ValueError: Input 0 is incompatible with layer lstm_54: expected ndim=3, found ndim=2

[PietroAmin]

First off, make sure to check your support options.

The preferred way to resolve usage related matters is through the docs which are maintained up-to-date with the latest version of Talos.

If you do end up asking for support in a new issue, make sure to follow the below steps carefully.

1) Confirm the below

• [yes ] I have looked for an answer in the Docs
• [yes ] My Python version is 3.5 or higher
• [ yes] I have searched through the issues Issues for a duplicate
• [ yes] I've tested that my Keras model works as a stand-alone

2) Include the output of:

talos.__version__: 0.6.6

3) Explain clearly what you are trying to achieve

4) Explain what you have already tried

I simply have no idea why this error is popping up as if the model is trained without scan it works fine.

5) Provide a code-complete reference

• [yes ] My support question includes an input model
• [yes ] My support question includes a parameter dictionary
• [yes ] My support question includes a Scan() command
• [ ] My support question includes a link to a sample of the data

NOTE: If the data is sensitive and can't be shared, create dummy data that mimics it.

A self-contained Jupyter Notebook, Google Colab, or similar is highly preferred and will speed up helping you with your issue.

---

[github-actions[bot]]

Welcome to Talos community! Thanks so much for creating your first issue :)

[mattou78400]

Hi,

How was the issue fixed? I'm having the same kind of issue with predictig after a scan: scan_object = talos.autom8.AutoScan(task='continuous', max_param_values=3, experiment_name='testing.new') scan_object = scan_object.start(x=x_train, y=self.train_y, x_val = x_val, y_val = self.test_y, round_limit=2, fraction_limit=0.00001) talos.Deploy(scan_object=scan_object, model_name='deploy', metric='mae') [...] loaded_model = talos.Restore('deploy.zip') self.pred = loaded_model .model.predict(x_val) it then throws : Input 0 of layer sequential is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 393]

When the pred Xs are the same as the training_val Xs.