keras-io

keras-io copied to clipboard

Example of increasing dropout rate throughout training

2

This can go over the solution of: https://github.com/keras-team/keras/issues/16234

LukeWood

Need example for inference in transformer_asr.py

18

The example in transformer_asr.py is really interesting, but it only shows how to train the model. Can someone give an example of inference is done with the model to get...

ajohnson49

my input of customize dataset is (n, 600, 600, 3), i have tried resize before input to the modell, it works. But i still wonder, how can i input an...

YC0619

I use ctc to train a ASR model, but the result value is ,the below is the result of keras.backend.ctc_decode(pred, input_length=input_len, greedy=True). what happend to my program?the log probability if...

moseshu

Hi, Is the code 'collaborative_filtering_movielens.py' correctly implemented. I have replicated this code for same movie datasets. Seems like the prediction accuracy is close to 10%, while the loss is decreasing....

santhoshgits

Update metric_learning_tf_similarity.py

1

The "Last modified: 2022/02/29" is invalid. I suggest using "2022/02/28" as "Last modified".

tykimos

ValueError Traceback (most recent call last) in 16 17 # Begin training the model. ---> 18 clustering_learner.fit(x=inputs, y=labels, batch_size=512, epochs=50) ~/.local/lib/python3.9/site-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs) 65 except Exception as e: #...

rsinghal04

This issue is about keras' (amazing, if i may add) [tutorial about the MelGAN audio synthesis network](https://keras.io/examples/audio/melgan_spectrogram_inversion/). In [line 387 and the following](https://github.com/keras-team/keras-io/blob/master/examples/audio/melgan_spectrogram_inversion.py) we define the generator's loss.  Why...

basbrs

How to replace preprocessing.text_dataset_from_directory with the numpy array?

1

[Code](https://github.com/keras-team/keras-io/blob/master/examples/nlp/text_classification_from_scratch.py) how to input a `string` instead of `preprocessing.text_dataset_from_directory`? I tried using strings from python and the numpy array - but alas, no luck. I tried to figure out what...

Pro100rus32

So I follow this tutorial https://github.com/keras-team/keras-io/blob/master/examples/audio/transformer_asr.py My question is how can I load the model and then predict it, like `model.predict(x)` where x is an audio file

BernardoOlisan