def plot_trajectories(config,
videos,
videotype='.avi',
shuffle=1,
trainingsetindex=0,
filtered=False,
displayedbodyparts='all',
showfigures=False,
destfolder=None):
"""
Plots the trajectories of various bodyparts across the video.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
videos : list
A list of strings containing the full paths to videos for analysis or a path to the directory, where all the videos with same extension are stored.
videotype: string, optional
Checks for the extension of the video in case the input to the video is a directory.\n Only videos with this extension are analyzed. The default is ``.avi``
shuffle: list, optional
List of integers specifying the shuffle indices of the training dataset. The default is [1]
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
filtered: bool, default false
Boolean variable indicating if filtered output should be plotted rather than frame-by-frame predictions. Filtered version can be calculated with deeplabcutcore.filterpredictions
displayedbodyparts: list of strings, optional
This select the body parts that are plotted in the video.
Either ``all``, then all body parts from config.yaml are used,
or a list of strings that are a subset of the full list.
E.g. ['hand','Joystick'] for the demo Reaching-Mackenzie-2018-08-30/config.yaml to select only these two body parts.
showfigures: bool, default false
If true then plots are also displayed.
destfolder: string, optional
Specifies the destination folder that was used for storing analysis data (default is the path of the video).
Example
--------
for labeling the frames
>>> deeplabcutcore.plot_trajectories('home/alex/analysis/project/reaching-task/config.yaml',['/home/alex/analysis/project/videos/reachingvideo1.avi'])
--------
"""
cfg = auxiliaryfunctions.read_config(config)
trainFraction = cfg['TrainingFraction'][trainingsetindex]
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction
) #automatically loads corresponding model (even training iteration based on snapshot index)
bodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, displayedbodyparts)
Videos = auxiliaryfunctions.Getlistofvideos(videos, videotype)
for video in Videos:
print(video)
if destfolder is None:
videofolder = str(Path(video).parents[0])
else:
videofolder = destfolder
vname = str(Path(video).stem)
print("Starting % ", videofolder, video)
notanalyzed, dataname, DLCscorer = auxiliaryfunctions.CheckifNotAnalyzed(
videofolder, vname, DLCscorer, DLCscorerlegacy, flag='checking')
if notanalyzed:
print("The video was not analyzed with this scorer:", DLCscorer)
else:
#LoadData
print("Loading ", video, "and data.")
datafound, metadata, Dataframe, DLCscorer, suffix = auxiliaryfunctions.LoadAnalyzedData(
str(videofolder), vname, DLCscorer, filtered
) #returns boolean variable if data was found and metadata + pandas array
if datafound:
basefolder = videofolder
auxiliaryfunctions.attempttomakefolder(basefolder)
auxiliaryfunctions.attempttomakefolder(
os.path.join(basefolder, 'plot-poses'))
tmpfolder = os.path.join(basefolder, 'plot-poses', vname)
auxiliaryfunctions.attempttomakefolder(tmpfolder)
PlottingResults(tmpfolder, Dataframe, DLCscorer, cfg,
bodyparts, showfigures, suffix + '.png')
print(
'Plots created! Please check the directory "plot-poses" within the video directory'
)
def filterpredictions(config,video,videotype='avi',shuffle=1,trainingsetindex=0,
filtertype='median',windowlength=5,
p_bound=.001,ARdegree=3,MAdegree=1,alpha=.01,save_as_csv=True,destfolder=None):
"""
Fits frame-by-frame pose predictions with ARIMA model (filtertype='arima') or median filter (default).
Parameter
----------
config : string
Full path of the config.yaml file as a string.
video : string
Full path of the video to extract the frame from. Make sure that this video is already analyzed.
shuffle : int, optional
The shufle index of training dataset. The extracted frames will be stored in the labeled-dataset for
the corresponding shuffle of training dataset. Default is set to 1
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
filtertype: string
Select which filter, 'arima' or 'median' filter.
windowlength: int
For filtertype='median' filters the input array using a local window-size given by windowlength. The array will automatically be zero-padded.
https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.medfilt.html The windowlenght should be an odd number.
p_bound: float between 0 and 1, optional
For filtertype 'arima' this parameter defines the likelihood below,
below which a body part will be consided as missing data for filtering purposes.
ARdegree: int, optional
For filtertype 'arima' Autoregressive degree of Sarimax model degree.
see https://www.statsmodels.org/dev/generated/statsmodels.tsa.statespace.sarimax.SARIMAX.html
MAdegree: int
For filtertype 'arima' Moving Avarage degree of Sarimax model degree.
See https://www.statsmodels.org/dev/generated/statsmodels.tsa.statespace.sarimax.SARIMAX.html
alpha: float
Significance level for detecting outliers based on confidence interval of fitted SARIMAX model.
save_as_csv: bool, optional
Saves the predictions in a .csv file. The default is ``False``; if provided it must be either ``True`` or ``False``
destfolder: string, optional
Specifies the destination folder for analysis data (default is the path of the video). Note that for subsequent analysis this
folder also needs to be passed.
Example
--------
Arima model:
deeplabcutcore.filterpredictions('C:\\myproject\\reaching-task\\config.yaml',['C:\\myproject\\trailtracking-task\\test.mp4'],shuffle=3,filterype='arima',ARdegree=5,MAdegree=2)
Use median filter over 10bins:
deeplabcutcore.filterpredictions('C:\\myproject\\reaching-task\\config.yaml',['C:\\myproject\\trailtracking-task\\test.mp4'],shuffle=3,windowlength=10)
One can then use the filtered rather than the frame-by-frame predictions by calling:
deeplabcutcore.plot_trajectories('C:\\myproject\\reaching-task\\config.yaml',['C:\\myproject\\trailtracking-task\\test.mp4'],shuffle=3,filtered=True)
deeplabcutcore.create_labeled_video('C:\\myproject\\reaching-task\\config.yaml',['C:\\myproject\\trailtracking-task\\test.mp4'],shuffle=3,filtered=True)
--------
Returns filtered pandas array with the same structure as normal output of network.
"""
cfg = auxiliaryfunctions.read_config(config)
DLCscorer,DLCscorerlegacy=auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction = cfg['TrainingFraction'][trainingsetindex])
Videos=auxiliaryfunctions.Getlistofvideos(video,videotype)
if len(Videos)>0:
for video in Videos:
if destfolder is None:
destfolder = str(Path(video).parents[0])
print("Filtering with %s model %s"%(filtertype,video))
videofolder = destfolder
vname=Path(video).stem
notanalyzed,outdataname,sourcedataname,scorer=auxiliaryfunctions.CheckifPostProcessing(destfolder,vname,DLCscorer,DLCscorerlegacy,suffix='filtered')
if notanalyzed:
Dataframe = pd.read_hdf(sourcedataname,'df_with_missing')
for bpindex,bp in tqdm(enumerate(cfg['bodyparts'])):
pdindex = pd.MultiIndex.from_product([[scorer], [bp], ['x', 'y','likelihood']],names=['scorer', 'bodyparts', 'coords'])
x,y,p=Dataframe[scorer][bp]['x'].values,Dataframe[scorer][bp]['y'].values,Dataframe[scorer][bp]['likelihood'].values
if filtertype=='arima':
meanx,CIx=FitSARIMAXModel(x,p,p_bound,alpha,ARdegree,MAdegree,False)
meany,CIy=FitSARIMAXModel(y,p,p_bound,alpha,ARdegree,MAdegree,False)
meanx[0]=x[0]
meany[0]=y[0]
else:
meanx=signal.medfilt(x,kernel_size=windowlength)
meany=signal.medfilt(y,kernel_size=windowlength)
if bpindex==0:
data = pd.DataFrame(np.hstack([np.expand_dims(meanx,axis=1),np.expand_dims(meany,axis=1),np.expand_dims(p,axis=1)]), columns=pdindex)
else:
item=pd.DataFrame(np.hstack([np.expand_dims(meanx,axis=1),np.expand_dims(meany,axis=1),np.expand_dims(p,axis=1)]), columns=pdindex)
data=pd.concat([data.T, item.T]).T
data.to_hdf(outdataname, 'df_with_missing', format='table', mode='w')
if save_as_csv:
print("Saving filtered csv poses!")
data.to_csv(outdataname.split('.h5')[0]+'.csv')
def analyze_videos(config,
videos,
videotype='avi',
shuffle=1,
trainingsetindex=0,
gputouse=None,
save_as_csv=False,
destfolder=None,
batchsize=None,
crop=None,
get_nframesfrommetadata=True,
TFGPUinference=True,
dynamic=(False, .5, 10)):
"""
Makes prediction based on a trained network. The index of the trained network is specified by parameters in the config file (in particular the variable 'snapshotindex')
Output: The labels are stored as MultiIndex Pandas Array, which contains the name of the network, body part name, (x, y) label position \n
in pixels, and the likelihood for each frame per body part. These arrays are stored in an efficient Hierarchical Data Format (HDF) \n
in the same directory, where the video is stored. However, if the flag save_as_csv is set to True, the data can also be exported in \n
comma-separated values format (.csv), which in turn can be imported in many programs, such as MATLAB, R, Prism, etc.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
videos : list
A list of strings containing the full paths to videos for analysis or a path to the directory, where all the videos with same extension are stored.
videotype: string, optional
Checks for the extension of the video in case the input to the video is a directory.\n Only videos with this extension are analyzed. The default is ``.avi``
shuffle: int, optional
An integer specifying the shuffle index of the training dataset used for training the network. The default is 1.
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
gputouse: int, optional. Natural number indicating the number of your GPU (see number in nvidia-smi). If you do not have a GPU put None.
See: https://nvidia.custhelp.com/app/answers/detail/a_id/3751/~/useful-nvidia-smi-queries
save_as_csv: bool, optional
Saves the predictions in a .csv file. The default is ``False``; if provided it must be either ``True`` or ``False``
destfolder: string, optional
Specifies the destination folder for analysis data (default is the path of the video). Note that for subsequent analysis this
folder also needs to be passed.
batchsize: int, default from pose_cfg.yaml
Change batch size for inference; if given overwrites value in pose_cfg.yaml
crop: list, optional (default=None)
List of cropping coordinates as [x1, x2, y1, y2].
Note that the same cropping parameters will then be used for all videos.
If different video crops are desired, run 'analyze_videos' on individual videos
with the corresponding cropping coordinates.
TFGPUinference: bool, default: True
Perform inference on GPU with Tensorflow code. Introduced in "Pretraining boosts out-of-domain robustness for pose estimation" by
Alexander Mathis, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis Source: https://arxiv.org/abs/1909.11229
dynamic: triple containing (state,detectiontreshold,margin)
If the state is true, then dynamic cropping will be performed. That means that if an object is detected (i.e. any body part > detectiontreshold),
then object boundaries are computed according to the smallest/largest x position and smallest/largest y position of all body parts. This window is
expanded by the margin and from then on only the posture within this crop is analyzed (until the object is lost, i.e. <detectiontreshold). The
current position is utilized for updating the crop window for the next frame (this is why the margin is important and should be set large
enough given the movement of the animal).
Examples
--------
Windows example for analyzing 1 video
>>> deeplabcutcore.analyze_videos('C:\\myproject\\reaching-task\\config.yaml',['C:\\yourusername\\rig-95\\Videos\\reachingvideo1.avi'])
--------
If you want to analyze only 1 video
>>> deeplabcutcore.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi'])
--------
If you want to analyze all videos of type avi in a folder:
>>> deeplabcutcore.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos'],videotype='.avi')
--------
If you want to analyze multiple videos
>>> deeplabcutcore.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi','/analysis/project/videos/reachingvideo2.avi'])
--------
If you want to analyze multiple videos with shuffle = 2
>>> deeplabcutcore.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi','/analysis/project/videos/reachingvideo2.avi'],shuffle=2)
--------
If you want to analyze multiple videos with shuffle = 2 and save results as an additional csv file too
>>> deeplabcutcore.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi','/analysis/project/videos/reachingvideo2.avi'],shuffle=2,save_as_csv=True)
--------
"""
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ[
'TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
if gputouse is not None: #gpu selection
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
tf.compat.v1.reset_default_graph()
start_path = os.getcwd(
) #record cwd to return to this directory in the end
cfg = auxiliaryfunctions.read_config(config)
trainFraction = cfg['TrainingFraction'][trainingsetindex]
if crop is not None:
cfg['cropping'] = True
cfg['x1'], cfg['x2'], cfg['y1'], cfg['y2'] = crop
print("Overwriting cropping parameters:", crop)
print(
"These are used for all videos, but won't be save to the cfg file."
)
modelfolder = os.path.join(
cfg["project_path"],
str(auxiliaryfunctions.GetModelFolder(trainFraction, shuffle, cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, trainFraction))
# Check which snapshots are available and sort them by # iterations
try:
Snapshots = np.array([
fn.split('.')[0]
for fn in os.listdir(os.path.join(modelfolder, 'train'))
if "index" in fn
])
except FileNotFoundError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s has not been trained/does not exist.\n Please train it before using it to analyze videos.\n Use the function 'train_network' to train the network for shuffle %s."
% (shuffle, shuffle))
if cfg['snapshotindex'] == 'all':
print(
"Snapshotindex is set to 'all' in the config.yaml file. Running video analysis with all snapshots is very costly! Use the function 'evaluate_network' to choose the best the snapshot. For now, changing snapshot index to -1!"
)
snapshotindex = -1
else:
snapshotindex = cfg['snapshotindex']
increasing_indices = np.argsort([int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
print("Using %s" % Snapshots[snapshotindex], "for model", modelfolder)
##################################################
# Load and setup CNN part detector
##################################################
# Check if data already was generated:
dlc_cfg['init_weights'] = os.path.join(modelfolder, 'train',
Snapshots[snapshotindex])
trainingsiterations = (dlc_cfg['init_weights'].split(
os.sep)[-1]).split('-')[-1]
# Update number of output and batchsize
dlc_cfg['num_outputs'] = cfg.get('num_outputs',
dlc_cfg.get('num_outputs', 1))
if batchsize == None:
#update batchsize (based on parameters in config.yaml)
dlc_cfg['batch_size'] = cfg['batch_size']
else:
dlc_cfg['batch_size'] = batchsize
cfg['batch_size'] = batchsize
if dynamic[0]: #state=true
#(state,detectiontreshold,margin)=dynamic
print("Starting analysis in dynamic cropping mode with parameters:",
dynamic)
dlc_cfg['num_outputs'] = 1
TFGPUinference = False
dlc_cfg['batch_size'] = 1
print(
"Switching batchsize to 1, num_outputs (per animal) to 1 and TFGPUinference to False (all these features are not supported in this mode)."
)
# Name for scorer:
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations=trainingsiterations)
if dlc_cfg['num_outputs'] > 1:
if TFGPUinference:
print(
"Switching to numpy-based keypoint extraction code, as multiple point extraction is not supported by TF code currently."
)
TFGPUinference = False
print("Extracting ", dlc_cfg['num_outputs'], "instances per bodypart")
xyz_labs_orig = ['x', 'y', 'likelihood']
suffix = [str(s + 1) for s in range(dlc_cfg['num_outputs'])]
suffix[
0] = '' # first one has empty suffix for backwards compatibility
xyz_labs = [x + s for s in suffix for x in xyz_labs_orig]
else:
xyz_labs = ['x', 'y', 'likelihood']
#sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
if TFGPUinference:
sess, inputs, outputs = predict.setup_GPUpose_prediction(dlc_cfg)
else:
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
pdindex = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'], xyz_labs],
names=['scorer', 'bodyparts', 'coords'])
##################################################
# Datafolder
##################################################
Videos = auxiliaryfunctions.Getlistofvideos(videos, videotype)
if len(Videos) > 0:
#looping over videos
for video in Videos:
DLCscorer = AnalyzeVideo(video, DLCscorer, DLCscorerlegacy,
trainFraction, cfg, dlc_cfg, sess, inputs,
outputs, pdindex, save_as_csv, destfolder,
TFGPUinference, dynamic)
os.chdir(str(start_path))
print(
"The videos are analyzed. Now your research can truly start! \n You can create labeled videos with 'create_labeled_video'."
)
print(
"If the tracking is not satisfactory for some videos, consider expanding the training set. You can use the function 'extract_outlier_frames' to extract any outlier frames!"
)
return DLCscorer #note: this is either DLCscorer or DLCscorerlegacy depending on what was used!
else:
os.chdir(str(start_path))
print("No video/s found. Please check your path!")
return DLCscorer
def extract_outlier_frames(
config,
videos,
videotype="avi",
shuffle=1,
trainingsetindex=0,
outlieralgorithm="jump",
comparisonbodyparts="all",
epsilon=20,
p_bound=0.01,
ARdegree=3,
MAdegree=1,
alpha=0.01,
extractionalgorithm="kmeans",
automatic=False,
cluster_resizewidth=30,
cluster_color=False,
opencv=True,
savelabeled=True,
destfolder=None,
):
"""
Extracts the outlier frames in case, the predictions are not correct for a certain video from the cropped video running from
start to stop as defined in config.yaml.
Another crucial parameter in config.yaml is how many frames to extract 'numframes2extract'.
Parameter
----------
config : string
Full path of the config.yaml file as a string.
videos : list
A list of strings containing the full paths to videos for analysis or a path to the directory, where all the videos with same extension are stored.
videotype: string, optional
Checks for the extension of the video in case the input to the video is a directory.\n Only videos with this extension are analyzed. The default is ``.avi``
shuffle : int, optional
The shufle index of training dataset. The extracted frames will be stored in the labeled-dataset for
the corresponding shuffle of training dataset. Default is set to 1
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
outlieralgorithm: 'fitting', 'jump', 'uncertain', or 'manual'
String specifying the algorithm used to detect the outliers. Currently, deeplabcut supports three methods + a manual GUI option. 'Fitting'
fits a Auto Regressive Integrated Moving Average model to the data and computes the distance to the estimated data. Larger distances than
epsilon are then potentially identified as outliers. The methods 'jump' identifies larger jumps than 'epsilon' in any body part; and 'uncertain'
looks for frames with confidence below p_bound. The default is set to ``jump``.
comparisonbodyparts: list of strings, optional
This select the body parts for which the comparisons with the outliers are carried out. Either ``all``, then all body parts
from config.yaml are used orr a list of strings that are a subset of the full list.
E.g. ['hand','Joystick'] for the demo Reaching-Mackenzie-2018-08-30/config.yaml to select only these two body parts.
p_bound: float between 0 and 1, optional
For outlieralgorithm 'uncertain' this parameter defines the likelihood below, below which a body part will be flagged as a putative outlier.
epsilon; float,optional
Meaning depends on outlieralgoritm. The default is set to 20 pixels.
For outlieralgorithm 'fitting': Float bound according to which frames are picked when the (average) body part estimate deviates from model fit
For outlieralgorithm 'jump': Float bound specifying the distance by which body points jump from one frame to next (Euclidean distance)
ARdegree: int, optional
For outlieralgorithm 'fitting': Autoregressive degree of ARIMA model degree. (Note we use SARIMAX without exogeneous and seasonal part)
see https://www.statsmodels.org/dev/generated/statsmodels.tsa.statespace.sarimax.SARIMAX.html
MAdegree: int
For outlieralgorithm 'fitting': MovingAvarage degree of ARIMA model degree. (Note we use SARIMAX without exogeneous and seasonal part)
See https://www.statsmodels.org/dev/generated/statsmodels.tsa.statespace.sarimax.SARIMAX.html
alpha: float
Significance level for detecting outliers based on confidence interval of fitted ARIMA model. Only the distance is used however.
extractionalgorithm : string, optional
String specifying the algorithm to use for selecting the frames from the identified putatative outlier frames. Currently, deeplabcut
supports either ``kmeans`` or ``uniform`` based selection (same logic as for extract_frames).
The default is set to``uniform``, if provided it must be either ``uniform`` or ``kmeans``.
automatic : bool, optional
Set it to True, if you want to extract outliers without being asked for user feedback.
cluster_resizewidth: number, default: 30
For k-means one can change the width to which the images are downsampled (aspect ratio is fixed).
cluster_color: bool, default: False
If false then each downsampled image is treated as a grayscale vector (discarding color information). If true, then the color channels are considered. This increases
the computational complexity.
opencv: bool, default: True
Uses openCV for loading & extractiong (otherwise moviepy (legacy))
savelabeled: bool, default: True
If true also saves frame with predicted labels in each folder.
destfolder: string, optional
Specifies the destination folder that was used for storing analysis data (default is the path of the video).
Examples
Windows example for extracting the frames with default settings
>>> deeplabcutcore.extract_outlier_frames('C:\\myproject\\reaching-task\\config.yaml',['C:\\yourusername\\rig-95\\Videos\\reachingvideo1.avi'])
--------
for extracting the frames with default settings
>>> deeplabcutcore.extract_outlier_frames('/analysis/project/reaching-task/config.yaml',['/analysis/project/video/reachinvideo1.avi'])
--------
for extracting the frames with kmeans
>>> deeplabcutcore.extract_outlier_frames('/analysis/project/reaching-task/config.yaml',['/analysis/project/video/reachinvideo1.avi'],extractionalgorithm='kmeans')
--------
for extracting the frames with kmeans and epsilon = 5 pixels.
>>> deeplabcutcore.extract_outlier_frames('/analysis/project/reaching-task/config.yaml',['/analysis/project/video/reachinvideo1.avi'],epsilon = 5,extractionalgorithm='kmeans')
--------
"""
cfg = auxiliaryfunctions.read_config(config)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction=cfg["TrainingFraction"][trainingsetindex]
)
Videos = auxiliaryfunctions.Getlistofvideos(videos, videotype)
for video in Videos:
if destfolder is None:
videofolder = str(Path(video).parents[0])
else:
videofolder = destfolder
notanalyzed, dataname, DLCscorer = auxiliaryfunctions.CheckifNotAnalyzed(
videofolder,
str(Path(video).stem),
DLCscorer,
DLCscorerlegacy,
flag="checking",
)
if notanalyzed:
print(
"It seems the video has not been analyzed yet, or the video is not found! You can only refine the labels after the a video is analyzed. Please run 'analyze_video' first. Or, please double check your video file path"
)
else:
Dataframe = pd.read_hdf(dataname, "df_with_missing")
scorer = Dataframe.columns.get_level_values(0)[0] # reading scorer from
nframes = np.size(Dataframe.index)
# extract min and max index based on start stop interval.
startindex = max([int(np.floor(nframes * cfg["start"])), 0])
stopindex = min([int(np.ceil(nframes * cfg["stop"])), nframes])
Index = np.arange(stopindex - startindex) + startindex
# figure out body part list:
bodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts
)
Indices = []
if (
outlieralgorithm == "uncertain"
): # necessary parameters: considered body parts and
for bpindex, bp in enumerate(bodyparts):
if (
bp in cfg["bodyparts"]
): # filter [who knows what users put in...]
p = Dataframe[scorer][bp]["likelihood"].values[Index]
Indices.extend(
np.where(p < p_bound)[0] + startindex
) # all indices between start and stop that are below p_bound.
elif outlieralgorithm == "jump":
for bpindex, bp in enumerate(bodyparts):
if (
bp in cfg["bodyparts"]
): # filter [who knows what users put in...]
dx = np.diff(Dataframe[scorer][bp]["x"].values[Index])
dy = np.diff(Dataframe[scorer][bp]["y"].values[Index])
# all indices between start and stop with jump larger than epsilon (leading up to this point!)
Indices.extend(
np.where((dx ** 2 + dy ** 2) > epsilon ** 2)[0]
+ startindex
+ 1
)
elif outlieralgorithm == "fitting":
# deviation_dataname = str(Path(videofolder)/Path(dataname))
# Calculate deviatons for video
[d, o] = ComputeDeviations(
Dataframe,
cfg,
bodyparts,
scorer,
dataname,
p_bound,
alpha,
ARdegree,
MAdegree,
)
# Some heuristics for extracting frames based on distance:
Indices = np.where(d > epsilon)[
0
] # time points with at least average difference of epsilon
if (
len(Index) < cfg["numframes2pick"] * 2
and len(d) > cfg["numframes2pick"] * 2
): # if too few points qualify, extract the most distant ones.
Indices = np.argsort(d)[::-1][: cfg["numframes2pick"] * 2]
elif outlieralgorithm == "manual":
wd = Path(config).resolve().parents[0]
os.chdir(str(wd))
from deeplabcutcore.refine_training_dataset import (
outlier_frame_extraction_toolbox,
)
outlier_frame_extraction_toolbox.show(
config, video, shuffle, Dataframe, scorer, savelabeled
)
# Run always except when the outlieralgorithm == manual.
if not outlieralgorithm == "manual":
Indices = np.sort(list(set(Indices))) # remove repetitions.
print(
"Method ",
outlieralgorithm,
" found ",
len(Indices),
" putative outlier frames.",
)
print(
"Do you want to proceed with extracting ",
cfg["numframes2pick"],
" of those?",
)
if outlieralgorithm == "uncertain":
print(
"If this list is very large, perhaps consider changing the paramters (start, stop, p_bound, comparisonbodyparts) or use a different method."
)
elif outlieralgorithm == "jump":
print(
"If this list is very large, perhaps consider changing the paramters (start, stop, epsilon, comparisonbodyparts) or use a different method."
)
elif outlieralgorithm == "fitting":
print(
"If this list is very large, perhaps consider changing the paramters (start, stop, epsilon, ARdegree, MAdegree, alpha, comparisonbodyparts) or use a different method."
)
if automatic == False:
askuser = input("yes/no")
else:
askuser = "******"
if (
askuser == "y"
or askuser == "yes"
or askuser == "Ja"
or askuser == "ha"
): # multilanguage support :)
# Now extract from those Indices!
ExtractFramesbasedonPreselection(
Indices,
extractionalgorithm,
Dataframe,
dataname,
scorer,
video,
cfg,
config,
opencv,
cluster_resizewidth,
cluster_color,
savelabeled,
)
else:
print(
"Nothing extracted, please change the parameters and start again..."
)
def create_labeled_video(
config,
videos,
videotype="avi",
shuffle=1,
trainingsetindex=0,
filtered=False,
save_frames=False,
Frames2plot=None,
delete=False,
displayedbodyparts="all",
codec="mp4v",
outputframerate=None,
destfolder=None,
draw_skeleton=False,
trailpoints=0,
displaycropped=False,
):
"""
Labels the bodyparts in a video. Make sure the video is already analyzed by the function 'analyze_video'
Parameters
----------
config : string
Full path of the config.yaml file as a string.
videos : list
A list of strings containing the full paths to videos for analysis or a path to the directory, where all the videos with same extension are stored.
videotype: string, optional
Checks for the extension of the video in case the input to the video is a directory.\n Only videos with this extension are analyzed. The default is ``.avi``
shuffle : int, optional
Number of shuffles of training dataset. Default is set to 1.
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
filtered: bool, default false
Boolean variable indicating if filtered output should be plotted rather than frame-by-frame predictions. Filtered version can be calculated with deeplabcutcore.filterpredictions
videotype: string, optional
Checks for the extension of the video in case the input is a directory.\nOnly videos with this extension are analyzed. The default is ``.avi``
save_frames: bool
If true creates each frame individual and then combines into a video. This variant is relatively slow as
it stores all individual frames. However, it uses matplotlib to create the frames and is therefore much more flexible (one can set transparency of markers, crop, and easily customize).
Frames2plot: List of indices
If not None & save_frames=True then the frames corresponding to the index will be plotted. For example, Frames2plot=[0,11] will plot the first and the 12th frame.
delete: bool
If true then the individual frames created during the video generation will be deleted.
displayedbodyparts: list of strings, optional
This select the body parts that are plotted in the video. Either ``all``, then all body parts
from config.yaml are used orr a list of strings that are a subset of the full list.
E.g. ['hand','Joystick'] for the demo Reaching-Mackenzie-2018-08-30/config.yaml to select only these two body parts.
codec: codec for labeled video. Options see http://www.fourcc.org/codecs.php [depends on your ffmpeg installation.]
outputframerate: positive number, output frame rate for labeled video (only available for the mode with saving frames.) By default: None, which results in the original video rate.
destfolder: string, optional
Specifies the destination folder that was used for storing analysis data (default is the path of the video).
draw_skeleton: bool
If ``True`` adds a line connecting the body parts making a skeleton on on each frame. The body parts to be connected and the color of these connecting lines are specified in the config file. By default: ``False``
trailpoints: int
Number of revious frames whose body parts are plotted in a frame (for displaying history). Default is set to 0.
displaycropped: bool, optional
Specifies whether only cropped frame is displayed (with labels analyzed therein), or the original frame with the labels analyzed in the cropped subset.
Examples
--------
If you want to create the labeled video for only 1 video
>>> deeplabcutcore.create_labeled_video('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi'])
--------
If you want to create the labeled video for only 1 video and store the individual frames
>>> deeplabcutcore.create_labeled_video('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi'],save_frames=True)
--------
If you want to create the labeled video for multiple videos
>>> deeplabcutcore.create_labeled_video('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/reachingvideo1.avi','/analysis/project/videos/reachingvideo2.avi'])
--------
If you want to create the labeled video for all the videos (as .avi extension) in a directory.
>>> deeplabcutcore.create_labeled_video('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/'])
--------
If you want to create the labeled video for all the videos (as .mp4 extension) in a directory.
>>> deeplabcutcore.create_labeled_video('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos/'],videotype='mp4')
--------
"""
cfg = auxiliaryfunctions.read_config(config)
start_path = os.getcwd() # record cwd to return to this directory in the end
trainFraction = cfg["TrainingFraction"][trainingsetindex]
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction
) # automatically loads corresponding model (even training iteration based on snapshot index)
bodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, displayedbodyparts
)
if draw_skeleton:
bodyparts2connect = cfg["skeleton"]
skeleton_color = cfg["skeleton_color"]
else:
bodyparts2connect = None
skeleton_color = None
Videos = auxiliaryfunctions.Getlistofvideos(videos, videotype)
for video in Videos:
if destfolder is None:
videofolder = Path(video).parents[0] # where your folder with videos is.
else:
videofolder = destfolder
os.chdir(str(videofolder))
videotype = Path(video).suffix
print("Starting % ", videofolder, videos)
vname = str(Path(video).stem)
# if notanalyzed:
# notanalyzed,outdataname,sourcedataname,DLCscorer=auxiliaryfunctions.CheckifPostProcessing(folder,vname,DLCscorer,DLCscorerlegacy,suffix='checking')
if filtered == True:
videooutname1 = os.path.join(vname + DLCscorer + "filtered_labeled.mp4")
videooutname2 = os.path.join(
vname + DLCscorerlegacy + "filtered_labeled.mp4"
)
else:
videooutname1 = os.path.join(vname + DLCscorer + "_labeled.mp4")
videooutname2 = os.path.join(vname + DLCscorerlegacy + "_labeled.mp4")
if os.path.isfile(videooutname1) or os.path.isfile(videooutname2):
print("Labeled video already created.")
else:
print("Loading ", video, "and data.")
datafound, metadata, Dataframe, DLCscorer, suffix = auxiliaryfunctions.LoadAnalyzedData(
str(videofolder), vname, DLCscorer, filtered
) # returns boolean variable if data was found and metadata + pandas array
videooutname = os.path.join(vname + DLCscorer + suffix + "_labeled.mp4")
if datafound and not os.path.isfile(
videooutname
): # checking again, for this loader video could exist
# Loading cropping data used during analysis
cropping = metadata["data"]["cropping"]
[x1, x2, y1, y2] = metadata["data"]["cropping_parameters"]
if save_frames == True:
tmpfolder = os.path.join(str(videofolder), "temp-" + vname)
auxiliaryfunctions.attempttomakefolder(tmpfolder)
clip = vp(video)
CreateVideoSlow(
videooutname,
clip,
Dataframe,
tmpfolder,
cfg["dotsize"],
cfg["colormap"],
cfg["alphavalue"],
cfg["pcutoff"],
trailpoints,
cropping,
x1,
x2,
y1,
y2,
delete,
DLCscorer,
bodyparts,
outputframerate,
Frames2plot,
bodyparts2connect,
skeleton_color,
draw_skeleton,
displaycropped,
)
else:
if (
displaycropped
): # then the cropped video + the labels is depicted
clip = vp(
fname=video,
sname=videooutname,
codec=codec,
sw=x2 - x1,
sh=y2 - y1,
)
CreateVideo(
clip,
Dataframe,
cfg["pcutoff"],
cfg["dotsize"],
cfg["colormap"],
DLCscorer,
bodyparts,
trailpoints,
cropping,
x1,
x2,
y1,
y2,
bodyparts2connect,
skeleton_color,
draw_skeleton,
displaycropped,
)
else: # then the full video + the (perhaps in cropped mode analyzed labels) are depicted
clip = vp(fname=video, sname=videooutname, codec=codec)
CreateVideo(
clip,
Dataframe,
cfg["pcutoff"],
cfg["dotsize"],
cfg["colormap"],
DLCscorer,
bodyparts,
trailpoints,
cropping,
x1,
x2,
y1,
y2,
bodyparts2connect,
skeleton_color,
draw_skeleton,
displaycropped,
)
os.chdir(str(start_path))
def analyzeskeleton(
config,
videos,
videotype="avi",
shuffle=1,
trainingsetindex=0,
save_as_csv=False,
destfolder=None,
):
"""
Extracts length and orientation of each "bone" of the skeleton as defined in the config file.
Parameter
----------
config : string
Full path of the config.yaml file as a string.
videos : list
A list of strings containing the full paths to videos for analysis or a path to the directory, where all the videos with same extension are stored.
shuffle : int, optional
The shufle index of training dataset. The extracted frames will be stored in the labeled-dataset for
the corresponding shuffle of training dataset. Default is set to 1
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
save_as_csv: bool, optional
Saves the predictions in a .csv file. The default is ``False``; if provided it must be either ``True`` or ``False``
destfolder: string, optional
Specifies the destination folder for analysis data (default is the path of the video). Note that for subsequent analysis this
folder also needs to be passed.
"""
# Load config file, scorer and videos
cfg = auxiliaryfunctions.read_config(config)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction=cfg["TrainingFraction"][trainingsetindex]
)
Videos = auxiliaryfunctions.Getlistofvideos(videos, videotype)
for video in Videos:
print("Processing %s" % (video))
if destfolder is None:
destfolder = str(Path(video).parents[0])
vname = Path(video).stem
notanalyzed, outdataname, sourcedataname, scorer = auxiliaryfunctions.CheckifPostProcessing(
destfolder, vname, DLCscorer, DLCscorerlegacy, suffix="_skeleton"
)
if notanalyzed:
Dataframe = pd.read_hdf(sourcedataname, "df_with_missing")
# Process skeleton
bones = {}
for bp1, bp2 in cfg["skeleton"]:
name = "{}_{}".format(bp1, bp2)
bones[name] = analyzebone(
Dataframe[scorer][bp1], Dataframe[scorer][bp2]
)
skeleton = pd.concat(bones, axis=1)
# save
skeleton.to_hdf(outdataname, "df_with_missing", format="table", mode="w")
if save_as_csv:
skeleton.to_csv(outdataname.split(".h5")[0] + ".csv")