss.pennylane.ai/u/josh)
#### Post date: [February 8, 2020, 2:36am UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/2 "2020-02-08T02:36:04Z")
Hi @Matthias_Rosenkranz! You’re right that PennyLane only currently works with TensorFlow eager (not autograph), so `dynamic=True` is currently required when using Keras.
I haven’t used PennyLane with Keras personally, however I can link you a few resources that have:
- [https://towardsdatascience.com/classifying-documents-with-quantum-enhanced-transfer-learning-8ee6d04f3ccd](https://towardsdatascience.com/classifying-documents-with-quantum-enhanced-transfer-learning-8ee6d04f3ccd)
- [https://github.com/rdisipio/qnlp](https://github.com/rdisipio/qnlp)
- One of our researchers, @Tom_Bromley, has also used Keras with PennyLane: [https://github.com/XanaduAI/qml/issues/28#issuecomment-574889614](https://github.com/XanaduAI/qml/issues/28#issuecomment-574889614)
On our [tutorials page](https://pennylane.ai/qml/implementations.html), we have quite a few tutorials using PyTorch and TensorFlow directly, but none using Keras so far, this would be a great addition if you wanted to add a demonstration once your code is working!
---
### Author:  [@josh](https://discuss.pennylane.ai/u/josh)
#### Post date: [February 8, 2020, 2:43am UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/3 "2020-02-08T02:43:02Z")
Having a look at @Tom_Bromley’s code, I note that the error message in your colab notebook disappears if you add a `compute_output_shape` method:
```python
class QuantumLayer(tf.keras.layers.Layer):
def __init__ (self, num_outputs, qnode, **kwargs):
super(QuantumLayer, self). __init__ (**kwargs)
self.num_outputs = num_outputs
self.qnode = qnode
def call(self, inputs):
outputs = []
for input in inputs:
outputs.append(self.qnode(input))
return tf.reshape(outputs, shape=(inputs.shape[0], self.num_outputs))
def compute_output_shape(self, input_shape):
return input_shape
```
I’m not too familiar with Keras, but perhaps this needs to always be defined if `dynamic=True`.
---
### Author:  [@Matthias\_Rosenkranz](https://discuss.pennylane.ai/u/Matthias_Rosenkranz)
#### Post date: [February 10, 2020, 8:08am UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/4 "2020-02-10T08:08:03Z")
Thanks @josh! Defining `compute_output_shape` made it work.
---
### Author:  [@Matthias\_Rosenkranz](https://discuss.pennylane.ai/u/Matthias_Rosenkranz)
#### Post date: [February 10, 2020, 11:59am UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/5 "2020-02-10T11:59:33Z")
For reference, here is a working Colab including the Keras-style training via `compile` and `fit`. It’s not a very useful model in itself as it just fits a classical NN to output a parameter for `R_y` that flips the initial |0\rangle state.
[https://colab.research.google.com/drive/1gKcSyiZ4pHuA1UEXhCz-C5YLhbn1Bho9](https://colab.research.google.com/drive/1gKcSyiZ4pHuA1UEXhCz-C5YLhbn1Bho9)
Btw, also works with the newly released pennylane 0.8 :).
---
### Author:  [@Tom\_Bromley](https://discuss.pennylane.ai/u/Tom_Bromley)
#### Post date: [May 19, 2020, 8:37pm UTC](https://discuss.pennylane.ai/t/qnode-inside-keras-layer/335/6 "2020-05-19T20:37:53Z")
Hi @Matthias_Rosenkranz,
We have now added a new [KerasLayer](https://pennylane.readthedocs.io/en/latest/code/api/pennylane.qnn.KerasLayer.html) feature to PennyLane that converts QNodes to a Keras Layer. This should make it easy to interface more with other elements of Keras.
You can access this feature by installing the latest version of PennyLane:
```python
pip install pennylane --upgrade
```