ds-academy / tadgan Goto Github PK
View Code? Open in Web Editor NEWTadGAN for T.F 2.0
TadGAN for T.F 2.0
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?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.