SimBA (Simple Behavioral Analysis), a pipeline and GUI for developing supervised behavioral classifiers
Home Page: https://simba-uw-tf-dev.readthedocs.io/
License: GNU General Public License v3.0
Hello!
We are reaching out because we would love to have your project listed on Open Neuroscience, and also share information about this project:
Open Neuroscience is a community run project, where we are curating and highlighting open source projects related to neurosciences!
Briefly, we have a website where short descritptions about projects are listed, with links to the projects themselves, their authors, together with images and other links.
Once a new entry is made, we make a quick check for spam, and publish it.
Once published, we make people aware of the new entry by Twitter and a Facebook group.
To add information about their project, developers only need to fill out this form
In the form, people can add subfields and tags to their entries, so that projects are filterable and searchable on the website!
The reason why we have the form system is that it makes it open for everyone to contribute to the website and allows developers themselves to describe their projects!
Also, there are so many amazing projects coming out in Neurosciences that it would be impossible for us to keep track and log them all!
Please get in touch if you have any questions or would like to collaborate!
Hi, First of all thank you for creating SIMBA! This is my 1st approach to this kind of tracking programs and I'm just learning to use the program.
I'm running SIMBA w/TF in Windows 10 with:
I created a DLC project with one video, and when I want to extract the frames in this video (w/automatic form and uniform algorithm) I get the following in my anaconda prompt:
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\users\agost\anaconda3\envs\dlc-gpu\lib\tkinter\__init__.py", line 1705, in __call__
return self.func(*args)
File "c:\users\agost\anaconda3\envs\dlc-gpu\lib\site-packages\simba\SimBA.py", line 2148, in dlc_extractframes_command
select_numfram2pick(config_path,self.label_numframes2pick.entry_get)
NameError: name 'select_numfram2pick' is not defined
Describe the bug
After entering the command
git clone -b SimBA_no_DLC https://github.com/sgoldenlab/simba.git
files are updated correctly, then after the command
pip install -r simba/SimBA/requirements.txt
I receive the error
ERROR: Cannot uninstall 'PyYAML'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.
Under the correct directory, then running the command
python SimBA.py
produces the following
Traceback (most recent call last):
File "SimBA.py", line 8, in
from tkinter_functions import *
ModuleNotFoundError: No module named 'tkinter_functions'
Any advice would be appreciated.
To Reproduce
Steps to reproduce the behavior:
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
Smartphone (please complete the following information):
Additional context
Add any other context about the problem here.
Hello,
I'm using multi-animal pose-estimation data in SimBA. I already extracted the frames, and should now set the video parameters. But here the error message my prompt returns:
Consequently, no video row appear, and I cannot define the scales on my videos.
Would someone please have a suggestion to fix this problem?
FYI: I'm using the 1.2.5 simba version and get the same error on windows 7 and 10. My videos are .avi.
Thank you,
Best,
Dorian
Describe the bug
I'm doing a test run using an hour long mp4 file and DLC labels for 1 animal, 8 body parts. Extract Features appears to be working until it hits "Calculating rolling windows: medians, medians, and sums..." at which I get the following error:
Desktop (please complete the following information):
Is your feature request related to a problem? Please describe.
This feature request is in direct connection to this issue
Describe the solution you'd like
As this is mainly a copy/paste of data, plus some minor adjustments to the additional logs you create:
My suggestion would be a button in the outlier correction tab that creates a dummy outlier correction (without the calculations) file and handles the data movement/creation just as the normal function would.
Another alternative would be to allow the import of filtered/corrected files that will be transformed into your style of logging/handling these kinds of files.
It probably depends if there is any use for a truly raw tracking file in SimBa's workflow if the advanced user has already the abililty to filter/correct them disconnected from SimBa.
Describe alternatives you've considered
An easy alternative is to set the parameters given to the correction higher than the max resolution of the video, so that no bodypart can ever reach that distance.
Additional context
I understand that this is a feature that helps refining raw tracking data further and is therefore intentionally not skippable. This is a minor request and the community can probably live without it for sure. But, as many groups work with tracking data like the one from DLC, some adapted their own tricks to handle outliers. Therefore it might be a usefull feature, for advanced users.
Thank you for your hard work so far.
Describe the bug
After starting the training with the following settings, the error occured.
[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 12 concurrent workers.
[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 8.9s
[Parallel(n_jobs=-1)]: Done 176 tasks | elapsed: 51.3s
[Parallel(n_jobs=-1)]: Done 426 tasks | elapsed: 2.1min
[Parallel(n_jobs=-1)]: Done 776 tasks | elapsed: 3.7min
[Parallel(n_jobs=-1)]: Done 1226 tasks | elapsed: 5.8min
[Parallel(n_jobs=-1)]: Done 1776 tasks | elapsed: 8.4min
[Parallel(n_jobs=-1)]: Done 2000 out of 2000 | elapsed: 9.4min finished
[Parallel(n_jobs=12)]: Using backend ThreadingBackend with 12 concurrent workers.
[Parallel(n_jobs=12)]: Done 26 tasks | elapsed: 0.0s
[Parallel(n_jobs=12)]: Done 176 tasks | elapsed: 0.2s
[Parallel(n_jobs=12)]: Done 426 tasks | elapsed: 0.5s
[Parallel(n_jobs=12)]: Done 776 tasks | elapsed: 1.0s
[Parallel(n_jobs=12)]: Done 1226 tasks | elapsed: 1.6s
[Parallel(n_jobs=12)]: Done 1776 tasks | elapsed: 2.4s
[Parallel(n_jobs=12)]: Done 2000 out of 2000 | elapsed: 2.7s finished
[Parallel(n_jobs=12)]: Using backend ThreadingBackend with 12 concurrent workers.
[Parallel(n_jobs=12)]: Done 26 tasks | elapsed: 0.0s
[Parallel(n_jobs=12)]: Done 176 tasks | elapsed: 0.2s
[Parallel(n_jobs=12)]: Done 426 tasks | elapsed: 0.5s
[Parallel(n_jobs=12)]: Done 776 tasks | elapsed: 1.0s
[Parallel(n_jobs=12)]: Done 1226 tasks | elapsed: 1.6s
[Parallel(n_jobs=12)]: Done 1776 tasks | elapsed: 2.4s
[Parallel(n_jobs=12)]: Done 2000 out of 2000 | elapsed: 2.7s finished
[Parallel(n_jobs=12)]: Using backend ThreadingBackend with 12 concurrent workers.
[Parallel(n_jobs=12)]: Done 26 tasks | elapsed: 0.0s
[Parallel(n_jobs=12)]: Done 176 tasks | elapsed: 0.2s
[Parallel(n_jobs=12)]: Done 426 tasks | elapsed: 0.5s
[Parallel(n_jobs=12)]: Done 776 tasks | elapsed: 1.0s
[Parallel(n_jobs=12)]: Done 1226 tasks | elapsed: 1.6s
[Parallel(n_jobs=12)]: Done 1776 tasks | elapsed: 2.3s
[Parallel(n_jobs=12)]: Done 2000 out of 2000 | elapsed: 2.6s finished
Exception in thread Thread-7:
Traceback (most recent call last):
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "simba.py", line 3737, in trainsinglemodel
trainmodel2(self.projectconfigini)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_model_2.py", line 302, in trainmodel2
generateFeatureImportanceBarGraph(log_df, N_feature_importance_bars)
UnboundLocalError: local variable 'log_df' referenced before assignment
Additional context
I guess this is an error based on the missing selection/toggle of "Generate Features Importance Log". Do you need to select both?
Is it possible to use 3d coordinates with this software? theoretically it should make it more accurate, especially for videos shot at non-90* angles.
Hello! :)
I am having issues with labelling the behaviours. Whenever I try to do it, it seems like the GUI does not load the extracted frames correctly, leaving me with a blank space where the video frames should be presented. I have tried extracting the frames again, but it tells me the frames have already been extracted, despite the fact that the folders inside input folder are empty. Any ideas on how to solve this? I am using the no DLC version, and I obtained the csvs from colab.
Thank you!
Filipa
When installing SimBA with TF in a fresh conda env. on windows 10 I get the following error message:
ERROR: imgaug 0.4.0 has requirement numpy>=1.15, but you'll have numpy 1.14.5 which is incompatible.
ERROR: imbalanced-learn 0.6.2 has requirement scikit-learn>=0.22, but you'll have scikit-learn 0.19.2 which is incompatible.
ERROR: tensorflow-gpu 1.14.0 has requirement protobuf>=3.6.1, but you'll have protobuf 3.6.0 which is incompatible.
ERROR: yellowbrick 0.9.1 has requirement scikit-learn>=0.20, but you'll have scikit-learn 0.19.2 which is incompatible.
I input the following commands:
conda create --name SimBA python=3.6
conda activate SimBA
git clone -b master https://github.com/sgoldenlab/simba.git
pip install -r simba/simba/requirements.txt
It installs several of the packages before I encounter the error.
When trying to import a .slp file into simba I get the following error in "project configuration / import tracking data":
I have imported the corresponding video in "project configuration / import videos into project folder".
What is the cause of this issue? Any suggestions on how to solve it?
First of all, thank you for developing SimBA!
I'm having an install issue that I cant seem to get around with dlc-windowsGPU (windows environment)
(dlc-windowsGPU) C:\Users\xxxxx\simba\simba>simba.py
Traceback (most recent call last):
File "C:\Users\maplight\simba\simba\SimBA.py", line 5, in
import deeplabcut
ModuleNotFoundError: No module named 'deeplabcut'
I have all the proper dependencies installed, I'm assuming it's a path I'm missing somewhere. using Anaconda. I have DeepLab installed:
(dlc-windowsGPU) C:\Users\xxxxx\DeepLabCut\
Thank you in advance for any guidance.
Hello everybody!
First of all, thank you for developing SimBA :) I was wondering if in the future it would be possible to add a feature that would allow users to define a ROI and use that feature as part of the classifier training.
Thanks!
Filipa
Hello,
@sgoldenlab sorry for this new request, but I'm actually unable to import slp files:
Would you have some suggestion to fix that?
Thank you,
Best,
Dorian
Setting an outlier correct C similar to described in the documentation (C = 1.5), or any other value causes the SimBA main window to be stuck at:
Pose-estimation body part setting for outlier correction: 7
Processing 1 files for movement outliers...
While cmd prompts the following:
Exception in Tkinter callback
Traceback (most recent call last):
File "C:\Users\Ejdrup\AppData\Local\Programs\Python\Python36\lib\tkinter\__init__.py", line 1699, in __call__
return self.func(*args)
File "SimBA.py", line 3981, in correct_outlier
dev_move_user_defined(configini)
File "C:\ProgramData\simba\simba\outlier_scripts\movement\correct_devs_mov_user_defined.py", line 115, in dev_move_user_defined
df_p_cols = pd.DataFrame([csv_df.pop(x) for x in p_cols]).T
File "C:\Users\Ejdrup\AppData\Local\Programs\Python\Python36\lib\site-packages\pandas\core\frame.py", line 450, in __init__
arrays, columns = to_arrays(data, columns, dtype=dtype)
File "C:\Users\Ejdrup\AppData\Local\Programs\Python\Python36\lib\site-packages\pandas\core\internals\construction.py", line 471, in to_arrays
data, columns, coerce_float=coerce_float, dtype=dtype
File "C:\Users\Ejdrup\AppData\Local\Programs\Python\Python36\lib\site-packages\pandas\core\internals\construction.py", line 522, in _list_of_series_to_arrays
indexer = indexer_cache[id(index)] = index.get_indexer(columns)
File "C:\Users\Ejdrup\AppData\Local\Programs\Python\Python36\lib\site-packages\pandas\core\indexes\base.py", line 2985, in get_indexer
"Reindexing only valid with uniquely" " valued Index objects"
pandas.core.indexes.base.InvalidIndexError: Reindexing only valid with uniquely valued Index objects
Hi again,
I am using the new version 1.1 of the SimBA environment, and came over a small glitch, I think related rather to my particular way of using it.
So, the bug:
after the "Outlier Correction" step I proceeded directly to "Extract Features" step, but got an error message in the main SimBA GUI window: "Error: make sure all the videos that are going to be analyzed are represented in the project_folder/logs/video_info.csv file". The step thus has failed.
Possible reason and working empiric fix:
The postures were analysed separately using DeepLabCut (not via SimBA pipeline), and then the .csv files with coordinates from DeepLabCut were loaded into the the resulting .csv files. Thus, the names of those files (something like "Dec0419_Trial1DLC_resnet50_resident_intruder_optogeneticsFeb14shuffle1_600000.csv") were not the same as the names of the movies loaded into the project ("Dec0419_Trial1.mp4"). The former names were listed in the log files project_folder\log\Outliers_location_nnnnnnn.csv and project_folder\log\Outliers_movement_nnnnnnnnnn.csv, but the latter (simpler) movie names were listed in the file project_folder\log\video_info.csv
The issue was resolved by pasting the values of the movie names from Outliers_*.csv log files into the video_info.csv log file.
Sincerely,
Olexiy.
Hello,
I wanted to upgrade to SimBA 1.1 (installation of the previous 1.0 version went smoothly).
Using Anaconda3 command prompt.
Followed the instructions on Github page:
git clone -b master https://github.com/sgoldenlab/simba.git
pip install -r simba/simba/requirements.txt
FFmpeg was already installed.
Then, in Anaconda3 run
python SimBA.py
SimBA GUI did not start, and instead resulted in the error message listed below.
Tried to go around by cloning the Tensorflow-free installation, repeating all the steps above and the following command:
git clone -b SimBA_no_TF https://github.com/sgoldenlab/simba.git
As a result, got the same error message.
Tried uninstalling Anaconda, then installed Anaconda & DeepLabCut newly, then repeated SimBA installation steps.... unfortunately, the same outcome.
Could you please help?
Thank you very much in advance.
Sincerely,
Olexiy.
Error messages in Anaconda prompt
(base) c:\Alex\simba\simba>python SimBA.py
Traceback (most recent call last):
File "SimBA.py", line 51, in
from ROI_freehand_draw_3 import roiFreehand
File "c:\Alex\simba\simba\ROI_freehand_draw_3.py", line 6, in
from shapely.geometry import Polygon
File "C:\anaconda3\lib\site-packages\shapely\geometry_init_.py", line 4, in
from .base import CAP_STYLE, JOIN_STYLE
File "C:\anaconda3\lib\site-packages\shapely\geometry\base.py", line 18, in
from shapely.coords import CoordinateSequence
File "C:\anaconda3\lib\site-packages\shapely\coords.py", line 8, in
from shapely.geos import lgeos
File "C:\anaconda3\lib\site-packages\shapely\geos.py", line 145, in
lgeos = CDLL(os.path.join(sys.prefix, 'Library', 'bin', 'geos_c.dll'))
File "C:\anaconda3\lib\ctypes_init.py", line 364, in init
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] The specified module could not be found
(base) c:\Alex\simba\simba>
Desktop (please complete the following information):
Additional context
Add any other context about the problem here.
After installing from the requirements.txt, getting the following Traceback:
Traceback (most recent call last):
File "SimBA.py", line 51, in
from ROI_freehand_draw_3 import roiFreehand
File "C:\Users\dlhag\simba\simba\ROI_freehand_draw_3.py", line 6, in
from shapely.geometry import Polygon
File "C:\Users\dlhag\Anaconda3\envs\simba\lib\site-packages\shapely\geometry_init_.py", line 4, in
from .base import CAP_STYLE, JOIN_STYLE
File "C:\Users\dlhag\Anaconda3\envs\simba\lib\site-packages\shapely\geometry\base.py", line 18, in
from shapely.coords import CoordinateSequence
File "C:\Users\dlhag\Anaconda3\envs\simba\lib\site-packages\shapely\coords.py", line 8, in
from shapely.geos import lgeos
File "C:\Users\dlhag\Anaconda3\envs\simba\lib\site-packages\shapely\geos.py", line 145, in
lgeos = CDLL(os.path.join(sys.prefix, 'Library', 'bin', 'geos_c.dll'))
File "C:\Users\dlhag\Anaconda3\envs\simba\lib\ctypes_init.py", line 348, in init
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] The specified module could not be found
Tried a few shapely versions, couldn't get anything other than this.
Any thoughts?
Describe the bug
When training a model using the app function "train single model from global environment" the following Error popt up. It seems to be connected to yellowbrick (so reporting?) but messes with the functionality. The model will not be saved (even though it was successfully trained).
This is the simba report window
This is the console until the error
This is the error message
Exception in thread Thread-182:
Traceback (most recent call last):
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "simba.py", line 3726, in trainsinglemodel
trainmodel2(self.projectconfigini)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_model_2.py", line 290, in trainmodel2
generateClassificationReport(clf, class_names)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_model_2.py", line 68, in generateClassificationReport
g = visualizer.poof(outpath=visualizerPath, clear_figure=True)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\yellowbrick\base.py", line 215, in poof
plt.savefig(outpath, **kwargs)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\matplotlib\pyplot.py", line 690, in savefig
fig.canvas.draw_idle() # need this if 'transparent=True' to reset colors
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\matplotlib\backends\_backend_tk.py", line 350, in draw_idle
self._idle_callback = self._tkcanvas.after_idle(idle_draw)
File "D:\Anaconda\envs\simba-gpu\lib\tkinter\__init__.py", line 764, in after_idle
return self.after('idle', func, *args)
File "D:\Anaconda\envs\simba-gpu\lib\tkinter\__init__.py", line 756, in after
name = self._register(callit)
File "D:\Anaconda\envs\simba-gpu\lib\tkinter\__init__.py", line 1372, in _register
self.tk.createcommand(name, f)
RuntimeError: main thread is not in main loop
Desktop (please complete the following information):
Simba GPU installation (Anaconda) on Windows 10
Additional context
A restart of the whole procedure went completely smooth without any errors. No restart necessary or anything. Just clicked the button again.
@sgoldenlab , Hello, I'm unfortunately dealing with a new error message.
I have been able to analyze the ROI and to obtain: number of entries, cumulative time, distance and velocity data.
Now I would like to draw heat maps. But I should first extract features right?
When I click Extract Features, it seems that the process stops, and here what happens:
I then click on append ROI data to features, and here what appears:
Have you any idea about the reason why it's not working?
As reminder, I'm working on multi animal project, on windows 7, avi videos, SimBA = 1.2.7. Concerning the outlier correction, I skipped it.
Thank you,
Best,
Dorian
Disclaimer
This is not a SimBa code bug. But probably a pandas or system specific behavior. This is why I called this "Report". Please feel free to close the issue if you see fit.
Describe the bug
As with all machine learning problems, I thought the best way to solve accuracy problems is to throw data at it:
Trying out 10 csv files from my experiments (about 600k frames in total) resulted in this error popping up.
I included my system info to give you a better overview. As mentioned below this might happen from overcommitment protection within the OS.
[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 46.8s
Exception in thread Thread-20:
Traceback (most recent call last):
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "simba.py", line 3764, in trainmultimodel
train_multimodel(self.projectconfigini)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_multiple_models_from_meta.py", line 164, in train_multimodel
features = baseFeatureFrame.copy()
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\pandas\core\generic.py", line 5996, in copy
data = self._data.copy(deep=deep)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\pandas\core\internals\managers.py", line 788, in copy
return self.apply("copy", axes=new_axes, deep=deep, do_integrity_check=False)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\pandas\core\internals\managers.py", line 438, in apply
applied = getattr(b, f)(**kwargs)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\pandas\core\internals\blocks.py", line 771, in copy
values = values.copy()
MemoryError: Unable to allocate 3.22 GiB for an array with shape (787, 549864) and data type float64
Simba console output
What google says:
A quick google hints at a OS issue/safety mechanism for memory allocation (although the thread is originally for Linux). Stackoverflow. There are a few provided solutions (including for windows) but I have not tried them yet.
Desktop (please complete the following information):
Simba-GPU installation with Anaconda
Operating System: Windows 10 Home 64-bit (10.0, Build 18362) (18362.19h1_release.190318-1202)
System Manufacturer: LENOVO
System Model: 81UH
Processor: Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz (12 CPUs), ~2.6GHz
Memory: 16384MB RAM
Additional context
As I was writing this issue, I restarted the process and I was able to reproduce the same result. But to my confusion the training continued despite of the memory issue.
Describe the bug
'Append ROI data to features' is not functioning as expected
To Reproduce
Steps to reproduce the behavior:
After successful execution of 'Analyze ROI' and 'Visualize ROI' steps:
Screenshots
Desktop (please complete the following information):
Describe the bug
After starting the outlier correction with both parameters set to 0 (the plan was to skip the correction with this), i got the following error message:
Exception in Tkinter callback Traceback (most recent call last): File "D:\Anaconda\envs\simba-gpu\lib\tkinter\__init__.py", line 1705, in __call__ return self.func(*args) File "simba.py", line 3818, in correct_outlier dev_loc_user_defined(configini) File "C:\Users\schwa\PycharmProjects\simba\simba\outlier_scripts\location\correct_devs_loc_user_defined.py", line 100, in dev_loc_user_defined currentArray[currentPosition][0] = reliableCoordinates[currentPosition][0] IndexError: index 7 is out of bounds for axis 0 with size 7
The csv file was transfered/created in the correct folder i assume "project_folder\csv\outlier_corrected_movement" but there is no file in "outlier_corrected_movement_location".
I checked your code and i guess it did not go through as the error occurs in one of the essential scripts.
To Reproduce
My user defined settings are: 9 points , 1 Animal (directly from DLC analysis)
The csv file is ca. 55k rows long
I am using a Windows 10 computer and your newest simba version (updated at 10 am local time)
Additional context
I cannot continue with extraction of features however.
It results in a message within your app:
Pose-estimation body part setting for feature extraction: user_defined Extracting features from 0 files... All feature extraction complete.
which is probably due a non working import in your code:
def extract_features_wotarget(inifile): .... csv_dir_in = os.path.join(csv_dir, 'outlier_corrected_movement_location') ....
########### FIND CSV FILES ########### for i in os.listdir(csv_dir_in): if i.__contains__(".csv"): fname = os.path.join(csv_dir_in, i) filesFound.append(fname) print('Extracting features from ' + str(len(filesFound)) + ' files...')
I can however continue if i copy+paste the same csv file (from outlier_corrected_movement) into the other folder. I haven't read through all of your code, but i assume that you keep the general structure of the dataframe that comes from dlc so this can work as a workaround for now (especially since i did not want to do a outlier correction anyway).
Hello,
I'm using SimBA with data obtained from multi animal pose estimation from DLC.
I have been able to extract my frames, to scale the video and to draw the ROIs. But when I want to run the ROI analysis (2 animals, one body part), there is an error. Here a screen shot of the prompt:
I'm analyzing 4 videos, and used the function "apply to all" after drawing the ROI of the first video. The first video seems ok, but the issue occurs at the second video:
Someone would have a solution to help me fixing this issue?
FYI: I'm using SimBA 1.2.5 on windows 7. My videos are ".avi".
I already successfully run ROI analysis with the same program configuration (but never using "apply to all" function) with other videos. So I don't know why this time it is not working.
Thank you,
Best,
Dorian
I try to run SimBA.py on OpenSUSE 15.1 x64 and ran into various portability errors. Mostly it's case-sensitivity (ie TheGoldenLab.PNG -> TheGoldenLab.png) and various instances of '\' in the code.
As both linux, mac and windows works fine with '/' as directory delimiter, I think it would be nice to change the \'s to /
Might be the wrong place, but it was the place I thought easiest to contact you and its semi a part of the software.
I suggest removing the current restriction on your osf.io repositories. They are current closed and you have to request access. It puts a unnecessary(?) delay on working with the software.
Hello! This is my first time writing an issue, so feel free to request lots of clarification.
I'm running the most recent version of Anaconda and attempting to install Simba. I've followed the instructions here for installing the standalone package w/o tf. I've been trying to resolve this for the past few hours to no avail.
Describe the bug
Simba will not run and has trouble installing.
To Reproduce
conda create --name new_env python==3.6conda activate new_envnew_env, run pip install simba-uw-no-tf. This is using pip version 20.1.1. Everything appears to build correctly except with the following warning:ERROR: imbalanced-learn 0.7.0 has requirement scikit-learn>=0.23, but you'll have scikit-learn 0.22.2 which is incompatible.simba in new_env. This fails and produces a long traceback.Traceback (most recent call last):File "c:\programdata\anaconda3\envs\new_env\lib\runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "c:\programdata\anaconda3\envs\new_env\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\ProgramData\Anaconda3\envs\new_env\Scripts\simba.exe\__main__.py", line 4, in <module> File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\simba\SimBA.py", line 47, in <module> from simba.ROI_freehand_draw_3 import roiFreehand File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\simba\ROI_freehand_draw_3.py", line 6, in <module> from shapely.geometry import Polygon File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\shapely\geometry\__init__.py", line 4, in <module> from .base import CAP_STYLE, JOIN_STYLE File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\shapely\geometry\base.py", line 18, in <module> from shapely.coords import CoordinateSequence File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\shapely\coords.py", line 8, in <module> from shapely.geos import lgeos File "c:\programdata\anaconda3\envs\new_env\lib\site-packages\shapely\geos.py", line 145, in <module> _lgeos = CDLL(os.path.join(sys.prefix, 'Library', 'bin', 'geos_c.dll')) File "c:\programdata\anaconda3\envs\new_env\lib\ctypes\__init__.py", line 348, in __init__ self._handle = _dlopen(self._name, mode)OSError: [WinError 126] The specified module could not be foundExpected behavior
Expect no conflicting dependencies and simba to start when simba is run in new_env
Desktop (please complete the following information):
new_env, 3.8 in base environThings I have tried
new_envsimba.simbaAny help/thoughts much appreciated!
Describe the bug
When importing a small image to create a pose configuration (96x161) the autosizing of the window is buggy (see image below).
Screenshots
Expected behavior
A clear and concise description of what you expected to happen.
Desktop (please complete the following information):
Additional context
I guess you will run into this issue with apps if you autosize and go to the limits of tkinter and such. So this is more of a note, than a real big issue. But as the original video resolution was 848x480 (quite common for tracking) the cut out might be something that happens more than once :)
You might know about this bug, and I know I'm not installing simba as per the instructions (using a conda environment etc.), but it seems like it should be an acceptable way to install it.
Describe the bug
Installing simba on Windows 10 in a conda environment fails due to geos DLL import error.
To Reproduce
Steps to reproduce the behavior:
conda create --name simba_bug_test python=3.6
conda activate simba_bug_test
git clone -b master https://github.com/sgoldenlab/simba.git
pip install -r simba\simba\requirements.txt
conda install cudatoolkit=10.0 cudnn
cd simba\simba
python SimBA.py
gives:
File "C:\Users\adam.\.conda\envs\simba_bug_test\lib\site-packages\shapely\coords.py", line 8, in <module>
from shapely.geos import lgeos
File "C:\Users\adam\.conda\envs\simba_bug_test\lib\site-packages\shapely\geos.py", line 145, in <module>
_lgeos = CDLL(os.path.join(sys.prefix, 'Library', 'bin', 'geos_c.dll'))
File "C:\Users\adam\.conda\envs\simba_bug_test\lib\ctypes\__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] The specified module could not be found
If I try:
pip uninstall shapely
pip install shapely
Then the error persists. However, if I install shapely from conda forge conda install -c conda-forge shapely, then simba loads.
N.B. it's also a bit annoying that simba has to be run from simba\simba
Desktop (please complete the following information):
After saving a labeling section and reopening at a later timepoint, SimBA keeps reopening at an older save. The file last_framelog remains unchanged as the following when saving at different timepoints:
[Last saved frames]' 'tracking_video2020-02-26t10_19_20 = 3736
Additionally, I'm not seeing any labels in the csv under targets_inserted, however, that might be because they are stored somewhere else?
Describe the bug
A clear and concise description of what the bug is.
Some of your scripts use backslashes for generating a path, which does not work on MacOS.
For example, in the create_project_init.py,
project_folder = str(directory +'\\' + project_name + '\\project_folder')
It would be better to use os.path.join()
The backslashes resulted in folders like this:
To Reproduce
Steps to reproduce the behavior:
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
Additional context
Add any other context about the problem here.
SIMBA v1.2 error while trying to label behaviors in larval zebrafish (TL= 100px = 5mm) in a 30x30mm arena (1024x1024px videos). Seven body part labeled (two eyes, swim bladder, four along tail)
Successful steps:
Project ini file created and loaded,
20 Videos loaded top video folder,
DLC csv files imported to csv/input_csv/original filename folder
Video parameters adjusted
Outlier correction settings of 0.7 (movement) and 1.5 (location) attempted but main screen window/log says:
Processing 0 files for location outliers...
Log for corrected "location outliers" saved in project_folder/logs
Outlier correction complete.
ROIs drawn
Features (6000 png frames) extracted to 20 folders (one per video)
Error occurs when Labeling behaviors:
video frames loaded and displayed in GUI window,
rheotaxis behaviors check box selected,
frame navigation works,
frame range selected (e.g. 3280-5005) and click save and advance to next frame:
Annotated behavior: Rheotaxis. Start frame: 3280. End frame: 5005
Click “generate / save csv” button gives the following file not found error:
(SIMBA) C:\Users\Fish_Behavior>simba
warning: Error opening file (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:901)
warning: C:/Users/Fish_Behavior/Desktop/SIMBA/1LZF_model/1LZF_model_07_28/project_folder\videos\0 (/build/opencv/modules/videoio/src/cap_ffmpeg_impl.hpp:902)
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\users\fish_behavior.conda\envs\simba\lib\tkinter_init_.py", line 1705, in call
return self.func(*args)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\SimBA.py", line 3389, in
button_setscale = Button(label_setscale,text='Set video parameters',command=lambda:video_info_table(self.projectconfigini))
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\SimBA.py", line 1050, in init
self.getdata()
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\SimBA.py", line 1100, in getdata
self.button = Button_getcoord(self.xscrollbar, self.data_lists[1], self.data_lists[5],self.pixel_list)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\SimBA.py", line 877, in init
self.ppmvar[i].set(ppmlist[i])
IndexError: list index out of range
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\users\fish_behavior.conda\envs\simba\lib\tkinter_init_.py", line 1705, in call
return self.func(*args)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\labelling_aggression.py", line 135, in
self.generate = Button(self.window, text="Generate / Save csv", command=lambda: save_video(self.window))
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\simba\labelling_aggression.py", line 474, in save_video
data = pd.read_csv(input_file)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\pandas\io\parsers.py", line 685, in parser_f
return _read(filepath_or_buffer, kwds)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\pandas\io\parsers.py", line 457, in _read
parser = TextFileReader(fp_or_buf, **kwds)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\pandas\io\parsers.py", line 895, in init
self._make_engine(self.engine)
File "c:\users\fish_behavior.conda\envs\simba\lib\site-packages\pandas\io\parsers.py", line 1135, in _make_engine
self._engine = CParserWrapper(self.f, **self.options)
File "c:\users\fish_behavior.conda\envs\simba\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\Fish_Behavior\Desktop\SIMBA\1LZF_model\1LZF_model_07_28\project_folder\csv\features_extracted\\20200318_AB_7dpf_ctl.csv' does not exist: b'C:\Users\Fish_Behavior\Desktop\SIMBA\1LZF_model\1LZF_model_07_28\project_folder\csv\features_extracted\\20200318_AB_7dpf_ctl.csv'
A clear and concise description of what the bug is.
To Reproduce
Steps to reproduce the behavior:
Expected behavior
A clear and concise description of what you expected to happen.
Screenshots
If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
Additional context
Add any other context about the problem here.
Hi again, @sgoldenlab, I had hoped it would be longer before I pestered you again!
The "Train Machine Model" step ran well for a few minutes before running into the below error:
Thoughts on how to circumvent this? I did a bit of looking around other forums (not related to SimBA) and found a suggestion that I add Graphviz to the Windows path. Thanks in advance for your help!
Is your feature request related to a problem? Please describe.
The Settings for training a machine model in SimBa have multiple options that present a predefined Value (e.g. NaN) when they are toggled. If you accept invalid settings (such as NaN) there is no feedback for the user but training the model will result in an error (often at the end of training).
See below for an example:
[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 12 concurrent workers.
[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 4.9s
[Parallel(n_jobs=-1)]: Done 176 tasks | elapsed: 26.0s
[Parallel(n_jobs=-1)]: Done 426 tasks | elapsed: 1.0min
[Parallel(n_jobs=-1)]: Done 776 tasks | elapsed: 1.9min
[Parallel(n_jobs=-1)]: Done 1226 tasks | elapsed: 3.0min
[Parallel(n_jobs=-1)]: Done 1776 tasks | elapsed: 4.4min
[Parallel(n_jobs=-1)]: Done 2000 out of 2000 | elapsed: 5.0min finished
Exception in thread Thread-1:
Traceback (most recent call last):
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "simba.py", line 3737, in trainsinglemodel
trainmodel2(self.projectconfigini)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_model_2.py", line 259, in trainmodel2
shuffle_splits = config.getint('create ensemble settings', 'LearningCurve_shuffle_k_splits')
File "D:\Anaconda\envs\simba-gpu\lib\configparser.py", line 818, in getint
fallback=fallback, **kwargs)
File "D:\Anaconda\envs\simba-gpu\lib\configparser.py", line 808, in _get_conv
**kwargs)
File "D:\Anaconda\envs\simba-gpu\lib\configparser.py", line 802, in _get
return conv(self.get(section, option, **kwargs))
ValueError: invalid literal for int() with base 10: 'NaN'
I assumed that there was a default value that would be taken if i leave the textbox 'NaN'.
Describe the solution you'd like
This is a user created issue (and i won't do it again), but it might be worthwhile to either validate the input when saving the settings (e.g. comparing if it is 'int', 'float', etc.). Then if it is invalid, setting the value to default (while telling the user) or making the user choose again. This would save some users (like me) from their own ignorance and others from wasting time training a machine model that will ultimately not be saved, because the validation process causes an error and everything is gone.
Describe alternatives you've considered
An alternative would be to validate the settings before starting the training. Simply throwing out an error (e.g. "ValueError: Some of your parameters are invalid. Consider reading the readme files again.")
Another alternative would be to check user input when pressing the save button. Similiar to a contact formular on a website. I guess this would take much more time (as it's related to gui programming) though.
Additional context
I would not document this kind of request if your overall goal wasn't to create a tool that can be used without any (or without a lot of) programming experience. SimBa is already simplifying a complicated process so much and it is doing great work!
Describe the bug
After getting the error in issue #22 , I toggled both boxes (see below) to circumvent the error #22 .
The following error occured after initializing training (or rather before it). I checked the code and it's the exception for an error in training (fitting), so could be anything? I checked both csv files if they contained the array and if it was valid (see further below).
simba/train_model_2.py:237
try:
clf.fit(data_train, target_train)
except ValueError:
print('ERROR: The model contains a faulty array. This may happen when trying to train a model with 0 examples of the behavior of interest')
I tried both train methods using global environment for 1 model and specific for 3 seperate models (as visible in the SimBa log). The console output is the same, so i didn't post the second.
Removing both boxes (Generate Features Importance Log and Graph) does not change the error (tested in the global settings method).
Settings:
SimBa - Log:
Console output:
(simba-gpu) C:\Users\schwa\PycharmProjects\simba\simba>python simba.py
Exception in thread Thread-1:
Traceback (most recent call last):
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 926, in _bootstrap_inner
self.run()
File "D:\Anaconda\envs\simba-gpu\lib\threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "simba.py", line 3734, in trainmultimodel
train_multimodel(self.projectconfigini)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_multiple_models_from_meta.py", line 263, in train_multimodel
generateClassificationReport(clf, class_names, classifierName, saveFileNo)
File "C:\Users\schwa\PycharmProjects\simba\simba\train_multiple_models_from_meta.py", line 51, in generateClassificationReport
visualizer.score(data_test, target_test)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\yellowbrick\classifier\classification_report.py", line 130, in score
y_pred = self.predict(X)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\sklearn\ensemble\_forest.py", line 612, in predict
proba = self.predict_proba(X)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\sklearn\ensemble\_forest.py", line 654, in predict_proba
check_is_fitted(self)
File "D:\Anaconda\envs\simba-gpu\lib\site-packages\sklearn\utils\validation.py", line 967, in check_is_fitted
raise NotFittedError(msg % {'name': type(estimator).__name__})
sklearn.exceptions.NotFittedError: This RandomForestClassifier instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator.
pd.Dataframe.describe() and np.sum() for both target_inserted csv files over all labelled frames (model names: 'active', 'resting' and 'inner_circle')
Dataframe 1
Dataframe.describe()
Active Resting Inner_circle
count 54892.000000 54892.000000 54892.000000
mean 0.750000 0.250000 0.394065
std 0.433017 0.433017 0.488653
min 0.000000 0.000000 0.000000
25% 0.750000 0.000000 0.000000
50% 1.000000 0.000000 0.000000
75% 1.000000 0.250000 1.000000
max 1.000000 1.000000 1.000000
np.sum()
Active 41169.0
Resting 13723.0
Inner_circle 21631.0
Dataframe 2
Dataframe.describe()
Active Resting Inner_circle
count 54892.000000 54892.000000 54892.000000
mean 0.750000 0.250000 0.394065
std 0.433017 0.433017 0.488653
min 0.000000 0.000000 0.000000
25% 0.750000 0.000000 0.000000
50% 1.000000 0.000000 0.000000
75% 1.000000 0.250000 1.000000
max 1.000000 1.000000 1.000000
np.sum()
Active 41169.0
Resting 13723.0
Inner_circle 21631.0
dtype: float64
As you can see both Dataframes (csv files) have labelled frames (with both True/1 and False/0 values). As I did the exact same thing, but with 1 csv file less, just yesterday. I am confused.
Additional context
The additional csv file was added using the provided functions. It's noteworthy that I did not label the csv file manually but added columns to the outlier corrected version via some automatic labelling method. This method worked before.
Desktop (please complete the following information):
Hello,
I am working on a maDLC project, and I have an error message when I try to import my h5 files on Simba.
Here the screenshot:
Would someone have a suggestion to fix this problem?
FYI: I labelled the body parts through DLC 2.b.5 on windows 7, then run the training and analysis on colab, modifying the first cell code to use DLC 2.b.7, and now I tried to switch on Simba on two different windows computer, one with windows7 the other with windows 10. Nothing works, always the same error.
Thank you for the help,
Best,
Dorian
Hello,
I'm attempting to create a new project using multi-animal pose estimation data from DLC. However, I am unable to import the tracking data in .H5 file format from DeepLabCut.
First I generated the Project Config, defined the tracking as multi-animal and imported the raw videos used to train the network on DLC. Yet, when i try to import the tracking data in .H5 file format from DeepLabCut from the DLC output folder "\training-datasets\iteration-0\UnaugmentedDataSet", with the .H5 file, I receive the following message on SimBA:
"Importing 0 multi-animal DLC h5 files to teh current project. All multi-animal DLC .h5 tracking files ordered and imported into SimBA project in CSV file format".
How can i solve these problems?
Thank you.
Disclaimer: This is a feature that mainly is directed at easy use and therefore is only meant as a suggestion.
I am currently trying to merge different automatic labelling approaches into one project and noticed that there is no option to add additional models after the initial project creation. This is probably connected to the consistency of the feature extraction tool, but could be easily implemented in a workaround solution (like the one i do).
Describe the solution you'd like
So far i saw the following necessary changes to add a model into an existing project:
in the project_config file add a new line in the following sections and increase the number of targets:
[SML settings]
model_dir = D:/SimBa\MovementDetector\models
model_path_1 = D:/SimBa\ProjectName\models\Existing_model1.sav
model_path_2 = D:/SimBa\ProjectName\models\Existing_model2.sav
model_path_3 = D:/SimBa\ProjectName\models\New_model.sav
no_targets = 3
target_name_1 = Existing_model1
target_name_2 = Existing_model2
target_name_3 = New_model
[threshold_settings]
threshold_1 =
threshold_2 =
threshold_3 =
[Minimum_bout_lengths]
min_bout_1 =
min_bout_2 =
min_bout_3 =
This addition to project_config file could be easily done via the app (i think) and would allow non advanced users to change the number of existing models without the need to create a new project.
With these changes and an external addition of extracted features to the necessary csv file i was able to create a new model and train it within the simba app.
Additional context
I have not tested if the feature extraction is working with all 3 models (Old_model1, old_model2, New_Model) if there are already feature extractions for the old models. You can probably elaborate if you are overwriting the feature extracted csv file or add columns to it.
Edit:
spelling
Hello everybody!
I am attempting to extract the features, but I run into this error message
I created an environment containing only python 3.6.0, then (inside the environment) I pip install simba-uw-no-tf, then conda install shapely, and conda install h5py. SimBA launches, and all the steps went fine until the extract features bit, where I get that error message. Any idea how to solve this? I am using the 1 animal 8bp config
I have install Simba using pip install simba-uw-no-tf, but when I tried launching Simba, I got the traceback below. I know this it is successfully installed because I opened the directory in my terminal (also shown below). I am using a Linux virtual machine is that changes anything.
Hello,
I'm using SimBA for the first time, and I have an issue just after clicking "import h5". The instructions are fuzzy and I cannot read what is asked. Here a picture:
I tried to recreate a new project several times, but I obtain systematically the same issue. would you have some suggestion to fix that bug?
FYI: I am using windows 10, and my training has been done on maDeeplabcut 2.2.b6 with 8bp. I worked on mov format for dlc analysis, and then I converted them in mp4 to switch on SimBA.
Thank you for the help,
Best,
Dorian
When executing SimBA.py I get the following error:
My input:
C:\ProgramData\simba\simba>python SimBA.py
Error output:
C:\ProgramData\simba\simba>python SimBA.py
ModuleNotFoundError: No module named 'numpy.core._multiarray_umath'
ImportError: numpy.core.multiarray failed to import
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "<frozen importlib._bootstrap>", line 960, in _find_and_load
SystemError: <class '_frozen_importlib._ModuleLockManager'> returned a result with an error set
ImportError: numpy.core._multiarray_umath failed to import
ImportError: numpy.core.umath failed to import
2020-04-27 14:43:13.667999: F tensorflow/python/lib/core/bfloat16.cc:675] Check failed: PyBfloat16_Type.tp_base != nullptr
Passing:
python
import numpy as np
np.__version__
returns 1.14.5, which is what is specified in the requirements.txt.
Hello,
Thank you for the new release of Simba.
I tried to install it on my mac using "pip install simba-uw-no-tf" command.
During the installation I noticed a bug: whereas this command should specify for intallation without TensorFlow, an error message appeared:
"Could not find a version that satisfies the requirement tensorflow_gpu==1.14.0..."
I added '#' before the tensorflow line in requirments, and that fixed the issue.
Nevertheless, I can not launch the program from my terminal.
Once cd in my simba folder, I tried both: "simba.py" and "pythonw simba.py" commands.
Here the error message returned:
FYI: I'm using python 3.7.6, with anaconda. I'm also using DeepLabCut 2.2.b5. Finally one friend tried also to install Simba on her Macos, and she had the same error.
Have you some suggestion to fix the bug?
Thank you very much!
Best,
Dorian
Describe the bug
ROI module is not working. After selecting the ROI's, the output CSV file appears to be empty.
To Reproduce
Steps to reproduce the behavior:
After loading the project
Expected behavior
A CSV file with analyzed ROI's
Screenshots
Desktop (please complete the following information):
Additional context
Hello everybody!
First of all, thank you so much for implementing the new features on simba! I can also see that you have added a lot of new (very clear!) documentation, and I really appreciate your effort, as I am sure it took a lot of hours. Thank you so much!
That being said, I am having some issues running the analysis of the ROI Data. All of the steps ran smoothly until then, but when I click the Analyse ROI Data button, the cmd terminal displays this:
The steps before this ran correctly, I believe, as an ROI_definitions h5 file was created
Any idea how to solve this? I am using Python 3.6.4
Rather than having the user supply the exact frame range labeled in the session to avoid erasing all previous labeling when saving (ouch I lost a lot of hours), I suggest tracking the frames actively labeled for each session, and then overwriting only those.
Describe the bug When I run simba and error about dlc appears.
(deeplabcut-py36) D:\Users\Administrator\Documents>simba
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\programdata\anaconda3\envs\deeplabcut-py36\lib\tkinter_init_.py", line 1705, in call
return self.func(*args)
File "c:\programdata\anaconda3\envs\deeplabcut-py36\lib\site-packages\simba\SimBA.py", line 1904, in
button_generatetempyaml_single = Button(label_tempyamlsingle,text='Add single video',command=lambda:generatetempyaml(self.label_set_configpath.file_path,self.label_genyamlsinglevideo.file_path))
File "c:\programdata\anaconda3\envs\deeplabcut-py36\lib\site-packages\simba\dlc_change_yamlfile.py", line 15, in generatetempyaml
deeplabcut.add_new_videos(tempyaml,[videolist],copy_videos=True)
NameError: name 'deeplabcut' is not defined
Desktop (please complete the following information):
Do you have any ideas? Thanks!
Hi
I installed the Simba (pip install simba-uw-no-tf) in my local. then i launched "simba". I am trying to create a project, after filling all fields the following error came out:
Traceback (most recent call last):
File "C:\users...\appdata\local\programspython\python37\lib\thinter_init_.py", line 1705, in call
return self.func(*args)
File "C:\users...\appdata\local\programs\python\python37\lib\site-packages\simba\simba.py", line 3056, in make_projectini
with open(no animalsPath, "r", encoding='utf8') as f:
FileNotFoundError: [errno 2] No such file or directory: 'C:\users\...\pose_configurations\no_animals\no_animals.csv
In fact the pose configurations folder is empty.
What should I do?
Hello, we are trying to run Simba as a singularity container on our cluster, the pip install fails (wxpython 4.0.1 fails to build because of older version of libgtk), we don't have root privileges on the machine so we decided to use singularity container instead.
The official 'pip3 install simba-uw-tf' ran fine and the binary was built but when we try to launch Simba get get the error(s):
` ImportError: Cannot load backend 'TkAgg' which requires the 'tk' interactive framework, as 'headless' is currently running
Singularity simba.sif:~/scratch> simba
Traceback (most recent call last):
File "/usr/local/bin/simba", line 7, in
from simba.SimBA import main
File "/usr/local/lib/python3.6/dist-packages/simba/SimBA.py", line 94, in
from simba.dpk_script.train_model import trainDPKmodel
File "/usr/local/lib/python3.6/dist-packages/simba/dpk_script/train_model.py", line 6, in
np.random.bit_generator = np.random._bit_generator
AttributeError: module 'numpy.random' has no attribute '_bit_generator'
Here is the singularity recipe file we used:
Bootstrap: docker
From: ubuntu:18.04%post
apt-get -y update && DEBIAN_FRONTEND=noninteractive
apt-get install python3-pip -y
apt-get install git -y
DEBIAN_FRONTEND="noninteractive" apt-get install tzdata python3-tk -y
apt-get install make gcc libgtk-3-dev libwebkitgtk-dev libwebkitgtk-3.0-dev libgstreamer-gl1.0-0 freeglut3 freeglut3-dev python-gst-1.0 python3-gst-1.0 libglib2.0-dev libgstreamer-plugins-base1.0-dev -y
pip3 install simba-uw-tf
pip3 install tk
Would it be possible to build a docker container for Simba, or any tips?
Hi, I'm using SimBA on some DLC output files, which I had to move to a different drive post-labelling. Now I'm not able to train the network.
Is there a config file with the project pointing to the DLC files I can access somewhere to edit to the new directory?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
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.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.