ds-academy / tadgan Goto Github PK

Hi, I trained the models in Tensorflow 2.6.0 with my own dataset, and I'm trying to use them to predict time series and find anomalies, which is the common use of the library. Where can I find the piece of code to do this? Can someone tell me how to execute time series prediction with the trained models in TensorFlow 2.6.0?

What is your environment, can you give a requirement.txt file?

Hi, Im a Korean too, but writing an issue in English.

When I ran your code in google colab, I got the error as following;

ValueError Traceback (most recent call last)
in ()
28 x = minibatch[j * batch_size: (j + 1) * batch_size]
29 z = np.random.normal(size=(batch_size, latent_dim, 1))
---> 30 epoch_cx_loss.append(critic_x_train_on_batch(x, z, valid, fake, delta))
...

ValueError: in user code:

<ipython-input-26-44815e824161>:9 critic_x_train_on_batch  *
    pred = critic_x(interpolated, training=True)

...

ValueError: Layer model_2 expects 1 input(s), but it received 2 input tensors. Inputs received: [<tf.Tensor 'model_4/Cast:0' shape=(64, 100, 1) dtype=float32>, <tf.Tensor 'model_4/model_1/sequential_1/activation/Tanh:0' shape=(64, 100, 1) dtype=float32>]

It tells me your model has to input only one but received 2 inputs.
When I googled this issue then I found
https://stackoverflow.com/questions/61586981/valueerror-layer-sequential-20-expects-1-inputs-but-it-received-2-input-tensor

But, I can't find the similar code
"it helped me when I changed: validation_data=[X_val, y_val] into validation_data=(X_val, y_val)" in your code, or models.

Can you help me?