AttributeError: 'Model' object has no attribute '_standardize_user_data' with nightly build of tensorflow 2.2. about keract

[leoffx]

@liuxingbaoyu fix worked for me! thanks!

[philipperemy]

@liuxingbaoyu update to the latest tensorflow and tell me if it solves the issue.

[liuxingbaoyu]

@philipperemy Still exists, I am using tf-nightly-gpu 2.2.0-dev20200418.

[philipperemy]

@liuxingbaoyu I found why. You're using the nightly version and it seems that this function was removed in the 2.2+ version. Currently, when you pip install tensorflow, it fetches the 2.1.0 and it works with this version (which is the latest version).

With pip install tf-nightly it fails:

Traceback (most recent call last):
  File "vgg16.py", line 38, in <module>
    activations = keract.get_activations(model, image)
  File "/Users/premy/PycharmProjects/keract/keract/keract.py", line 153, in get_activations
    activations = _evaluate(model, layer_outputs, x, y=None, auto_compile=auto_compile)
  File "/Users/premy/PycharmProjects/keract/keract/keract.py", line 47, in _evaluate
    return eval_fn(model._feed_inputs)
  File "/Users/premy/PycharmProjects/keract/keract/keract.py", line 42, in eval_fn
    return K.function(k_inputs, nodes_to_evaluate)(model._standardize_user_data(x, y))
AttributeError: 'Model' object has no attribute '_standardize_user_data'

I have no clear idea how to fix it.

Try to use TF 2.1.0 for now. When it becomes official, I'll check more in depth.

[liuxingbaoyu]

@philipperemy
This seems to work.

outputs = [
    layer.output for layer in model.layers
]

activations_model = tf.keras.models.Model(model.inputs, outputs=outputs)
activations_model.compile(optimizer='adam', loss='categorical_crossentropy')
activations = activations_model.predict(np.array(sample[0][:1]))

m={}

for i in range(len(activations)):
    m[model.layers[i].name]=activations[i]

keract.display_activations(m)

Quoted from: https://www.sicara.ai/blog/2019-08-28-interpretability-deep-learning-tensorflow

[philipperemy]

@liuxingbaoyu cool thanks for sharing!

[liuxingbaoyu]

@philipperemy Glad to help you!

[theowoo]

@philipperemy

Try to use TF 2.1.0 for now. When it becomes official, I'll check more in depth.

pip install tensorflow now fetches the 2.2.0 and the error described above persists.

[sixsamuraisoldier]

To add to @theowoo I'm getting the same issue

[philipperemy]

@theowoo @sixsamuraisoldier I've added a constraint to use 2.1.0 at most for now.
I'll have to look more into it when I have time.