catch-22: CAnonical Time-series CHaracteristics

Related tags

Deep Learningcatch22
Overview

catch22 - CAnonical Time-series CHaracteristics

DOI

About

catch22 is a collection of 22 time-series features coded in C that can be run from Python, R, Matlab, and Julia. The catch22 features are a high-performing subset of the over 7000 features in hctsa.

Features were selected based on their classification performance across a collection of 93 real-world time-series classification problems, as described in our open-access paper:

But what do the features do? You can learn more about what each feature does, with visualizations of how the features behave on real data, here.

The computational pipeline used to generate the catch22 feature set is in the op_importance repository.

For catch22-related information and resources, including a list of publications using catch22, see the catch22 wiki.

Summary of the performance of the catch22 feature set across 93 classification problems, and a comparison to the hctsa feature set (cf. Fig. 4 from our paper):

Installation: Python, R, Matlab, Julia, and compiled C

The fast, C-coded functions in this repository can be used in Python, Matlab, and R following the detailed installation instructions on the wiki.

There is also a native R version, downloadable from CRAN, Rcatch22.

And Julia users can use this Julia package to evaluate the catch22 feature set.

Usage

  • See language-specific usage information in the wiki.
  • Important Note: catch22 features only evaluate dynamical properties of time series and do not respond to basic differences in the location (e.g., mean) or spread (e.g., variance).
    • If you think features of the raw distribution may be important for your application, we suggest you add them (in the simplest case, two additional features: the mean and standard deviation) to this feature set.
  • Note that time series are z-scored internally which means e.g., constant time series will lead to NaN outputs.
Comments
  • Why catch22-0.2.0 got deleted from pypi

    Why catch22-0.2.0 got deleted from pypi

    Ideally, the version should be updated or can be made deprecated. But should not be removed from the repository(PyPi). Can you please upload them back with some new versions tags ?

    opened by cahuja1992 5
  • Anaconda Python 3 pip install not working

    Anaconda Python 3 pip install not working

    I tried pip install catch22 and got a long error log. These are the last few lines:

        C/SP_Summaries.c:161:9: error: ‘for’ loop initial declarations are only allowed in C99 mode
                 for(int i = 0; i < nWelch; i ++){
                 ^
        C/SP_Summaries.c:173:9: error: ‘for’ loop initial declarations are only allowed in C99 mode
                 for(int i=0; i<nWelch/5; i++){
                 ^
        error: command 'gcc' failed with exit status 1
        ----------------------------------------
    ERROR: Command errored out with exit status 1: /home/username/anaconda3/bin/python -u -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-kiwf2hln/catch22/setup.py'"'"'; __file__='"'"'/tmp/pip-install-kiwf2hln/catch22/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' install --record /tmp/pip-record-jtj01ddj/install-record.txt --single-version-externally-managed --compile --install-headers /home/username/anaconda3/include/python3.7m/catch22 Check the logs for full command output.
    

    System: Anaconda3, CentOS 7

    Any ideas?

    opened by chanshing 4
  • Generating a shared library for the C implementation (and using that to build pycatch22 etc.)

    Generating a shared library for the C implementation (and using that to build pycatch22 etc.)

    Hello!

    We package and maintain catch22 for Fedora Linux. Now that pycatch22 has been split into its own repo and bundles the C sources, we were wondering if:

    • it would make sense to compile the C sources from here and provide catch22 as a shared library (libcatch22.so.0 types on Linux)
    • use the shared library to link against when building pycatch22 etc.

    The advantage of this is that we won't need to bundle catch22 in pycatch22, and that catch22 is provided as a library for people using C to use.

    @musicinmybrain has created a pull request that generates the shared library (by adding a Makefile and so on) here. The main question here, as you'll see from that pull request, is whether you (upstream) intend to provide it as a C library, and if you do, would you be committing to ABI/shared object versioning etc. to notify users of changes and so on?

    Link to the libtool documentation on versioning: https://www.gnu.org/software/libtool/manual/html_node/Versioning.html#Versioning

    opened by sanjayankur31 3
  • Modified CO_f1ecac feature to use interpolation

    Modified CO_f1ecac feature to use interpolation

    I've modified the CO_f1ecac feature to use interpolation, making it a double (and equivalent to the HCTSA function). See HCTSA's CO_AutoCorr.m and BF_PointOfCrossing.m

    opened by olivercliff 3
  • WIP: catch24 integration

    WIP: catch24 integration

    Adds new .c and .h files for 2 new functions: DN_Mean and DN_Spread_Std which represent the mean and standard deviation, respectively. Adds a boolean argument to core function calls where users can specify if they want to compute catch24 or just catch22. Need to run tests to check everything is working properly, but I have made changes to C code, and R and Python wrappers. @benfulcher changes will need to be made to the MATLAB wrapper too, right?

    I'll remove the drafting tag once I have worked through unit tests, but either of you can feel free to run the additions and check they work if you have time.

    enhancement 
    opened by hendersontrent 3
  • Memory leaks fix

    Memory leaks fix

    Hi,

    First of all, thanks for this great package!

    I noticed that when doing a lot of calls to catch22.catch22_all(data), the memory consumption of grows. This pull request frees C arrays in C/CO_AutoCorr.c, C/helper_functions.c and wrap_Python/catch22_wrap_P3.c. With these changes, the memory consumption is stable. You can test this for yourself by running the following code before and after applying the changes that I am proposing.

    import catch22
    import numpy as np
    from memory_profiler import profile
    
    @profile
    def catch22_all(signal):
        catch22.catch22_all(signal)
        
    for i in range(10000):
        signal = np.random.randn(1000)
        catch22_all(signal)
    
    opened by Olivier-tl 3
  • Correction in CO_Histogram_AMI_even_2_5 implementation

    Correction in CO_Histogram_AMI_even_2_5 implementation

    Referring to this code snippet in CO_AutoCorr.c

    #define tau 2
    #define numBins 5
    
    double CO_HistogramAMI_even_2_5(const double y[], const int size)
    

    Why tau is 2 and numBins is 5? Shouldn't it be vice-versa according to the implementation of hctsa feature

    opened by imraniac 3
  • Error installing R package on Windows

    Error installing R package on Windows

    Hi,

    I have problem to install your package from R...following errors occurred:

    • installing source package 'catch22' ... ** libs c:/Rtools/mingw_64/bin/gcc -I"C:/PROGRA~1/R/R-35~1.1/include" -DNDEBUG -I../inst/include -I"C:/Users/PeterLaurinec/Documents/R/win-library/3.5/Rcpp/include" -O2 -Wall -std=gnu99 -mtune=generic -c CO_AutoCorr.c -o CO_AutoCorr.o In file included from CO_AutoCorr.c:8:0: CO_AutoCorr.c: In function 'CO_AutoCorr': fft.h:16:43: error: '_Imaginary_I' undeclared (first use in this function) #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y))) ^ CO_AutoCorr.c:63:16: note: in expansion of macro 'CMPLX' F[i] = CMPLX(y[i] - m, 0.0); ^ fft.h:16:43: note: each undeclared identifier is reported only once for each function it appears in #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y))) ^ CO_AutoCorr.c:63:16: note: in expansion of macro 'CMPLX' F[i] = CMPLX(y[i] - m, 0.0); ^ CO_AutoCorr.c: In function 'co_autocorrs': fft.h:16:43: error: '_Imaginary_I' undeclared (first use in this function) #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y))) ^ CO_AutoCorr.c:97:16: note: in expansion of macro 'CMPLX' F[i] = CMPLX(y[i] - m, 0.0); ^ CO_AutoCorr.c: In function 'CO_HistogramAMI_even_2_5': CO_AutoCorr.c:347:5: error: variable-sized object may not be initialized double binEdges[numBins+1] = {0}; ^ CO_AutoCorr.c:347:5: warning: excess elements in array initializer CO_AutoCorr.c:347:5: warning: (near initialization for 'binEdges') CO_AutoCorr.c:370:5: error: variable-sized object may not be initialized double binEdges12[(numBins + 1) * (numBins + 1)] = {0}; ^ CO_AutoCorr.c:370:5: warning: excess elements in array initializer CO_AutoCorr.c:370:5: warning: (near initialization for 'binEdges12') CO_AutoCorr.c:414:5: error: variable-sized object may not be initialized double pi[numBins] = {0}; ^ CO_AutoCorr.c:414:5: warning: excess elements in array initializer CO_AutoCorr.c:414:5: warning: (near initialization for 'pi') CO_AutoCorr.c:415:5: error: variable-sized object may not be initialized double pj[numBins] = {0}; ^ CO_AutoCorr.c:415:5: warning: excess elements in array initializer CO_AutoCorr.c:415:5: warning: (near initialization for 'pj') make: *** [C:/PROGRA~1/R/R-35~1.1/etc/x64/Makeconf:208: CO_AutoCorr.o] Error 1 ERROR: compilation failed for package 'catch22'

    Any idea? Thx

    opened by PetoLau 2
  • python3 issue

    python3 issue

    There is a difficulty in compiling using python3. E.g., python3 setup.py build gives the following:

    running build
    running build_ext
    building 'catch22_C' extension
    creating build
    creating build/temp.macosx-10.7-x86_64-3.7
    creating build/C
    gcc -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I../C/ -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include/python3.7m -c catch22_wrap.c -o build/temp.macosx-10.7-x86_64-3.7/catch22_wrap.o
    gcc -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I../C/ -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include/python3.7m -c ../C/MD_hrv.c -o build/temp.macosx-10.7-x86_64-3.7/../C/MD_hrv.o
    gcc -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include -arch x86_64 -I../C/ -I/Users/alex/miniconda3/envs/pipe-516-ram-mating-behaviour/include/python3.7m -c ../C/SP_Summaries.c -o build/temp.macosx-10.7-x86_64-3.7/../C/SP_Summaries.o
    In file included from ../C/CO_AutoCorr.h:9:0,
                     from ../C/SP_Summaries.c:9:
    ../C/SP_Summaries.c: In function 'welch':
    ../C/fft.h:16:43: error: '_Imaginary_I' undeclared (first use in this function)
     #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y)))
                                               ^
    ../C/SP_Summaries.c:43:20: note: in expansion of macro 'CMPLX'
                 F[i] = CMPLX(xw[i] - m, 0.0);
                        ^~~~~
    ../C/fft.h:16:43: note: each undeclared identifier is reported only once for each function it appears in
     #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y)))
                                               ^
    ../C/SP_Summaries.c:43:20: note: in expansion of macro 'CMPLX'
                 F[i] = CMPLX(xw[i] - m, 0.0);
                        ^~~~~
    ../C/SP_Summaries.c:71:13: warning: suggest parentheses around comparison in operand of '&' [-Wparentheses]
             if(i>0 & i < Nout-1){
                ~^~
    error: command 'gcc' failed with exit status 1
    

    Can fix? Or just limit to python2?

    opened by benfulcher 2
  • Python package version mismatch

    Python package version mismatch

    In release 0.4.0, the Python package instead has version 0.3.1.

    https://github.com/DynamicsAndNeuralSystems/catch22/blob/2e1a271c6a7437b6a4a754e1adc7e34d7a224c01/wrap_Python/setup.py#L17

    https://github.com/DynamicsAndNeuralSystems/catch22/blob/2e1a271c6a7437b6a4a754e1adc7e34d7a224c01/wrap_Python/setup_P3.py#L17

    opened by musicinmybrain 1
  • Error installing R wrapper (+ fixes for docs)

    Error installing R wrapper (+ fixes for docs)

    Been trying to install the R wrapper without much success (though more success than I've had with the Python and Matlab wrappers!). I noticed a few issues with the documentation along the way, and have noted them here along with the error I get:

    The install docs refer to./C_functions, but this directory appears to be./C in current builds.

    I think the .c and .h files are supposed to be moved to ./wrap_R/catch22/src, rather than ./wrap_R/src (which is specified in the install instructions, but does not actually exist unless I manually create it).

    Running R CMD INSTALL catch22_x.y.tar.gz only “works” in the latter case, and then only if R CMD build catch22 was run after the .c and .h files are copied to ./wrap_R/catch22/src. Attempting to build with these files in ./wrap_R/src causes the following error:

    catch22_wrap.cpp:5:25: fatal error: CO_AutoCorr.h: No such file or directory
    

    The docs should clarify that users should replace catch22_x.y.tar.gz with the tar file generated by the previous step. The name of this fill will depend on their version of catch22.

    Fixing the error related to the location of the C files got me as far as the following error. Any advice would be appreciated:

    (r-environment) # [email protected] in ~/Software/catch22/wrap_R [17:55:06]
    $ R CMD INSTALL catch22_0.1.tar.gz
    * installing to library \u2018/home/despoB/dlurie/anaconda3/envs/r-environment/lib/R/library\u2019
    * installing *source* package \u2018catch22\u2019 ...
    ** libs
    gcc -std=gnu99 -I/home/despoB/dlurie/anaconda3/envs/r-environment/lib/R/include -DNDEBUG -I../inst/include -I"/home/despoB/dlurie/anaconda3/envs/r-environment/lib/R/library/Rcpp/include" -I/home/despoB/dlurie/anaconda3/envs/r-environment/include   -fpic  -I/home/despoB/dlurie/anaconda3/envs/r-environment/include  -c CO_AutoCorr.c -o CO_AutoCorr.o
    In file included from CO_AutoCorr.c:8:0:
    CO_AutoCorr.c: In function \u2018CO_AutoCorr\u2019:
    fft.h:16:43: error: \u2018_Imaginary_I\u2019 undeclared (first use in this function)
     #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y)))
                                               ^
    CO_AutoCorr.c:63:16: note: in expansion of macro \u2018CMPLX\u2019
             F[i] = CMPLX(y[i] - m, 0.0);
                    ^
    fft.h:16:43: note: each undeclared identifier is reported only once for each function it appears in
     #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y)))
                                               ^
    CO_AutoCorr.c:63:16: note: in expansion of macro \u2018CMPLX\u2019
             F[i] = CMPLX(y[i] - m, 0.0);
                    ^
    CO_AutoCorr.c: In function \u2018co_autocorrs\u2019:
    fft.h:16:43: error: \u2018_Imaginary_I\u2019 undeclared (first use in this function)
     #define CMPLX(x, y) ((cplx)((double)(x) + _Imaginary_I * (double)(y)))
                                               ^
    CO_AutoCorr.c:97:16: note: in expansion of macro \u2018CMPLX\u2019
             F[i] = CMPLX(y[i] - m, 0.0);
                    ^
    make: *** [CO_AutoCorr.o] Error 1
    ERROR: compilation failed for package \u2018catch22\u2019
    * removing \u2018/home/despoB/dlurie/anaconda3/envs/r-environment/lib/R/library/catch22\u2019
    
    opened by danlurie 1
  • 14 * possible use of wrong binary operator ?

    14 * possible use of wrong binary operator ?

    fedora/pass300/20220906/catch22.spec.out:IN_AutoMutualInfoStats.c:44:19: warning: suggest parentheses around comp arison in operand of '&' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:PD_PeriodicityWang.c:66:20: warning: suggest parentheses around comparis on in operand of '&' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:PD_PeriodicityWang.c:72:25: warning: suggest parentheses around comparis on in operand of '&' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:SB_BinaryStats.c:40:20: warning: suggest parentheses around comparison i n operand of '|' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:SB_BinaryStats.c:78:20: warning: suggest parentheses around comparison i n operand of '|' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:SP_Summaries.c:86:13: warning: suggest parentheses around comparison in operand of '&' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:splinefit.c:606:14: warning: suggest parentheses around comparison in op erand of '&' [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/IN_AutoMutualInfoStats.c:44:19: warning: suggest parentheses around comparison in operand of ‘&’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/PD_PeriodicityWang.c:66:20: warning: suggest parentheses around com parison in operand of ‘&’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/PD_PeriodicityWang.c:72:25: warning: suggest parentheses around com parison in operand of ‘&’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/SB_BinaryStats.c:40:20: warning: suggest parentheses around compari son in operand of ‘|’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/SB_BinaryStats.c:78:20: warning: suggest parentheses around compari son in operand of ‘|’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/SP_Summaries.c:86:13: warning: suggest parentheses around compariso n in operand of ‘&’ [-Wparentheses] fedora/pass300/20220906/catch22.spec.out:../C/splinefit.c:606:14: warning: suggest parentheses around comparison in operand of ‘&’ [-Wparentheses]

    I checked the first two, presumably the rest are the same.

    opened by dcb314 1
  • Installation failure: `for’ loop initial declarations are only allowed in C99 mode`

    Installation failure: `for’ loop initial declarations are only allowed in C99 mode`

    When running pip install catch22, the C compilation seems to complain. I tried it with python 3.7-3.9.

     C/CO_AutoCorr.c:531:9: error: ‘for’ loop initial declarations are only allowed in C99 mode
                 for(int j = 0; j < numBins; j++){
                 ^
        error: command '/usr/bin/gcc' failed with exit code 1
        ----------------------------------------
    ERROR: Command errored out with exit status 1: /home/cxx579/anaconda3/envs/test_env/bin/python -u -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-l6lnk30h/catch22_0230d4e651e84fa1a6f4489c53513e34/setup.py'"'"'; __file__='"'"'/tmp/pip-install-l6lnk30h/catch22_0230d4e651e84fa1a6f4489c53513e34/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' install --record /tmp/pip-record-g8rdn06o/install-record.txt --single-version-externally-managed --compile --install-headers /home/cxx579/anaconda3/envs/test_env/include/python3.9/catch22 Check the logs for full command output.
    

    I am not an expert in C and how it tights up with the Python wrapper but it might. have to do with this? Any ideas how to fix this. Thx :D

    This issue can be fixed by

    export CFLAGS="-std=c99"
    

    However, it might be good to change the for loop instantiation that is more compatible by declaring the the iteration variable outside the loop like:

    int i;
    for (i=0;i<10;i++) { ..
    
    opened by angerhang 0
  • Segmentation Faults on Small Datasets

    Segmentation Faults on Small Datasets

    What Happened

    Get a segmentation fault when running catch22.catch22_all on short lists/numpy.arrays.

    What I Expected to Happen

    Returns a dictionary of features (perhaps with a lot of NaN-types due to the short timeseries)

    Minimum Complete Verifable Example

    >>> import catch22
    >>> catch22.catch22_all([1,2])
    Segmentation fault
    

    Further Details

    Can check that this doesn't happen with longer arrays like so:

    import catch22
    timeseries = list(range(10))
    while timeseries:
        print(len(timeseries))
        catch22.catch22_all(timeseries)
        timeseries = timeseries[:-1]
    
    opened by evanharwin 4
  • Failed to install catch22

    Failed to install catch22

    I am using Sagemaker notebook and failed to install catch22 package.

    Tried to add 'extra_compile_args = ['-std=c99']' before running 'pip install catch22'. Getting the following error:

    C/SC_FluctAnal.c:12:5: note: use option -std=c99 or -std=gnu99 to compile your code

    opened by Sidshroff 0
  • wrap_Python setup.py should add

    wrap_Python setup.py should add "extra_compile_args = ['-std=c99']" (GCC 7.5.0)

    or else the compilation will fail in Linux. setup_P3.py :

    the c++ extension module
    extension_mod = Extension("catch22_C",
            sources=["catch22_wrap_P3.c"] + sourceFileList,
            include_dirs=[sourceDir],
            extra_compile_args = ['-std=c99']
    )
    

    Python:

        active environment : base
        active env location : /opt/anaconda
                shell level : 1
           user config file : /root/.condarc
     populated config files : /root/.condarc
              conda version : 4.9.2
        conda-build version : 3.17.8
             python version : 3.7.3.final.0
           virtual packages : __glibc=2.27=0
                              __unix=0=0
                              __archspec=1=x86_64
    

    gcc

    Using built-in specs.
    COLLECT_GCC=gcc
    COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/7/lto-wrapper
    OFFLOAD_TARGET_NAMES=nvptx-none
    OFFLOAD_TARGET_DEFAULT=1
    Target: x86_64-linux-gnu
    Configured with: ../src/configure -v --with-pkgversion='Ubuntu 7.5.0-3ubuntu1~18.04' --with-bugurl=file:///usr/share/doc/gcc-7/README.Bugs --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --prefix=/usr --with-gcc-major-version-only --program-suffix=-7 --program-prefix=x86_64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-bootstrap --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-vtable-verify --enable-libmpx --enable-plugin --enable-default-pie --with-system-zlib --with-target-system-zlib --enable-objc-gc=auto --enable-multiarch --disable-werror --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-offload-targets=nvptx-none --without-cuda-driver --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
    Thread model: posix
    gcc version 7.5.0 (Ubuntu 7.5.0-3ubuntu1~18.04)
    
    opened by xiaoluffy 0
  • Failed to install

    Failed to install

    Hi, I failed to install it in Python, would you mind checking out what is the problem? And how to use catch22? Is there a GUI or maybe a handbook for detailed method? image

    opened by IrenXu 7
Releases(v0.4.0)
  • v0.4.0(Jun 21, 2022)

  • v0.3.1(Jun 9, 2022)

    Adds a catch24 option to compute Mean (DN_Mean) and Standard Deviation (DN_Spread_Std) as features in addition to the standard catch22. Deletes R wrapper from repository as native R implementation Rcatch22 is on CRAN and requires no manual compilation. Interpolates the CO_f1ecac feature to now return a double instead of an integer for more nuanced performance in feature-based time-series analysis applications, such as time-series classification.

    Source code(tar.gz)
    Source code(zip)
  • v0.2.1(Jan 11, 2021)

  • v0.2.0(Jan 10, 2021)

  • v0.1.0(Jun 21, 2020)

Owner
Carl H Lubba
Carl H Lubba
OREO: Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (NeurIPS 2021)

OREO: Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (NeurIPS 2021) Video demo We here provide a video demo from co

20 Nov 25, 2022
G-NIA model from "Single Node Injection Attack against Graph Neural Networks" (CIKM 2021)

Single Node Injection Attack against Graph Neural Networks This repository is our Pytorch implementation of our paper: Single Node Injection Attack ag

Shuchang Tao 18 Nov 21, 2022
Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning This repository is the official implementation of CARE.

ChongjianGE 89 Dec 02, 2022
YOLOX-Paddle - A reproduction of YOLOX by PaddlePaddle

YOLOX-Paddle A reproduction of YOLOX by PaddlePaddle 数据集准备 下载COCO数据集,准备为如下路径 /ho

QuanHao Guo 6 Dec 18, 2022
Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)

An Image is Worth 16x16 Words, What is a Video Worth? paper Official PyTorch Implementation Gilad Sharir, Asaf Noy, Lihi Zelnik-Manor DAMO Academy, Al

213 Nov 12, 2022
This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

Project This repo has been populated by an initial template to help get you started. Please make sure to update the content to build a great experienc

Microsoft 674 Dec 26, 2022
Pytorch implementation of the Variational Recurrent Neural Network (VRNN).

VariationalRecurrentNeuralNetwork Pytorch implementation of the Variational RNN (VRNN), from A Recurrent Latent Variable Model for Sequential Data. Th

emmanuel 251 Dec 17, 2022
GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]

GANimation: Anatomically-aware Facial Animation from a Single Image [Project] [Paper] Official implementation of GANimation. In this work we introduce

Albert Pumarola 1.8k Dec 28, 2022
Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

Useful materials and tutorials for 110-1 NTU DBME5028 (Application of Deep Learning in Medical Imaging)

7 Jun 22, 2022
A Structured Self-attentive Sentence Embedding

Structured Self-attentive sentence embeddings Implementation for the paper A Structured Self-Attentive Sentence Embedding, which was published in ICLR

Kaushal Shetty 488 Nov 28, 2022
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Fre-GAN Vocoder Fre-GAN: Adversarial Frequency-consistent Audio Synthesis Training: python train.py --config config.json Citation: @misc{kim2021frega

Rishikesh (ऋषिकेश) 93 Dec 17, 2022
PyTorch DepthNet Training on Still Box dataset

DepthNet training on Still Box Project page This code can replicate the results of our paper that was published in UAVg-17. If you use this repo in yo

Clément Pinard 115 Nov 21, 2022
Tensorflow Repo for "DeepGCNs: Can GCNs Go as Deep as CNNs?"

DeepGCNs: Can GCNs Go as Deep as CNNs? In this work, we present new ways to successfully train very deep GCNs. We borrow concepts from CNNs, mainly re

Guohao Li 612 Nov 15, 2022
Implementation for Curriculum DeepSDF

Curriculum-DeepSDF This repository is an implementation for Curriculum DeepSDF. Full paper is available here. Preparation Please follow original setti

Haidong Zhu 69 Dec 29, 2022
SAN for Product Attributes Prediction

SAN Heterogeneous Star Graph Attention Network for Product Attributes Prediction This repository contains the official PyTorch implementation for ADVI

Xuejiao Zhao 9 Dec 12, 2022
Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh

Arjun Majumdar 44 Dec 14, 2022
The modify PyTorch version of Siam-trackers which are speed-up by TensorRT.

SiamTracker-with-TensorRT The modify PyTorch version of Siam-trackers which are speed-up by TensorRT or ONNX. [Updating...] Examples demonstrating how

9 Dec 13, 2022
【CVPR 2021, Variational Inference Framework, PyTorch】 From Rain Generation to Rain Removal

From Rain Generation to Rain Removal (CVPR2021) Hong Wang, Zongsheng Yue, Qi Xie, Qian Zhao, Yefeng Zheng, and Deyu Meng [PDF&&Supplementary Material]

Hong Wang 48 Nov 23, 2022
Boostcamp CV Serving For Python

Boostcamp-CV-Serving Prerequisites MySQL GCP Cloud Storage GCP key file Sentry Streamlit Cloud Secrets: .streamlit/secrets.toml #DO NOT SHARE THIS I

Jungwon Seo 19 Feb 22, 2022
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

PointRCNN PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud Code release for the paper PointRCNN:3D Object Proposal Generation a

Shaoshuai Shi 1.5k Dec 27, 2022