7fantasysz / mscred Goto Github PK
View Code? Open in Web Editor NEWMulti-Scale Convolutional Recurrent Encoder-Decoder
Multi-Scale Convolutional Recurrent Encoder-Decoder
problem:
I spend a few days and I run this but it doesn't work. And it seems that the necessary files are missing. Documents and instructions are needed .
environment:
windows 10 X64
python 3.6
tensorflow 1.12.0
maybe help:
Namespace(gap_time=10, max_time=20000, min_time=0, raw_data_path='../data/synthetic_data_with_anomaly-s-1.csv', save_data_path='../data/', step_max=5, test_end_point=20000, test_start_point=8000, train_end_point=8000, train_start_point=0, ts_type='node', win_size=[10, 30, 60])
generating signature with window 10...
generating signature with window 30...
generating signature with window 60...
matrix generation finish!
Traceback (most recent call last):
generating train/test data samples...
File "C:/******/MSCRED-master/code/matrix_generator.py", line 283, in <module>
generate_train_test_data()
File "C:/******/MSCRED-master/code/matrix_generator.py", line 245, in generate_train_test_data
data_all.append(np.load(path_temp))
File "E:\******\lib\site-packages\numpy\lib\npyio.py", line 384, in load
fid = open(file, "rb")
FileNotFoundError: [Errno 2] No such file or directory: '/home/zhaos/ts_data_csv2/signature_matrix/matrix_win_10total_count.npy'
Process finished with exit code 1
How can I run this project on Windows?
Please help me.
when run py file ,get error:
Traceback (most recent call last):
File "matrix_generator.py", line 185, in
generate_train_test_data()
File "matrix_generator.py", line 149, in generate_train_test_data
data_all.append(np.load(path_temp))
File "D:\anaconda3\lib\site-packages\numpy\lib\npyio.py", line 428, in load
fid = open(os_fspath(file), "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'd:/ts_data_csv2/signature_matrix/matrix_win_10total_count.npy'
how to get this file?
What is the meaning of the variable gap_time
in utils.py
?
It seems that 'gap time between each segment' does not fit the use of the variable as:
In line 45 of file generation _signature_matrice.py
, u directly slice data from raw_data
without considering the gap variable,
which means that you only use a small part of the data.
Am I missing something or is this a bug?
Can anyone reproduce the result from paper? I am really curious.
I am learning your codes, and wanna do some progress. If u have more TS anomaly data, could u share to me ?
From what I see in the data of this repository the data have the following shape :
(number of time series * lenght of time series)
However a multivatiate time serie should have the following shape :
(number of time series * lenght of time series * number of features)
Is it me who have missed something or a problem in the data?
Hello, could you tell me this file's name in your github project?
I can't find this file and understand the format of the input data.
Thank you!
In 'matrix_generator.py'...
It has indentationError in line 188, because it has wrote by mixing tab and space.
Can you replace all the space to tab?
in 'MSCRED_TF.py'...
The command for calling pandas has blocked by commented out.
Can you remove '#' in line 4?
Can you add a license to this repo?
Some thought about a license:
Stack Excahnge
Chose a License
No module named 'pytest'
where is the 'pytest'
In the MSCRED_TF file various Tensorflow versions are used.
It is not possible to get the program worked.
With the use of tensorflow v1 the placeholder attribute is available, but tf.contrib can not be used.
In Tensorflow 2 the placeholder attribute is not supported.
Does anyone solved this problem?
Hi,
Firstly very nice paper and I quite like the idea, really like to apply it to other areas. Thus Im hoping that you guys are still monitoring this repo and open for discussion.
Although I have a pretty straight forward question about the way the model was used and trained:
In Figure-2 in the paper and in the code, more specifically:
loss = tf.reduce_mean(tf.square(data_input[-1] - deconv_out))
It seems that you guys are using the tensor in the last time step of the input as the model's output tensor?
Maybe I have missed something obvious, but doesn't that simply imply that the inputs contains complete information of the output, i.e. the model can directly "see" the output in the input? Which means that by "selecting the last tensor in input" (like by setting weights for those input images to 1 and rest 0), we get a perfect estimator?
So my point is when reconstruct something shouldnt the input contain a very lossy or at least an "incomplete info version of the output", instead of containing complete information of what its suppose to reconstruct?
Im doing experiments with random walks on my own implementation of the network, and by using the last step of input as the model's output, I was still able to get very small losses ("reconstructed perfectly"). So Im suspecting that its exactly what the model is doing, i.e. by selecting one step of input as output.
In that case, my guess about why it still worked is, by "half training the model" the trainer were able to adjust the weights for the most common sample patterns, but the learning rate is not fast enough to make the model an simple "input selecting model" yet. However if you would have let the model training to converge, then this ability would be lost since the model will end up "selecting" input from inputs.
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.