In Tensorflow documentation, it is shown how to tune several hyperparameters but not the learning rate.I have searched how to tune learning rate using HParams dashboard but could not find much. The only example is another question on github but it does not work.Can you please give me some suggestions on this?Should I use a callback function?Or provide different learning rates in hp_optimizer as in the question in github? Or something else?
Thank you,
Related
I am trying to dynamically modify the neural network architecture(e.g, add/delete layer...) and hyperparameter during the training period on Tensorflow.(e.g.,control_func(#layer,#neuron,learning_rate...)) However, I have no idea how to implement it in the code. Could anyone can provide some reference, insight, or tutorial? Thanks a lot!
fellow community!
I have next problem: I want to evaluate my model after each epoch using F1/AUC or other related scores in Keras. I use Tensorflow as backend.
I have searched the internet, but didn't found anything meaningful that would create a picture of a solution.
Can anyone propose something? Do I need to write my custom Sequence generator? Right now I am using ImageDataGenerator to get images from folder
in Google Drive.
Any answers are very appreciated. Thanks in advance!
All of it is in tf.metrics which is aliased also as tf.keras.metrics. It's both in the new 2.0 API and in the 1.x API.
In particular, you will use classes:
AUC
Precision and Recall from wich you can compute the F1 score
I am new to both TensorFlow and also Document Similarity / Topic Modeling therefore I apologize if my questions don't make complete sense.
From my limited understanding, topic modelling is done using algorithms such as LSA,LDA,etc. I have seen code using gensim and LSA but the time to train is very high for the large set of documents I have in mind. Consequently the CPU and RAM resources are very heavy.
Tensorflow doesn't seem to have a native LSA or LDA implementation.
I would appreciate an opinion on :
Would LDA implemented using Tensorflow have a better performance than implemented using gensim?
Could someone tell me of other Tensorflow primitives that I should look at for document similarity rather than LDA?
Once again I am sorry if my questions are too vague and do not cover sufficient information to give a proper response. I am new to this domain and I would appreciate any directions someone could point me to.
Thank you for your time.
Regards,
Jeetu
Problem
Do you have a tutorial for LTSM or RNN time series anomaly detection using deep learning with CNTK? If not, can you make one or suggest a series of simple steps here for us to follow?
I am a software developer and a member of a team investigating using deep learning on time series data we have for anomaly detection. We have not found anything on your python docs that can help us. It seems most of the tutorials are for visual recognition problems and not specific to the problem domain of interest to us.
Using LTSM and RNN in Anomaly Detection
I have found the following
This link references why we are trying to use time series for anomaly detection
This paper convinced us that the first link is a respected approach to the problem in general
This link also outlined the same approach
I look around on CNTK here, but didn't find any similar question and so I hope this question helps other developers in the future.
Additional Notes and Questions
My problem is that I am finding CNTK not that simple to use or as well documented as I had hoped. Frankly, our framework and stack is heavy on .NET and Microsoft technologies. So I repeat the question again for emphasis with a few follow ups:
Do you have any resources you feel you can recommend to developers learning neural networks, deep learning, and so on to help us understand what is going on under the hood with CNTK?
Build 2017 mentions C# is supported by CNTK. Can you please point us in the direction of where the documentation and support is for this?
Most importantly can you please help get us unstuck on trying to do time series anomaly analysis for time series using CNTK?
Thank you very much for time and assistance in reading and asking this question
Thanks for your feedback. Your suggestions help improve the toolkit.
First Bullet
I would suggest that you can start with the CNTK tutorials.
https://github.com/Microsoft/CNTK/tree/master/Tutorials
They are designed from CNTK 101 to 301. Suggest that you work through them. Many of them even though uses image data, the concept and the models are amenable to build solutions with numerical data. 101-103 series are great to understand basics of the train-test-predict workflow.
Second Bullet:
Once you have trained the model (using Python recommended). The model evaluation can be performed using different language bindings, C# being one of them.
https://github.com/Microsoft/CNTK/wiki/CNTK-Evaluation-Overview
Third Bullet
There are different approaches suggested in the papers you have cited. All of them are possible to do in CNTK with some changes to the code in the tutorials.
The key tutorial for you would be CNTK 106, CNTK 105, and CNTK 202
Anomaly as classification: This would involve you label your target value as 1 of N classes, with one of the class being "anomaly". Then you can combine 106 with 202, to classify the prediction
Anomaly as an autoencoder: You can need to study 105 autoencoder. Now instead of a dense network, you could apply the concept for Recurrent networks. Train only on the normal data. Once trained, pass any data through the trained model. The difference between the input and autoencoded version will be small for normal data but the difference will be much larger for anomalies. The 105 tutorial uses images, but you can train these models with any numerical data.
Hope you find these suggestions helpful.
I am a beginner with Tensorflow and machine learning in general.For my project I have to classify urban sound data.
I have extracted mfccs of my sample data and now I want to classify them by using a CNN in Tensorflow. I don't know how many channels I should use and why. Can anyone help me? Thanks.
I was working on a similar project and I found this paper useful with this.
http://karol.piczak.com/papers/Piczak2015-ESC-ConvNet.pdf