Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
    Nirjal444
    @Nirjal444
    I see three different videos which I have used for pose estimation in sleap.
    video.png
    Simon Nilsson
    @sronilsson
    @Nirjal444 yes, you would see this error, as SimBA doesn't know which video represents aggression.slp. SimBA expects there to be en Aggression.mp4 or similar (eg Avi) in the project, and can't locate it.
    Nirjal444
    @Nirjal444
    @sronilsson This aggression.slp is the sleap main project file. As per your answer does each videos has their own .slp file? Or am i uploading the wrong slp file? Will renaming the videos fix the error?
    Simon Nilsson
    @sronilsson
    @Nirjal444 - that's right, use your sleap project to generate predictions (run inference) on videos, to create a slp file for each video, then import those slp files
    17 replies
    Nuno Beltrao
    @nunobeltrao_gitlab
    Hello! I'm new to SimBA and I'm having some trouble getting it started. I've done the installation as described in the documentation page, but when I try to start SimBA there's an import error. Could you help me solve this? Thanks!
    image.png
    Nuno Beltrao
    @nunobeltrao_gitlab
    Yes, it did fix it @sronilsson ! Thanks for your help!
    Simon Nilsson
    @sronilsson
    :thumbsup:
    Nuno Beltrao
    @nunobeltrao_gitlab

    @sronilsson I'm having another issue. I'm trying to use DLC through SimBA, but I get an error when I try to create the DLC project. What should I do?

    Exception in Tkinter callback
    Traceback (most recent call last):
    File "C:\Users\nunob\miniconda3\envs\simbaenv\lib\tkinter__init.py", line 1705, in call__
    return self.func(*args)
    File "C:\Users\nunob\miniconda3\envs\simbaenv\lib\site-packages\simba\SimBA.py", line 1497, in createprojectcommand
    config_path = deeplabcut.create_new_project(str(projectname), str(experimentalname), videolist,working_directory=str(self.folderpath1selected.folder_path), copy_videos=copyvid)
    NameError: name 'deeplabcut' is not defined

    Simon Nilsson
    @sronilsson
    Hi @nunobeltrao_gitlab. Got it. We have removed support for DLC within SimBA - it is possible to use it through earlier versions of simba-uw-tf. However, I haven't been maintaining it for some years. Those menus where built before DLC had their GUI. I highly recommend using DLC (or SLEAP), which both are great GUIs now, instead of accessing the DLC package through the SimBA menus.
    vchiang001
    @vchiang001
    image.png
    5 replies
    Nirjal444
    @Nirjal444
    error.png
    slp.png
    marinasoong
    @marinasoong
    Hello Simon @sronilsson , I got some data from DLC and am planning to use SimBA, but I get errors when I install it. Could you have a look at it, please?
    image.png
    Simon Nilsson
    @sronilsson
    Hi @marinasoong! I think platform.linux_distribution is removed in python 3.8 and above. If you use python 3.6, does it work?
    3 replies
    ayah26
    @ayah26

    Hello! I am on step 10 (sklearn visualization) and I attempted to generate videos to visualize classification results for all of my videos -- but in the simBA window it stopped after almost finishing the first video and gave this error in command--

    Exception in Tkinter callback
    Traceback (most recent call last):
    File "c:\users\owner\anaconda3\envs\simbaenv-2\lib\tkinter__init.py", line 1705, in call
    return self.func(*args)
    File "c:\users\owner\anaconda3\envs\simbaenv-2\lib\site-packages\simba\SimBA.py", line 5852, in plotsklearn_result
    plotsklearnresult(self.projectconfigini,self.videovar.get(),self.genframevar.get())
    File "c:\users\owner\anaconda3\envs\simbaenv-2\lib\site-packages\simba\sklearn_plot_scripts\plot_sklearn_results_2.py", line 141, in plotsklearnresult
    currAnimal = currentDf.loc[currentDf.index[currRow], [currXheader, currYheader, curr_bp_p_header]]
    File "c:\users\owner\anaconda3\envs\simbaenv-2\lib\site-packages\pandas\core\indexes\base.py", line 4280, in
    getitem__
    return getitem(key)
    IndexError: index 9203 is out of bounds for axis 0 with size 9203

    Simon Nilsson
    @sronilsson
    Hi @ayah26! Got it, can you try to update simba pip install simba-uw-tf --dev and let me know if error persists?
    29 replies
    Marcelobot
    @Marcelobot

    Hello im struggling oftentimes with importing new H5 Files and recieve the following term in the terminal:
    "All multi-animal DLC .h5 tracking files ordered and imported into SimBA project in the chosen workflow file format"

    But the truth is, that everything was well stored and ready for import:

    image.png

    What could be the reason behind? Ive tried all different types of interpolation

    Cant wait to read your answer :)
    Thanks already!

    image.png

    The related Code in Terminal:

    image.png
    Simon Nilsson
    @sronilsson
    hello @Marcelobot - does it only happen when you use interpolation? if you open the project_config.ini, what does it say under [General settings][animal_no], and under [Multi animal IDs][id_list] ?
    hzsugar
    @hzsugar

    Hi! When trying to create a project (multi-animal DLC, 8bp) in the dev version (which I checked for updates today) I get this error:

    Exception in Tkinter callback
    Traceback (most recent call last):
    File "C:\Users\hczakhar\Anaconda3\envs\hzsimba\lib\tkinter__init.py", line 1705, in call__
    return self.func(*args)
    File "C:\Users\hczakhar\Anaconda3\envs\hzsimba\lib\site-packages\simba\SimBA.py", line 3754, in make_projectini
    self.configinifile = write_inifile(msconfig,project_path,project_name,no_targets,target_list,bp, listindex, animalNo, self.csvORparquet.getChoices())
    File "C:\Users\hczakhar\Anaconda3\envs\hzsimba\lib\site-packages\simba\create_project_ini.py", line 91, in write_inifile
    f.write('modelpath' + str(i+1) + ' = ' + os.path.join(str(models_folder), str(target_list[i])) + '.sav' +'\n')
    IndexError: list index out of range

    Simon Nilsson
    @sronilsson
    Thanks @hzsugar! very helpful, I was just cleaning this function yesterday, and create_project_ini.py and self.configinifile = write_inifile ... shouldn't be used or exist anymore, surprised to see this. Can you update SimBA, version 0.94.1, and let me know if the error still persist?
    hzsugar
    @hzsugar
    Thanks, that worked, and fixed an issue I was having earlier! (Wasn't able to import videos or tracking data.)
    Simon Nilsson
    @sronilsson
    Thanks for letting me know!
    Marcelobot
    @Marcelobot
    image.png
    Is there a parameter to improve the quality of the videos?
    Actually its not about the size of letters but more the quality so that the video is less flattering while watching
    2 replies
    marinasoong
    @marinasoong
    Screenshot from 2022-08-03 11-00-18.png
    Screenshot from 2022-08-03 10-59-35.png
    Screenshot from 2022-08-03 11-00-08.png
    Hi @sronilsson , my colleagues and I tried to install SimBA in python 3.6, but ran into issues with wxpython. Could you help me with that?
    Nastacia Goodwin
    @goodwinnastacia
    image.png
    1 reply
    @sssm12 please look here for files
    kkw11
    @kkw11
    Trying to analyze more data with trained models. When I try to extract features on the corrected DLC csv it gives an error. Any suggestions on what to change? Exception in thread Thread-3:
    Traceback (most recent call last):
    File "C:\Users\kkw11.conda\envs\SimBA\lib\threading.py", line 916, in _bootstrap_inner
    self.run()
    File "C:\Users\kkw11.conda\envs\SimBA\lib\threading.py", line 864, in run
    self._target(self._args, *self._kwargs)
    File "C:\Users\kkw11.conda\envs\SimBA\lib\site-packages\simba\SimBA.py", line 5933, in extractfeatures
    extract_features_wotarget_user_defined(self.projectconfigini)
    File "C:\Users\kkw11.conda\envs\SimBA\lib\site-packages\simba\features_scripts\extract_features_user_defined.py", line 80, in extract_features_wotarget_user_defined
    roll_windows.append(int(fps / roll_windows_values[i]))
    OverflowError: cannot convert float infinity to integer
    5 replies
    AlbaLM94
    @AlbaLM94

    Hi! I am using the latest version and I am in the outlier correction step. I could choose the settings for outlier correction without any issues bit when I click Correct outlier I get this error: Exception in Tkinter callback
    Traceback (most recent call last):
    File "C:\Users\BePhysLab\anaconda3\envs\simBA\lib\tkinter__init.py", line 1705, in call__
    return self.func(*args)
    File "C:\Users\BePhysLab\anaconda3\envs\simBA\lib\site-packages\simba\SimBA.py", line 5543, in correct_outlier
    dev_move_user_defined(configini)
    File "C:\Users\BePhysLab\anaconda3\envs\simBA\lib\site-packages\simba\outlier_scripts\movement\correct_devs_mov_user_defined.py", line 52, in dev_move_user_defined
    x_cols, y_cols, p_cols = getBpNames(configFile)
    File "C:\Users\BePhysLab\anaconda3\envs\simBA\lib\site-packages\simba\drop_bp_cords.py", line 132, in getBpNames
    colHead1, colHead2, colHead3 = (bodypart + '_x', bodypart + '_y', bodypart + '_p')
    TypeError: unsupported operand type(s) for +: 'float' and 'str'

    Thanks for your help!

    3 replies
    Simon Nilsson
    @sronilsson
    Thanks for reporting @AlbaLM94 - can you confirm which version of Simba you have with pip show simba-uw-tf-dev and I will check if I can replicate.
    AlbaLM94
    @AlbaLM94
    Sure. I have Version: 0.94.3
    8 replies
    aloksneurobot1
    @aloksneurobot1
    Hi @sronilsson While training my model i end up getting error that shap_features_categories.csv file was not found. I checked my folders in anaconda and its present there. following is the error log from cmd window : Exception in Tkinter callback
    Traceback (most recent call last):
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\tkinter__init.py", line 1705, in call
    return self.func(args)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\simba\SimBA.py", line 4035, in <lambda>
    button_trainmachinemodel = Button(label_trainmachinemodel,text='Train single model from global environment',fg='blue',command = lambda: threading.Thread(target=trainmodel2(self.projectconfigini)).start())
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\simba\train_model_2.py", line 389, in trainmodel2
    generateShapLog(data_train, target_train, feature_list, classifierName, shap_target_present_no,shap_target_absent_no, inifile)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\simba\train_model_2.py", line 132, in generateShapLog
    shap_summary_calculations(inifile, outputDfShap, classifierName, expected_value, tree_evaluations_out)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\simba\shap_calcs.py", line 50, in shap_summary_calculations
    colCats = pd.read_csv(feat_cat_csv_path, header=[0, 1])
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\pandas\io\parsers.py", line 685, in parser_f
    return _read(filepath_or_buffer, kwds)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\pandas\io\parsers.py", line 457, in _read
    parser = TextFileReader(fp_or_buf, *
    kwds)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\pandas\io\parsers.py", line 895, in
    init
    self._make_engine(self.engine)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\pandas\io\parsers.py", line 1135, in _make_engine
    self._engine = CParserWrapper(self.f, **self.options)
    File "C:\Users\user\anaconda3\envs\simbaenv\lib\site-packages\pandas\io\parsers.py", line 1917, in
    init
    self._reader = parsers.TextReader(src, **kwds)
    File "pandas/_libs/parsers.pyx", line 382, in pandas._libs.parsers.TextReader.
    cinit__
    File "pandas/_libs/parsers.pyx", line 689, in pandas._libs.parsers.TextReader._setup_parser_source
    FileNotFoundError: [Errno 2] File b'C:\Users\user\simba\assets\shap\feature_categories\shap_feature_categories.csv' does not exist: b'C:\Users\user\simba\assets\shap\feature_categories\shap_feature_categories.csv'
    5 replies
    Could you kindly direct me to reasons for this error? How can I solve this ? thank you!!
    Marcelobot
    @Marcelobot
    image.png
    image.png
    Marcelobot
    @Marcelobot

    image.png

    Hello Could you explain how the F1_score is calculated to this classification report?

    Ive actually understood how in general its calculated and it sounds clear, that it might will be the best parameter for objectively messure the performance of models BUT to be honest it seems a bit confusing how it developes better or getting worse.

    Which data is exactly used to create those classification reports after every training?
    And would you say i should go strictly after this f1_score to compare performaces of networks?

    image.png

    Here ive tried out different undersample Ratios for training, as you recommented to me. And compared them for all 11 different models. The marker used has been the f1_score ive recieved by this mentioned classification reports of trainings.

    hzsugar
    @hzsugar

    Hi, I'm having some difficulty with videos and .csv files of tracking data from DLC not importing correctly: I receive the message "Copying videos..." in the terminal but even after some time no files appear in the directory. When I manually place videos and .csv files in the proper directories, and try to extract frames, I get this error: "('expected str, bytes or os.PathLike object, not ConfigParser',)
    Please make sure videos are imported and located in /project_folder/videos"

    Am I going about this the right way? At the moment I have a trained DLC model that I am trying to import into SimBA for behavior labeling. Is there an easier way to do this?

    6 replies
    VAmoroso13
    @VAmoroso13

    Simon, thank you again for the help!

    I have one further question that builds on something hzsugar asked. I came across SimBA after using DLC extensively and have some pretrained networks and data that have been optimized well. I would like to use the SimBA pipeline for analysis, how does one go about importing this? I'm afraid I'm a bit lost.

    Thank you for any help and sorry about wasting your time.

    3 replies