def __init__(self, dlc_cfg_path, model_snapshot):
self.dlc_cfg = load_config(dlc_cfg_path)
self.dlc_cfg["init_weights"] = model_snapshot
self.dlc_cfg['batch_size'] = 1
self.sess, self.inputs, self.outputs = setup_pose_prediction(
self.dlc_cfg)
self.tracked_parts = self.dlc_cfg['all_joints_names']
def test_net(visualise, cache_scoremaps):
logging.basicConfig(level=logging.INFO)
cfg = load_config()
dataset = create_dataset(cfg)
dataset.set_shuffle(False)
dataset.set_test_mode(True)
sess, inputs, outputs = setup_pose_prediction(cfg)
if cache_scoremaps:
out_dir = cfg.scoremap_dir
if not os.path.exists(out_dir):
os.makedirs(out_dir)
num_images = dataset.num_images
predictions = np.zeros((num_images, ), dtype=np.object)
for k in range(num_images):
print("processing image {}/{}".format(k, num_images - 1))
batch = dataset.next_batch()
outputs_np = sess.run(outputs, feed_dict={inputs: batch[Batch.inputs]})
scmap, locref = extract_cnn_output(outputs_np, cfg)
pose = argmax_pose_predict(scmap, locref, cfg.stride)
pose_refscale = np.copy(pose)
pose_refscale[:, 0:2] /= cfg.global_scale
predictions[k] = pose_refscale
if visualise:
img = np.squeeze(batch[Batch.inputs]).astype("uint8")
visualize.show_heatmaps(cfg, img, scmap, pose)
visualize.waitforbuttonpress()
if cache_scoremaps:
base = os.path.basename(batch[Batch.data_item].im_path)
raw_name = os.path.splitext(base)[0]
out_fn = os.path.join(out_dir, raw_name + ".mat")
scipy.io.savemat(out_fn,
mdict={"scoremaps": scmap.astype("float32")})
out_fn = os.path.join(out_dir, raw_name + "_locreg" + ".mat")
if cfg.location_refinement:
scipy.io.savemat(
out_fn, mdict={"locreg_pred": locref.astype("float32")})
scipy.io.savemat("predictions.mat", mdict={"joints": predictions})
sess.close()
def load_deeplabcut():
"""
Loads TensorFlow with predefined in config DeepLabCut model
:return: tuple of DeepLabCut config, TensorFlow session, inputs and outputs
"""
model = os.path.join(DLC_PATH, models_folder, MODEL)
cfg = load_config(os.path.join(model, 'test/pose_cfg.yaml'))
snapshots = sorted([sn.split('.')[0] for sn in os.listdir(model + '/train/') if "index" in sn])
cfg['init_weights'] = model + '/train/' + snapshots[-1]
sess, inputs, outputs = predict.setup_pose_prediction(cfg)
return cfg, sess, inputs, outputs
def analyze_videos(config,videos,shuffle=1,trainingsetindex=0,videotype='avi',gputouse=None,save_as_csv=False, destfolder=None):
"""
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')
You can crop the video (before analysis), by changing 'cropping'=True and setting 'x1','x2','y1','y2' in the config file. The same cropping parameters will then be used for creating the video.
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.
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).
videotype: string, optional
Checks for the extension of the video in case the input to the video is a directory.\nOnly videos with this extension are analyzed. The default is ``.avi``
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)
Examples
--------
If you want to analyze only 1 video
>>> deeplabcut.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:
>>> deeplabcut.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos'],videotype='.avi')
--------
If you want to analyze multiple videos
>>> deeplabcut.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
>>> deeplabcut.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
>>> deeplabcut.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
tf.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]
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 batchsize (based on parameters in config.yaml)
dlc_cfg['batch_size']=cfg['batch_size']
# Name for scorer:
DLCscorer = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations=trainingsiterations)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
pdindex = pd.MultiIndex.from_product([[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],names=['scorer', 'bodyparts', 'coords'])
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
##################################################
# Datafolder
##################################################
#checks if input is a directory
if [os.path.isdir(i) for i in videos] == [True]:#os.path.isdir(video)==True:
"""
Analyzes all the videos in the directory.
"""
print("Analyzing all the videos in the directory")
videofolder= videos[0]
os.chdir(videofolder)
videolist=[fn for fn in os.listdir(os.curdir) if (videotype in fn) and ('_labeled.mp4' not in fn)] #exclude labeled-videos!
Videos = sample(videolist,len(videolist)) # this is useful so multiple nets can be used to analzye simultanously
else:
if isinstance(videos,str):
if os.path.isfile(videos): # #or just one direct path!
Videos=[videos]
else:
Videos=[]
else:
Videos=[v for v in videos if os.path.isfile(v)]
if len(Videos)>0:
#looping over videos
for video in Videos:
AnalyzeVideo(video,DLCscorer,trainFraction,cfg,dlc_cfg,sess,inputs, outputs,pdindex,save_as_csv, destfolder)
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!")
def load_model(cfg, shuffle=1, trainingsetindex=0, TFGPUinference=True, modelprefix=""):
"""
Loads a tensorflow session with a DLC model from the associated configuration
Return a tensorflow session with DLC model given cfg and shuffle
Parameters:
-----------
cfg : dict
Configuration read from the project's main config.yaml file
shuffle : int, optional
which shuffle to use
trainingsetindex : int. optional
which training fraction to use, identified by its index
TFGPUinference : bool, optional
use tensorflow inference model? default = True
Returns:
--------
sess : tensorflow session
tensorflow session with DLC model from the provided configuration, shuffle, and trainingsetindex
checkpoint file path : string
the path to the checkpoint file associated with the loaded model
"""
########################
### find snapshot to use
########################
train_fraction = cfg["TrainingFraction"][trainingsetindex]
model_folder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
train_fraction, shuffle, cfg, modelprefix=modelprefix
)
),
)
path_test_config = os.path.normpath(model_folder + "/test/pose_cfg.yaml")
path_train_config = os.path.normpath(model_folder + "/train/pose_cfg.yaml")
try:
dlc_cfg = load_config(str(path_train_config))
# dlc_cfg_train = load_config(str(path_train_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, train_fraction)
)
# 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(model_folder, "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 trying to export.\n Use the function 'train_network' to train the network for shuffle %s."
% (shuffle, shuffle)
)
if len(Snapshots) == 0:
raise FileNotFoundError(
"The train folder for iteration %s and shuffle %s exists, but no snapshots were found.\n Please train this model before trying to export.\n Use the function 'train_network' to train the network for iteration %s shuffle %s."
% (cfg["iteration"], shuffle, cfg["iteration"], shuffle)
)
if cfg["snapshotindex"] == "all":
print(
"Snapshotindex is set to 'all' in the config.yaml file. 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]
####################################
### Load and setup CNN part detector
####################################
# Check if data already was generated:
dlc_cfg["init_weights"] = os.path.join(
model_folder, "train", Snapshots[snapshotindex]
)
trainingsiterations = (dlc_cfg["init_weights"].split(os.sep)[-1]).split("-")[-1]
dlc_cfg["num_outputs"] = cfg.get("num_outputs", dlc_cfg.get("num_outputs", 1))
dlc_cfg["batch_size"] = None
# load network
if TFGPUinference:
sess, _, _ = predict.setup_GPUpose_prediction(dlc_cfg)
output = ["concat_1"]
else:
sess, _, _ = predict.setup_pose_prediction(dlc_cfg)
if dlc_cfg["location_refinement"]:
output = ["Sigmoid", "pose/locref_pred/block4/BiasAdd"]
else:
output = ["Sigmoid", "pose/part_pred/block4/BiasAdd"]
input = tf.get_default_graph().get_operations()[0].name
return sess, input, output, dlc_cfg
def evaluate_multianimal_full(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
modelprefix="",
c_engine=False,
):
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.nnet import (
predict_multianimal as predictma, )
from deeplabcut.utils import auxiliaryfunctions, auxfun_multianimal
import tensorflow as tf
if "TF_CUDNN_USE_AUTOTUNE" in os.environ:
del os.environ[
"TF_CUDNN_USE_AUTOTUNE"] # was potentially set during training
tf.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
start_path = os.getcwd()
##################################################
# Load data...
##################################################
cfg = auxiliaryfunctions.read_config(config)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
TrainingFractions = [cfg["TrainingFraction"][trainingsetindex]]
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Handle data previously annotated on a different platform
sep = "/" if "/" in Data.index[0] else "\\"
if sep != os.path.sep:
Data.index = Data.index.str.replace(sep, os.path.sep)
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
all_bpts = np.asarray(
len(cfg["individuals"]) * cfg["multianimalbodyparts"] +
cfg["uniquebodyparts"])
colors = visualization.get_cmap(len(comparisonbodyparts),
name=cfg["colormap"])
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in TrainingFractions:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
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))
# TODO: IMPLEMENT for different batch sizes?
dlc_cfg["batch_size"] = 1 # due to differently sized images!!!
joints = dlc_cfg["all_joints_names"]
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0]
for fn in os.listdir(os.path.join(str(modelfolder), "train"))
if "index" in fn
])
if len(Snapshots) == 0:
print(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
else:
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
final_result = []
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split(
"-"
)[-1] # read how many training siterations that corresponds to.
# name for deeplabcut net (based on its parameters)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg,
shuffle,
trainFraction,
trainingsiterations,
modelprefix=modelprefix,
)
print(
"Running ",
DLCscorer,
" with # of trainingiterations:",
trainingsiterations,
)
(
notanalyzed,
resultsfilename,
DLCscorer,
) = auxiliaryfunctions.CheckifNotEvaluated(
str(evaluationfolder),
DLCscorer,
DLCscorerlegacy,
Snapshots[snapindex],
)
if os.path.isfile(
resultsfilename.split(".h5")[0] + "_full.pickle"):
print("Model already evaluated.", resultsfilename)
else:
if plotting:
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
# print(dlc_cfg)
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(
dlc_cfg)
PredicteData = {}
dist = np.full((len(Data), len(all_bpts)), np.nan)
conf = np.full_like(dist, np.nan)
distnorm = np.full(len(Data), np.nan)
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(
Data.index)):
image_path = os.path.join(cfg["project_path"],
imagename)
image = io.imread(image_path)
frame = img_as_ubyte(skimage.color.gray2rgb(image))
GT = Data.iloc[imageindex]
df = GT.unstack("coords").reindex(
joints, level='bodyparts')
# Evaluate PAF edge lengths to calibrate `distnorm`
temp = GT.unstack("bodyparts")[joints]
xy = temp.values.reshape(
(-1, 2, temp.shape[1])).swapaxes(1, 2)
edges = xy[:, dlc_cfg["partaffinityfield_graph"]]
lengths = np.sum(
(edges[:, :, 0] - edges[:, :, 1])**2, axis=2)
distnorm[imageindex] = np.nanmax(lengths)
# FIXME Is having an empty array vs nan really that necessary?!
groundtruthidentity = list(
df.index.get_level_values(
"individuals").to_numpy().reshape((-1, 1)))
groundtruthcoordinates = list(
df.values[:, np.newaxis])
for i, coords in enumerate(groundtruthcoordinates):
if np.isnan(coords).any():
groundtruthcoordinates[i] = np.empty(
(0, 2), dtype=float)
groundtruthidentity[i] = np.array(
[], dtype=str)
PredicteData[imagename] = {}
PredicteData[imagename]["index"] = imageindex
pred = predictma.get_detectionswithcostsandGT(
frame,
groundtruthcoordinates,
dlc_cfg,
sess,
inputs,
outputs,
outall=False,
nms_radius=dlc_cfg.nmsradius,
det_min_score=dlc_cfg.minconfidence,
c_engine=c_engine,
)
PredicteData[imagename]["prediction"] = pred
PredicteData[imagename]["groundtruth"] = [
groundtruthidentity,
groundtruthcoordinates,
GT,
]
coords_pred = pred["coordinates"][0]
probs_pred = pred["confidence"]
for bpt, xy_gt in df.groupby(level="bodyparts"):
inds_gt = np.flatnonzero(
np.all(~np.isnan(xy_gt), axis=1))
n_joint = joints.index(bpt)
xy = coords_pred[n_joint]
if inds_gt.size and xy.size:
# Pick the predictions closest to ground truth,
# rather than the ones the model has most confident in
d = cdist(xy_gt.iloc[inds_gt], xy)
rows, cols = linear_sum_assignment(d)
min_dists = d[rows, cols]
inds = np.flatnonzero(all_bpts == bpt)
sl = imageindex, inds[inds_gt[rows]]
dist[sl] = min_dists
conf[sl] = probs_pred[n_joint][
cols].squeeze()
if plotting:
fig = visualization.make_multianimal_labeled_image(
frame,
groundtruthcoordinates,
coords_pred,
probs_pred,
colors,
cfg["dotsize"],
cfg["alphavalue"],
cfg["pcutoff"],
)
visualization.save_labeled_frame(
fig,
image_path,
foldername,
imageindex in trainIndices,
)
sess.close() # closes the current tf session
# Compute all distance statistics
df_dist = pd.DataFrame(dist, columns=df.index)
df_conf = pd.DataFrame(conf, columns=df.index)
df_joint = pd.concat([df_dist, df_conf],
keys=["rmse", "conf"],
names=["metrics"],
axis=1)
df_joint = df_joint.reorder_levels(list(
np.roll(df_joint.columns.names, -1)),
axis=1)
df_joint.sort_index(axis=1,
level=["individuals", "bodyparts"],
ascending=[True, True],
inplace=True)
write_path = os.path.join(
evaluationfolder,
f"dist_{trainingsiterations}.csv")
df_joint.to_csv(write_path)
# Calculate overall prediction error
error = df_joint.xs("rmse", level="metrics", axis=1)
mask = df_joint.xs("conf", level="metrics",
axis=1) >= cfg["pcutoff"]
error_masked = error[mask]
error_train = np.nanmean(error.iloc[trainIndices])
error_train_cut = np.nanmean(
error_masked.iloc[trainIndices])
error_test = np.nanmean(error.iloc[testIndices])
error_test_cut = np.nanmean(
error_masked.iloc[testIndices])
results = [
trainingsiterations,
int(100 * trainFraction),
shuffle,
np.round(error_train, 2),
np.round(error_test, 2),
cfg["pcutoff"],
np.round(error_train_cut, 2),
np.round(error_test_cut, 2),
]
final_result.append(results)
# For OKS/PCK, compute the standard deviation error across all frames
sd = df_dist.groupby("bodyparts",
axis=1).mean().std(axis=0)
sd["distnorm"] = np.sqrt(np.nanmax(distnorm))
sd.to_csv(write_path.replace("dist.csv", "sd.csv"))
if show_errors:
string = "Results for {} training iterations: {}, shuffle {}:\n" \
"Train error: {} pixels. Test error: {} pixels.\n" \
"With pcutoff of {}:\n" \
"Train error: {} pixels. Test error: {} pixels."
print(string.format(*results))
print("##########################################")
print(
"Average Euclidean distance to GT per individual (in pixels)"
)
print(
error_masked.groupby(
'individuals',
axis=1).mean().mean().to_string())
print(
"Average Euclidean distance to GT per bodypart (in pixels)"
)
print(
error_masked.groupby(
'bodyparts',
axis=1).mean().mean().to_string())
PredicteData["metadata"] = {
"nms radius":
dlc_cfg.nmsradius,
"minimal confidence":
dlc_cfg.minconfidence,
"PAFgraph":
dlc_cfg.partaffinityfield_graph,
"all_joints":
[[i] for i in range(len(dlc_cfg.all_joints))],
"all_joints_names": [
dlc_cfg.all_joints_names[i]
for i in range(len(dlc_cfg.all_joints))
],
"stride":
dlc_cfg.get("stride", 8),
}
print(
"Done and results stored for snapshot: ",
Snapshots[snapindex],
)
dictionary = {
"Scorer": DLCscorer,
"DLC-model-config file": dlc_cfg,
"trainIndices": trainIndices,
"testIndices": testIndices,
"trainFraction": trainFraction,
}
metadata = {"data": dictionary}
auxfun_multianimal.SaveFullMultiAnimalData(
PredicteData, metadata, resultsfilename)
tf.reset_default_graph()
if len(final_result
) > 0: # Only append if results were calculated
make_results_file(final_result, evaluationfolder,
DLCscorer)
# returning to intial folder
os.chdir(str(start_path))
def analyze_videos(config,
videos,
videotype='avi',
shuffle=1,
trainingsetindex=0,
gputouse=None,
save_as_csv=False,
destfolder=None,
cropping=None):
"""
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')
You can crop the video (before analysis), by changing 'cropping'=True and setting 'x1','x2','y1','y2' in the config file. The same cropping parameters will then be used for creating the video.
Note: you can also pass cropping = [x1,x2,y1,y2] coordinates directly, that then will be used for all videos. You can of course loop over videos & pass specific coordinates for each case.
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.
Examples
--------
Windows example for analyzing 1 video
>>> deeplabcut.analyze_videos('C:\\myproject\\reaching-task\\config.yaml',['C:\\yourusername\\rig-95\\Videos\\reachingvideo1.avi'])
--------
If you want to analyze only 1 video
>>> deeplabcut.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:
>>> deeplabcut.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos'],videotype='.avi')
--------
If you want to analyze multiple videos
>>> deeplabcut.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
>>> deeplabcut.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
>>> deeplabcut.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)
vers = (tf.__version__).split('.')
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
TF.reset_default_graph()
start_path = os.getcwd(
) #record cwd to return to this directory in the end
cfg = auxiliaryfunctions.read_config(config)
if cropping is not None:
cfg['cropping'] = True
cfg['x1'], cfg['x2'], cfg['y1'], cfg['y2'] = cropping
print("Overwriting cropping parameters:", cropping)
print(
"These are used for all videos, but won't be save to the cfg file."
)
trainFraction = cfg['TrainingFraction'][trainingsetindex]
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 batchsize (based on parameters in config.yaml)
dlc_cfg['batch_size'] = cfg['batch_size']
# update number of outputs
dlc_cfg['num_outputs'] = cfg.get('num_outputs', 1)
print('num_outputs = ', dlc_cfg['num_outputs'])
# Name for scorer:
DLCscorer = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations=trainingsiterations)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
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]
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:
AnalyzeVideo(video, DLCscorer, trainFraction, cfg, dlc_cfg, sess,
inputs, outputs, pdindex, save_as_csv, destfolder)
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!"
)
else:
print("No video was found in the path/ or single video with path:",
videos)
print(
"Perhaps the videotype is distinct from the videos in the path, I was looking for:",
videotype)
return DLCscorer
def evaluate_network(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
rescale=False,
modelprefix="",
c_engine=False,
):
"""
Evaluates the network based on the saved models at different stages of the training network.\n
The evaluation results are stored in the .h5 and .csv file under the subdirectory 'evaluation_results'.
Change the snapshotindex parameter in the config file to 'all' in order to evaluate all the saved models.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
Shuffles: 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). This
variable can also be set to "all".
plotting: bool, optional
Plots the predictions on the train and test images. The default is ``False``; if provided it must be either ``True`` or ``False``
show_errors: bool, optional
Display train and test errors. The default is `True``
comparisonbodyparts: list of bodyparts, Default is "all".
The average error will be computed for those body parts only (Has to be a subset of the body parts).
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
rescale: bool, default False
Evaluate the model at the 'global_scale' variable (as set in the test/pose_config.yaml file for a particular project). I.e. every
image will be resized according to that scale and prediction will be compared to the resized ground truth. The error will be reported
in pixels at rescaled to the *original* size. I.e. For a [200,200] pixel image evaluated at global_scale=.5, the predictions are calculated
on [100,100] pixel images, compared to 1/2*ground truth and this error is then multiplied by 2!. The evaluation images are also shown for the
original size!
Examples
--------
If you do not want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml', Shuffles=[1])
--------
If you want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml',Shuffles=[1],True)
"""
import os
start_path = os.getcwd()
from deeplabcut.utils import auxiliaryfunctions
cfg = auxiliaryfunctions.read_config(config)
if cfg.get("multianimalproject", False):
from deeplabcut.pose_estimation_tensorflow.evaluate_multianimal import (
evaluate_multianimal_full, )
# TODO: Make this code not so redundant!
evaluate_multianimal_full(
config,
Shuffles,
trainingsetindex,
plotting,
show_errors,
comparisonbodyparts,
gputouse,
modelprefix,
c_engine=c_engine,
)
else:
from deeplabcut.utils.auxfun_videos import imread, imresize
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import (
data_to_input, )
from deeplabcut.utils import auxiliaryfunctions
import tensorflow as tf
if "TF_CUDNN_USE_AUTOTUNE" in os.environ:
del os.environ[
"TF_CUDNN_USE_AUTOTUNE"] # was potentially set during training
tf.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
if (trainingsetindex < len(cfg["TrainingFraction"])
and trainingsetindex >= 0):
TrainingFractions = [
cfg["TrainingFraction"][int(trainingsetindex)]
]
else:
raise Exception(
"Please check the trainingsetindex! ",
trainingsetindex,
" should be an integer from 0 .. ",
int(len(cfg["TrainingFraction"]) - 1),
)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in TrainingFractions:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction,
shuffle,
cfg,
modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
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))
# change batch size, if it was edited during analysis!
dlc_cfg[
"batch_size"] = 1 # in case this was edited for analysis.
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction,
shuffle,
cfg,
modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0] for fn in os.listdir(
os.path.join(str(modelfolder), "train"))
if "index" in fn
])
try: # check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
raise ValueError(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
final_result = []
########################### RESCALING (to global scale)
if rescale == True:
scale = dlc_cfg["global_scale"]
Data = (pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
) * scale)
else:
scale = 1
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split(
"-"
)[-1] # read how many training siterations that corresponds to.
# Name for deeplabcut net (based on its parameters)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg,
shuffle,
trainFraction,
trainingsiterations,
modelprefix=modelprefix,
)
print(
"Running ",
DLCscorer,
" with # of trainingiterations:",
trainingsiterations,
)
(
notanalyzed,
resultsfilename,
DLCscorer,
) = auxiliaryfunctions.CheckifNotEvaluated(
str(evaluationfolder),
DLCscorer,
DLCscorerlegacy,
Snapshots[snapindex],
)
if notanalyzed:
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(
dlc_cfg)
Numimages = len(Data.index)
PredicteData = np.zeros(
(Numimages, 3 * len(dlc_cfg["all_joints_names"])))
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(
Data.index)):
image = imread(os.path.join(
cfg["project_path"], imagename),
mode="RGB")
if scale != 1:
image = imresize(image, scale)
image_batch = data_to_input(image)
# Compute prediction with the CNN
outputs_np = sess.run(
outputs, feed_dict={inputs: image_batch})
scmap, locref = predict.extract_cnn_output(
outputs_np, dlc_cfg)
# Extract maximum scoring location from the heatmap, assume 1 person
pose = predict.argmax_pose_predict(
scmap, locref, dlc_cfg.stride)
PredicteData[imageindex, :] = (
pose.flatten()
) # NOTE: thereby cfg_test['all_joints_names'] should be same order as bodyparts!
sess.close() # closes the current tf session
index = pd.MultiIndex.from_product(
[
[DLCscorer],
dlc_cfg["all_joints_names"],
["x", "y", "likelihood"],
],
names=["scorer", "bodyparts", "coords"],
)
# Saving results
DataMachine = pd.DataFrame(PredicteData,
columns=index,
index=Data.index.values)
DataMachine.to_hdf(resultsfilename,
"df_with_missing",
format="table",
mode="w")
print(
"Done and results stored for snapshot: ",
Snapshots[snapindex],
)
DataCombined = pd.concat([Data.T, DataMachine.T],
axis=0,
sort=False).T
RMSE, RMSEpcutoff = pairwisedistances(
DataCombined,
cfg["scorer"],
DLCscorer,
cfg["pcutoff"],
comparisonbodyparts,
)
testerror = np.nanmean(
RMSE.iloc[testIndices].values.flatten())
trainerror = np.nanmean(
RMSE.iloc[trainIndices].values.flatten())
testerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[testIndices].values.flatten())
trainerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[trainIndices].values.flatten())
results = [
trainingsiterations,
int(100 * trainFraction),
shuffle,
np.round(trainerror, 2),
np.round(testerror, 2),
cfg["pcutoff"],
np.round(trainerrorpcutoff, 2),
np.round(testerrorpcutoff, 2),
]
final_result.append(results)
if show_errors == True:
print(
"Results for",
trainingsiterations,
" training iterations:",
int(100 * trainFraction),
shuffle,
"train error:",
np.round(trainerror, 2),
"pixels. Test error:",
np.round(testerror, 2),
" pixels.",
)
print(
"With pcutoff of",
cfg["pcutoff"],
" train error:",
np.round(trainerrorpcutoff, 2),
"pixels. Test error:",
np.round(testerrorpcutoff, 2),
"pixels",
)
if scale != 1:
print(
"The predictions have been calculated for rescaled images (and rescaled ground truth). Scale:",
scale,
)
print(
"Thereby, the errors are given by the average distances between the labels by DLC and the scorer."
)
if plotting == True:
print("Plotting...")
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
Plotting(
cfg,
comparisonbodyparts,
DLCscorer,
trainIndices,
DataCombined * 1.0 / scale,
foldername,
) # Rescaling coordinates to have figure in original size!
tf.reset_default_graph()
# print(final_result)
else:
DataMachine = pd.read_hdf(resultsfilename,
"df_with_missing")
if plotting == True:
DataCombined = pd.concat([Data.T, DataMachine.T],
axis=0,
sort=False).T
print(
"Plotting...(attention scale might be inconsistent in comparison to when data was analyzed; i.e. if you used rescale)"
)
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
Plotting(
cfg,
comparisonbodyparts,
DLCscorer,
trainIndices,
DataCombined * 1.0 / scale,
foldername,
)
if len(final_result
) > 0: # Only append if results were calculated
make_results_file(final_result, evaluationfolder,
DLCscorer)
print(
"The network is evaluated and the results are stored in the subdirectory 'evaluation_results'."
)
print(
"If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos."
)
print(
"Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)"
)
# returning to intial folder
os.chdir(str(start_path))
def extract_maps(
config,
shuffle=0,
trainingsetindex=0,
gputouse=None,
rescale=False,
Indices=None,
modelprefix="",
):
"""
Extracts the scoremap, locref, partaffinityfields (if available).
Returns a dictionary indexed by: trainingsetfraction, snapshotindex, and imageindex
for those keys, each item contains: (image,scmap,locref,paf,bpt names,partaffinity graph, imagename, True/False if this image was in trainingset)
----------
config : string
Full path of the config.yaml file as a string.
shuffle: integer
integers specifying shuffle index of the training dataset. The default is 0.
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml). This
variable can also be set to "all".
rescale: bool, default False
Evaluate the model at the 'global_scale' variable (as set in the test/pose_config.yaml file for a particular project). I.e. every
image will be resized according to that scale and prediction will be compared to the resized ground truth. The error will be reported
in pixels at rescaled to the *original* size. I.e. For a [200,200] pixel image evaluated at global_scale=.5, the predictions are calculated
on [100,100] pixel images, compared to 1/2*ground truth and this error is then multiplied by 2!. The evaluation images are also shown for the
original size!
Examples
--------
If you want to extract the data for image 0 and 103 (of the training set) for model trained with shuffle 0.
>>> deeplabcut.extract_maps(configfile,0,Indices=[0,103])
"""
from deeplabcut.utils.auxfun_videos import imread, imresize
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.nnet import (
predict_multianimal as predictma, )
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions
from tqdm import tqdm
import tensorflow as tf
vers = (tf.__version__).split(".")
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
import pandas as pd
from pathlib import Path
import numpy as np
TF.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
if trainingsetindex < len(
cfg["TrainingFraction"]) and trainingsetindex >= 0:
TrainingFractions = [
cfg["TrainingFraction"][int(trainingsetindex)]
]
else:
raise Exception(
"Please check the trainingsetindex! ",
trainingsetindex,
" should be an integer from 0 .. ",
int(len(cfg["TrainingFraction"]) - 1),
)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
Maps = {}
for trainFraction in TrainingFractions:
Maps[trainFraction] = {}
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(trainFraction,
shuffle,
cfg,
modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
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))
# change batch size, if it was edited during analysis!
dlc_cfg["batch_size"] = 1 # in case this was edited for analysis.
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0]
for fn in os.listdir(os.path.join(str(modelfolder), "train"))
if "index" in fn
])
try: # check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
########################### RESCALING (to global scale)
scale = dlc_cfg["global_scale"] if rescale else 1
Data *= scale
bptnames = [
dlc_cfg["all_joints_names"][i]
for i in range(len(dlc_cfg["all_joints"]))
]
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split("-")[
-1] # read how many training siterations that corresponds to.
# Name for deeplabcut net (based on its parameters)
# DLCscorer,DLCscorerlegacy = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations)
# notanalyzed, resultsfilename, DLCscorer=auxiliaryfunctions.CheckifNotEvaluated(str(evaluationfolder),DLCscorer,DLCscorerlegacy,Snapshots[snapindex])
# print("Extracting maps for ", DLCscorer, " with # of trainingiterations:", trainingsiterations)
# if notanalyzed: #this only applies to ask if h5 exists...
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
Numimages = len(Data.index)
PredicteData = np.zeros(
(Numimages, 3 * len(dlc_cfg["all_joints_names"])))
print("Analyzing data...")
if Indices is None:
Indices = enumerate(Data.index)
else:
Ind = [Data.index[j] for j in Indices]
Indices = enumerate(Ind)
DATA = {}
for imageindex, imagename in tqdm(Indices):
image = imread(os.path.join(cfg["project_path"], imagename),
mode="RGB")
if scale != 1:
image = imresize(image, scale)
image_batch = data_to_input(image)
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
if cfg.get("multianimalproject", False):
scmap, locref, paf = predictma.extract_cnn_output(
outputs_np, dlc_cfg)
pagraph = dlc_cfg["partaffinityfield_graph"]
else:
scmap, locref = predict.extract_cnn_output(
outputs_np, dlc_cfg)
paf = None
pagraph = []
if imageindex in testIndices:
trainingfram = False
else:
trainingfram = True
DATA[imageindex] = [
image,
scmap,
locref,
paf,
bptnames,
pagraph,
imagename,
trainingfram,
]
Maps[trainFraction][Snapshots[snapindex]] = DATA
os.chdir(str(start_path))
return Maps
def evaluate_multiview_network(config,videos,projection_matrices,multiview_step,snapshot_index=None,Shuffles=[1],plotting = None,show_errors = True,comparisonbodyparts="all",gputouse=None):
"""
Evaluates the network based on the saved models at different stages of the training network.\n
The evaluation results are stored in the .h5 and .csv file under the subdirectory 'evaluation_results'.
Change the snapshotindex parameter in the config file to 'all' in order to evaluate all the saved models.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
videos: list of strings
Name of each video, one per viewpoint. Must be in the same order that it was in for training
projection_matrices: list of arrays
Projection matrix for each viewpoint. Each is a 3x4 array
multiview_step:
1 or 2. Indicates whether network was trained with train_multiview_network_step_1 or train_multiview_network_step_2
Shuffles: list, optional
List of integers specifying the shuffle indices of the training dataset. The default is [1]
plotting: bool, optional
Plots the predictions on the train and test images. The default is ``False``; if provided it must be either ``True`` or ``False``
show_errors: bool, optional
Display train and test errors. The default is `True``
comparisonbodyparts: list of bodyparts, Default is "all".
The average error will be computed for those body parts only (Has to be a subset of the body parts).
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
Examples
--------
If you do not want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml', shuffle=[1])
--------
If you want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml',shuffle=[1],True)
"""
import os
from skimage import io
import skimage.color
from deeplabcut.pose_estimation_tensorflow.nnet import predict as ptf_predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions, visualization
import tensorflow as tf
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ['TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
tf.reset_default_graph()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path=os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
# Loading human annotatated data
trainingsetfolder=auxiliaryfunctions.GetTrainingSetFolder(cfg)
Datas = [pd.read_hdf(os.path.join(cfg['project_path'], 'labeled-data', video, 'CollectedData_'+cfg['scorer']+'.h5'), 'df_with_missing') for video in videos]
# Get list of body parts to evaluate network for
comparisonbodyparts=auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(cfg,comparisonbodyparts)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(str(cfg["project_path"]+"/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in cfg["TrainingFraction"]:
##################################################
# Load and setup CNN part detector
##################################################
datafn,metadatafn=auxiliaryfunctions.GetDataandMetaDataFilenames(trainingsetfolder,trainFraction,shuffle,cfg)
modelfolder=os.path.join(cfg["project_path"],str(auxiliaryfunctions.GetModelFolder(trainFraction,shuffle,cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
# Load meta data
metadatas = []
for video in videos:
m = ('-'+video).join(os.path.splitext(metadatafn))
data, trainIndices, testIndices, trainFraction=auxiliaryfunctions.LoadMetadata(os.path.join(cfg["project_path"],m))
metadatas.append(data)
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))
#change batch size, if it was edited during analysis!
dlc_cfg['batch_size']=1 #in case this was edited for analysis.
#Create folder structure to store results.
evaluationfolder=os.path.join(cfg["project_path"],str(auxiliaryfunctions.GetEvaluationFolder(trainFraction,shuffle,cfg)))
auxiliaryfunctions.attempttomakefolder(evaluationfolder,recursive=True)
#path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
dlc_cfg.multiview_step = multiview_step
dlc_cfg.projection_matrices = projection_matrices
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([fn.split('.')[0]for fn in os.listdir(os.path.join(str(modelfolder), 'train'))if "index" in fn])
try: #check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError("Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."%(shuffle,trainFraction))
increasing_indices = np.argsort([int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if snapshot_index is not None:
snapindices = [i for i in range(len(Snapshots)) if int(Snapshots[i].split('-')[1].split('.')[0])==snapshot_index]
elif cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"]<len(Snapshots):
snapindices=[cfg["snapshotindex"]]
else:
print("Invalid choice, only -1 (last), any integer up to last, or all (as string)!")
final_result=[]
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(str(modelfolder),'train',Snapshots[snapindex]) #setting weights to corresponding snapshot.
trainingsiterations = (dlc_cfg['init_weights'].split(os.sep)[-1]).split('-')[-1] #read how many training siterations that corresponds to.
#name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:", trainingsiterations)
resultsfilename=os.path.join(str(evaluationfolder),DLCscorer + '-' + Snapshots[snapindex]+ '.h5')
try:
DataMachine = pd.read_hdf(resultsfilename,'df_with_missing')
print("This net has already been evaluated!")
except FileNotFoundError:
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(dlc_cfg)
Numimages = len(Datas[0].index)
PredicteDatas = np.zeros((Numimages,len(Datas), 3 * len(dlc_cfg['all_joints_names'])))
imagesizes = []
print("Analyzing data...")
if multiview_step == 1:
for imageindex in tqdm(range(len(Datas[0].index))):
imagenames = [Data.index[imageindex] for Data in Datas]
images = [io.imread(os.path.join(cfg['project_path'],imagename),mode='RGB') for imagename in imagenames]
images = [skimage.color.gray2rgb(image) for image in images]
image_batch = images
imagesizes.append([image.shape for image in images])
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
scmap, locref = ptf_predict.extract_cnn_output(outputs_np, dlc_cfg)
# Extract maximum scoring location from the heatmap, assume 1 person
pose = ptf_predict.argmax_pose_predict(scmap, locref, dlc_cfg.stride)
PredicteDatas[imageindex] = pose.reshape([pose.shape[0], -1]) # NOTE: thereby cfg_test['all_joints_names'] should be same order as bodyparts!
sess.close() #closes the current tf session
index = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],
names=['scorer', 'bodyparts', 'coords'])
# Saving results
for i, video in enumerate(videos):
print('Evaluating 2D predictions on video %s'%video)
Data = Datas[i]
DataMachine = pd.DataFrame(PredicteDatas[:,i], columns=index, index=Data.index.values)
r = ('-'+video).join(os.path.splitext(resultsfilename))
DataMachine.to_hdf(r,'df_with_missing',format='table',mode='w')
print("Done and results stored for snapshot: ", Snapshots[snapindex])
DataCombined = pd.concat([Data.T, DataMachine.T], axis=0).T
RMSE,RMSEpcutoff = pairwisedistances(DataCombined, cfg["scorer"], DLCscorer,cfg["pcutoff"],comparisonbodyparts)
testerror = np.nanmean(RMSE.iloc[testIndices].values.flatten())
trainerror = np.nanmean(RMSE.iloc[trainIndices].values.flatten())
testerrorpcutoff = np.nanmean(RMSEpcutoff.iloc[testIndices].values.flatten())
trainerrorpcutoff = np.nanmean(RMSEpcutoff.iloc[trainIndices].values.flatten())
results = [trainingsiterations,int(100 * trainFraction),shuffle,np.round(trainerror,2),np.round(testerror,2),cfg["pcutoff"],np.round(trainerrorpcutoff,2), np.round(testerrorpcutoff,2)]
final_result.append(results)
if show_errors == True:
print("Results for",trainingsiterations," training iterations:", int(100 * trainFraction), shuffle, "train error:",np.round(trainerror,2), "pixels. Test error:", np.round(testerror,2)," pixels.")
print("With pcutoff of", cfg["pcutoff"]," train error:",np.round(trainerrorpcutoff,2), "pixels. Test error:", np.round(testerrorpcutoff,2), "pixels")
print("Thereby, the errors are given by the average distances between the labels by DLC and the scorer.")
if plotting == True:
print("Plotting...")
colors = visualization.get_cmap(len(comparisonbodyparts),name=cfg['colormap'])
foldername=os.path.join(str(evaluationfolder),'LabeledImages_' + DLCscorer + '_' + Snapshots[snapindex]+'_'+video)
auxiliaryfunctions.attempttomakefolder(foldername)
NumFrames=np.size(DataCombined.index)
for ind in np.arange(NumFrames):
visualization.PlottingandSaveLabeledFrame(DataCombined,ind,trainIndices,cfg,colors,comparisonbodyparts,DLCscorer,foldername)
# get predictions in homogeneous pixel coordinates
# pixel coordinates have (0,0) in the top-left, and the bottom-right coordinate is (h,w)
predictions = PredicteDatas.reshape(Numimages, len(Datas), len(dlc_cfg['all_joints_names']), 3)
scores = np.copy(predictions[:,:,:,2])
predictions[:,:,:,2] = 1.0 # homogeneous coordinates; (x,y,1). Top-left corner is (-width/2, -height/2, 1); Bottom-right corner is opposite. Shape is num_images x num_views x num_joints x 3
num_ims, num_views, num_joints, _ = predictions.shape
# get labels in homogeneous pixel coordinates
labels = np.array([Data.values.reshape(num_ims, num_joints, 2) for Data in Datas]) # num_views x num_ims x num_joints x (x,y)
labels = np.transpose(labels, [1, 2, 0, 3]) # num_ims x num_joints x num_views x (x,y)
labels = np.concatenate([labels, np.ones([num_ims, num_joints, num_views, 1])], axis=3)
# solve linear system to get labels in 3D
# helpful explanation of equation found on pg 5 here: https://hal.inria.fr/inria-00524401/PDF/Sturm-cvpr05.pdf
labs = labels.reshape([num_ims * num_joints, num_views, 3]).astype(np.float)
confidences = ~np.isnan(np.sum(labs, axis=2))
valid = np.sum(~np.isnan(np.sum(labs, axis=2)), axis=1) >= 2
labs[~confidences] = 0
labels3d = project_3d(projection_matrices, labs, confidences=confidences)
labels3d[~valid] = np.nan
labels3d = labels3d.reshape([num_ims, num_joints, 3])
# solve linear system to get 3D predictions
preds = np.transpose(predictions, [0, 2, 1, 3]) # num_ims x num_joints x num_views x 3
preds = preds.reshape([num_ims*num_joints, num_views, 3])
preds3d = project_3d(projection_matrices, preds)
preds3d = preds3d.reshape([num_ims, num_joints, 3])
# try it with confidence weighting
scores = np.transpose(scores, [0, 2, 1]) # num_images x num_joints x num_views
scores = np.reshape(scores, [num_ims*num_joints, num_views])
preds3d_weighted = project_3d(projection_matrices, preds, confidences=scores)
preds3d_weighted = preds3d_weighted.reshape([num_ims, num_joints, 3])
# try it with the pcutoff
scores2 = np.copy(scores)
scores2[scores2 < cfg["pcutoff"]] = 0
preds3d_weighted_cutoff = project_3d(projection_matrices, preds, confidences=scores2)
preds3d_weighted_cutoff = preds3d_weighted_cutoff.reshape([num_ims, num_joints, 3])
print("\n\n3D errors:")
RMSE_train = np.nanmean(np.nansum((preds3d[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test = np.nanmean(np.nansum((preds3d[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
RMSE_train_weighted = np.nanmean(np.nansum((preds3d_weighted[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test_weighted = np.nanmean(np.nansum((preds3d_weighted[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
RMSE_train_weighted_cutoff = np.nanmean(np.nansum((preds3d_weighted_cutoff[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test_weighted_cutoff = np.nanmean(np.nansum((preds3d_weighted_cutoff[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
print("RMSE train: ", RMSE_train)
print("RMSE test: ", RMSE_test)
print("RMSE train weighted: ", RMSE_train_weighted)
print("RMSE test weighted: ", RMSE_test_weighted)
print("RMSE train weighted cutoff: ", RMSE_train_weighted_cutoff)
print("RMSE test weighted cutoff: ", RMSE_test_weighted_cutoff)
tail = np.nansum((preds3d_weighted - labels3d)**2, axis=2)**0.5
tail = np.sort(tail[~np.isnan(tail)])
tail = tail[-10:]
print('10 worst predictions: ', tail)
tf.reset_default_graph()
elif multiview_step==2:
preds3d = []
for imageindex in tqdm(range(len(Datas[0].index))):
imagenames = [Data.index[imageindex] for Data in Datas]
images = [io.imread(os.path.join(cfg['project_path'],imagename),mode='RGB') for imagename in imagenames]
images = [skimage.color.gray2rgb(image) for image in images]
image_batch = images
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
pred_3d = outputs_np[2]
preds3d.append(pred_3d)
sess.close() #closes the current tf session
preds3d = np.array(preds3d) # num_ims x num_joints x (x,y,z)
num_ims, num_joints = preds3d.shape[:2]
num_views = dlc_cfg.num_views
# get labels in homogeneous pixel coordinates
labels = np.array([Data.values.reshape(num_ims, num_joints, 2) for Data in Datas]) # num_views x num_ims x num_joints x (x,y)
labels = np.transpose(labels, [1, 2, 0, 3]) # num_ims x num_joints x num_views x (x,y)
labels = np.concatenate([labels, np.ones([num_ims, num_joints, num_views, 1])], axis=3)
# solve linear system to get labels in 3D
# helpful explanation of equation found on pg 5 here: https://hal.inria.fr/inria-00524401/PDF/Sturm-cvpr05.pdf
labs = labels.reshape([num_ims * num_joints, num_views, 3]).astype(np.float)
confidences = ~np.isnan(np.sum(labs, axis=2))
valid = np.sum(~np.isnan(np.sum(labs, axis=2)), axis=1) >= 2
labs[~confidences] = 0
labels3d = project_3d(projection_matrices, labs, confidences=confidences)
labels3d[~valid] = np.nan
labels3d = labels3d.reshape([num_ims, num_joints, 3])
print("\n\n3D errors (units are determined by projection matrices):")
RMSE_train = np.nanmean(np.nansum((preds3d[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test = np.nanmean(np.nansum((preds3d[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
print("RMSE train: ", RMSE_train)
print("RMSE test: ", RMSE_test)
tail = np.nansum((preds3d- labels3d)**2, axis=2)**0.5
tail = np.sort(tail[~np.isnan(tail)])
tail = tail[-10:]
print('10 worst predictions: ', tail)
tf.reset_default_graph()
else:
print('invalid multiview_step given')
return
make_results_file(final_result,evaluationfolder,DLCscorer)
print("The network is evaluated and the results are stored in the subdirectory 'evaluation_results'.")
print("If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos.")
print("Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)")
#returning to intial folder
os.chdir(str(start_path))
def analyze_videos(config,videos, videotype='avi', shuffle=1, trainingsetindex=0,
gputouse=None, save_as_csv=False, destfolder=None, batchsize=None,
cropping=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')
You can crop the video (before analysis), by changing 'cropping'=True and setting 'x1','x2','y1','y2' in the config file. The same cropping parameters will then be used for creating the video.
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
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
>>> deeplabcut.analyze_videos('C:\\myproject\\reaching-task\\config.yaml',['C:\\yourusername\\rig-95\\Videos\\reachingvideo1.avi'])
--------
If you want to analyze only 1 video
>>> deeplabcut.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:
>>> deeplabcut.analyze_videos('/analysis/project/reaching-task/config.yaml',['/analysis/project/videos'],videotype='.avi')
--------
If you want to analyze multiple videos
>>> deeplabcut.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
>>> deeplabcut.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
>>> deeplabcut.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.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 cropping is not None:
cfg['cropping']=True
cfg['x1'],cfg['x2'],cfg['y1'],cfg['y2']=cropping
print("Overwriting cropping parameters:", cropping)
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:
print("No video/s found. Please check your path!")
return DLCscorer
def generate_prediction(MAX_PREDICTION_STEPS=1000):
"""
Generator for predicting image
MAX_PREDICTION_STEPS : Number of predictions that should be done before re-initializing
"""
##################################################
# Clone arguments from deeplabcut.evaluate_network
##################################################
config = "/root/DLCROS_ws/Surgical_Tool_Tracking/ForwardPassDeepLabCut/DaVinci-Ambar-2019-10-31/config.yaml"
Shuffles = [1]
plotting = None
show_errors = True
comparisonbodyparts = "all"
gputouse = None
# Suppress scientific notation while printing
np.set_printoptions(suppress=True)
##################################################
# SETUP everything until image prediction
##################################################
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ[
'TF_CUDNN_USE_AUTOTUNE'] # was potentially set during training
vers = tf.__version__.split('.')
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
TF.reset_default_graph()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: # gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
##############
# Cloning for-loop variables
shuffle = Shuffles[0]
trainFraction = cfg["TrainingFraction"][0]
##############
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
##################################################
# Load and setup CNN part detector
##################################################
modelfolder = os.path.join(
cfg["project_path"],
str(auxiliaryfunctions.GetModelFolder(trainFraction, shuffle, cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
# Load meta data
# data, trainIndices, testIndices, trainFraction = auxiliaryfunctions.LoadMetadata(
# os.path.join(cfg["project_path"], metadatafn))
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."
)
dlc_cfg['batch_size'] = 1 # in case this was edited for analysis.
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split('.')[0]
for fn in os.listdir(os.path.join(str(modelfolder), 'train'))
if "index" in fn
])
try: # check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle and "
"trainFraction is not trained.\nPlease train it before evaluating."
"\nUse the function 'train_network' to do so.")
increasing_indices = np.argsort([int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
##################################################
# Compute predictions over image
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(
str(modelfolder), 'train',
Snapshots[snapindex]) # setting weights to corresponding snapshot.
trainingsiterations = (dlc_cfg['init_weights'].split(
os.sep)[-1]).split('-')[
-1] # read how many training siterations that corresponds to.
# name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(cfg, shuffle,
trainFraction,
trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:",
trainingsiterations)
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(dlc_cfg)
# Using GPU for prediction
# Specifying state of model (snapshot / training state)
# sess, inputs, outputs = ptf_predict.setup_GPUpose_prediction(dlc_cfg)
print("Analyzing test image ...")
imagename = "img034.png"
image = io.imread(imagename, plugin='matplotlib')
count = 0
start_time = time.time()
while count < MAX_PREDICTION_STEPS:
##################################################
# Predict for test image once, and wait for future images to arrive
##################################################
print("Calling predict_single_image")
pose = predict_single_image(image, sess, inputs, outputs, dlc_cfg)
##################################################
# Yield prediction to caller
##################################################
image = (
yield pose
) # Receive image here ( Refer https://stackabuse.com/python-generators/ for sending/receiving in generators)
step_time = time.time()
print(f"time: {step_time-start_time}")
start_time = step_time
count += 1
if count == MAX_PREDICTION_STEPS:
print(
f"Restart prediction system, Steps have exceeded {MAX_PREDICTION_STEPS}"
)
sess.close() # closes the current tf session
TF.reset_default_graph()
##################################################
# Compute predictions over image
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(str(modelfolder), 'train',
Snapshots[snapindex]) # setting weights to corresponding snapshot.
trainingsiterations = (dlc_cfg['init_weights'].split(os.sep)[-1]).split('-')[
-1] # read how many training siterations that corresponds to.
# name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(cfg, shuffle, trainFraction, trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:", trainingsiterations)
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(dlc_cfg)
# Using GPU for prediction
# Specifying state of model (snapshot / training state)
# sess, inputs, outputs = ptf_predict.setup_GPUpose_prediction(dlc_cfg)
print("Analyzing image...")
##################################################
# Wait for image to arrive
##################################################
image_arrived = True
# dikeo
imagename = "img034.png"
def analyze_videos_multiview(config,
videos,
projection_matrices,
multiview_step,
output_folder,
snapshot_index=None,
make_labeled_video=True,
shuffle=1,
trainingsetindex=0):
"""
videos: list of strings
each string is the path to a video. Each video should pertain to a different view
projection_matrices: list of matrices
each projection matrix is a 3x4 numpy array
multiview_step: int
either 1 or 2, denoting whether network was trained via
output_folder: string
a path to a folder in which to write output
make_labeled_video: bool, optional
if True, make a video out of the labeled frames and write it to output_folder
"""
from threading import Thread, Lock
from queue import Queue
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ[
'TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
if multiview_step != 1 and multiview_step != 2:
print('multiview_step should be either 1 or 2')
return
tf.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]
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))
dlc_cfg.multiview_step = multiview_step
if multiview_step == 2:
dlc_cfg.projection_matrices = projection_matrices
# 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))
increasing_indices = np.argsort([int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if snapshot_index is not None:
snapshotindex = -1
for i in range(len(Snapshots)):
if int(Snapshots[i].split('-')[1].split('.')[0]) == snapshot_index:
snapshotindex = i
elif 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']
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]
dlc_cfg['batch_size'] = 1
# Name for scorer:
DLCscorer = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations=trainingsiterations)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
caps = [cv2.VideoCapture(video) for video in videos]
for cap in caps:
fps = cap.get(
5
) #https://docs.opencv.org/2.4/modules/highgui/doc/reading_and_writing_images_and_video.html#videocapture-get
nframes = int(cap.get(7))
duration = nframes * 1. / fps
size = (int(cap.get(4)), int(cap.get(3)))
ny, nx = size
print("Duration of video [s]: ", round(duration, 2), ", recorded with ",
round(fps, 2), "fps!")
print("Overall # of frames: ", nframes,
" found with (before cropping) frame dimensions: ", nx, ny)
start = time.time()
print('Extracting pose')
qs = [Queue(maxsize=128) for _ in caps]
q = Queue(maxsize=128)
def extract_one(cap, q):
while cap.isOpened():
ret, frame = cap.read()
if ret:
# frame = cv2.resize(frame, (482, 256))
q.put(frame)
else:
break
q.put(None)
def extract_all(q):
while True:
res = [qq.get() for qq in qs]
if any([frame is None for frame in res]):
q.put(None)
break
q.put(res)
ts = [Thread(target=extract_one, args=z) for z in zip(caps, qs)]
t = Thread(target=extract_all, args=(q, ))
for tt in ts:
tt.start()
t.start()
poses = []
counter = 0
for _ in tqdm(range(nframes)):
frames = q.get()
if frames is not None:
frames = [
cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) for frame in frames
]
frames = [img_as_ubyte(frame) for frame in frames]
out = sess.run(outputs, feed_dict={inputs: frames})
if multiview_step == 2:
poses.append(out[2])
continue
scmap, locref = predict.extract_cnn_output(out, dlc_cfg)
pose = predict.argmax_pose_predict(scmap, locref, dlc_cfg.stride)
poses.append(pose)
else:
nframes = counter
break
counter += 1
print('Extracted pose for %d frames' % nframes)
if multiview_step == 1:
poses = np.array(poses) # nframes x num_views x num_joints x 3
num_views = poses.shape[1]
results = poses.reshape([nframes, -1])
pdindex = pd.MultiIndex.from_product(
[[DLCscorer], ['view_%d' % i for i in range(poses.shape[1])],
dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],
names=['scorer', 'views', 'bodyparts', 'coords'])
results = pd.DataFrame(data=results, columns=pdindex)
results.to_hdf(os.path.join(output_folder, '2dposes.h5'),
key='results')
results.to_csv(os.path.join(output_folder, '2dposes.csv'))
poses = np.transpose(poses,
[0, 2, 1, 3]).reshape([-1, num_views,
3]) # / [[[482, 256, 1]]]
scores = np.copy(poses[:, :, 2])
poses[:, :, 2] = 1
preds3d = project_3d(projection_matrices, poses, confidences=scores)
preds3d[~np.isfinite(preds3d)] = 0
preds3d = preds3d.reshape([nframes, -1])
elif multiview_step == 2:
preds3d = np.array(poses) # nframes x num_joints x 3
preds3d = preds3d.reshape([nframes, -1])
pdindex = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'z']],
names=['scorer', 'bodyparts', 'coords'])
results = pd.DataFrame(preds3d, columns=pdindex)
results.to_hdf(os.path.join(output_folder, '3dposes.h5'), key='results')
results.to_csv(os.path.join(output_folder, '3dposes.csv'))
if make_labeled_video:
print('making 3d video')
make_3d_labeled_video(preds3d.reshape([nframes, -1, 3]), output_folder)
def analyze_time_lapse_frames(config,directory,frametype='.png',shuffle=1,trainingsetindex=0,gputouse=None,save_as_csv=False):
"""
Analyzed all images (of type = frametype) in a folder and stores the output in one file.
You can crop the frames (before analysis), by changing 'cropping'=True and setting 'x1','x2','y1','y2' in the config file.
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.
directory: string
Full path to directory containing the frames that shall be analyzed
frametype: string, optional
Checks for the file extension of the frames. Only images with this extension are analyzed. The default is ``.png``
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``
Examples
--------
If you want to analyze all frames in /analysis/project/timelapseexperiment1
>>> deeplabcut.analyze_videos('/analysis/project/reaching-task/config.yaml','/analysis/project/timelapseexperiment1')
--------
If you want to analyze all frames in /analysis/project/timelapseexperiment1
>>> deeplabcut.analyze_videos('/analysis/project/reaching-task/config.yaml','/analysis/project/timelapseexperiment1', frametype='.bmp')
--------
Note: for test purposes one can extract all frames from a video with ffmeg, e.g. ffmpeg -i testvideo.avi thumb%04d.png
"""
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ['TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
tf.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]
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 batchsize (based on parameters in config.yaml)
dlc_cfg['batch_size']=cfg['batch_size']
# Name for scorer:
DLCscorer = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations=trainingsiterations)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
pdindex = pd.MultiIndex.from_product([[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],names=['scorer', 'bodyparts', 'coords'])
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
##################################################
# Loading the images
##################################################
#checks if input is a directory
if os.path.isdir(directory)==True:
"""
Analyzes all the frames in the directory.
"""
print("Analyzing all frames in the directory: ", directory)
os.chdir(directory)
framelist=np.sort([fn for fn in os.listdir(os.curdir) if (frametype in fn)])
vname = Path(directory).stem
dataname = os.path.join(directory,vname + DLCscorer + '.h5')
try:
# Attempt to load data...
pd.read_hdf(dataname)
print("Frames already analyzed!", dataname)
except FileNotFoundError:
nframes = len(framelist)
if nframes>1:
start = time.time()
PredicteData,nframes,nx,ny=GetPosesofFrames(cfg,dlc_cfg, sess, inputs, outputs,directory,framelist,nframes,dlc_cfg['batch_size'])
stop = time.time()
if cfg['cropping']==True:
coords=[cfg['x1'],cfg['x2'],cfg['y1'],cfg['y2']]
else:
coords=[0, nx, 0, ny]
dictionary = {
"start": start,
"stop": stop,
"run_duration": stop - start,
"Scorer": DLCscorer,
"config file": dlc_cfg,
"batch_size": dlc_cfg["batch_size"],
"frame_dimensions": (ny, nx),
"nframes": nframes,
"cropping": cfg['cropping'],
"cropping_parameters": coords
}
metadata = {'data': dictionary}
print("Saving results in %s..." %(directory))
auxiliaryfunctions.SaveData(PredicteData[:nframes,:], metadata, dataname, pdindex, framelist,save_as_csv)
print("The folder was analyzed. Now your research can truly start!")
print("If the tracking is not satisfactory for some frome, consider expanding the training set.")
else:
print("No frames were found. Consider changing the path or the frametype.")
os.chdir(str(start_path))
def evaluate_network(config,
Shuffles=[1],
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None):
"""
Evaluates the network based on the saved models at different stages of the training network.\n
The evaluation results are stored in the .h5 and .csv file under the subdirectory 'evaluation_results'.
Change the snapshotindex parameter in the config file to 'all' in order to evaluate all the saved models.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
Shuffles: list, optional
List of integers specifying the shuffle indices of the training dataset. The default is [1]
plotting: bool, optional
Plots the predictions on the train and test images. The default is ``False``; if provided it must be either ``True`` or ``False``
show_errors: bool, optional
Display train and test errors. The default is `True``
comparisonbodyparts: list of bodyparts, Default is "all".
The average error will be computed for those body parts only (Has to be a subset of the body parts).
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
Examples
--------
If you do not want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml', shuffle=[1])
--------
If you want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml',shuffle=[1],True)
"""
import os
from skimage import io
import skimage.color
from deeplabcut.pose_estimation_tensorflow.nnet import predict as ptf_predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions, visualization
import tensorflow as tf
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ[
'TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
vers = (tf.__version__).split('.')
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
TF.reset_default_graph()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(cfg["project_path"], str(trainingsetfolder),
'CollectedData_' + cfg["scorer"] + '.h5'),
'df_with_missing')
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in cfg["TrainingFraction"]:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(trainFraction, shuffle,
cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
# Load meta data
data, trainIndices, testIndices, trainFraction = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
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))
#change batch size, if it was edited during analysis!
dlc_cfg['batch_size'] = 1 #in case this was edited for analysis.
#Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg)))
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
#path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split('.')[0]
for fn in os.listdir(os.path.join(str(modelfolder), 'train'))
if "index" in fn
])
try: #check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
increasing_indices = np.argsort(
[int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
final_result = []
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(
str(modelfolder), 'train', Snapshots[snapindex]
) #setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg['init_weights'].split(os.sep)[-1]
).split(
'-'
)[-1] #read how many training siterations that corresponds to.
#name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:",
trainingsiterations)
resultsfilename = os.path.join(
str(evaluationfolder),
DLCscorer + '-' + Snapshots[snapindex] + '.h5')
try:
DataMachine = pd.read_hdf(resultsfilename,
'df_with_missing')
print("This net has already been evaluated!")
except FileNotFoundError:
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(
dlc_cfg)
Numimages = len(Data.index)
PredicteData = np.zeros(
(Numimages, 3 * len(dlc_cfg['all_joints_names'])))
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(Data.index)):
image = io.imread(os.path.join(cfg['project_path'],
imagename),
mode='RGB')
image = skimage.color.gray2rgb(image)
image_batch = data_to_input(image)
# Compute prediction with the CNN
outputs_np = sess.run(outputs,
feed_dict={inputs: image_batch})
scmap, locref = ptf_predict.extract_cnn_output(
outputs_np, dlc_cfg)
# Extract maximum scoring location from the heatmap, assume 1 person
pose = ptf_predict.argmax_pose_predict(
scmap, locref, dlc_cfg.stride)
PredicteData[imageindex, :] = pose.flatten(
) # NOTE: thereby cfg_test['all_joints_names'] should be same order as bodyparts!
sess.close() #closes the current tf session
index = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'],
['x', 'y', 'likelihood']],
names=['scorer', 'bodyparts', 'coords'])
# Saving results
DataMachine = pd.DataFrame(PredicteData,
columns=index,
index=Data.index.values)
DataMachine.to_hdf(resultsfilename,
'df_with_missing',
format='table',
mode='w')
print("Done and results stored for snapshot: ",
Snapshots[snapindex])
DataCombined = pd.concat([Data.T, DataMachine.T], axis=0).T
RMSE, RMSEpcutoff = pairwisedistances(
DataCombined, cfg["scorer"], DLCscorer, cfg["pcutoff"],
comparisonbodyparts)
testerror = np.nanmean(
RMSE.iloc[testIndices].values.flatten())
trainerror = np.nanmean(
RMSE.iloc[trainIndices].values.flatten())
testerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[testIndices].values.flatten())
trainerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[trainIndices].values.flatten())
results = [
trainingsiterations,
int(100 * trainFraction), shuffle,
np.round(trainerror, 2),
np.round(testerror, 2), cfg["pcutoff"],
np.round(trainerrorpcutoff, 2),
np.round(testerrorpcutoff, 2)
]
final_result.append(results)
if show_errors == True:
print("Results for",
trainingsiterations, " training iterations:",
int(100 * trainFraction), shuffle,
"train error:",
np.round(trainerror, 2), "pixels. Test error:",
np.round(testerror, 2), " pixels.")
print("With pcutoff of",
cfg["pcutoff"], " train error:",
np.round(trainerrorpcutoff,
2), "pixels. Test error:",
np.round(testerrorpcutoff, 2), "pixels")
print(
"Thereby, the errors are given by the average distances between the labels by DLC and the scorer."
)
if plotting == True:
print("Plotting...")
colors = visualization.get_cmap(
len(comparisonbodyparts), name=cfg['colormap'])
foldername = os.path.join(
str(evaluationfolder), 'LabeledImages_' +
DLCscorer + '_' + Snapshots[snapindex])
auxiliaryfunctions.attempttomakefolder(foldername)
NumFrames = np.size(DataCombined.index)
for ind in np.arange(NumFrames):
visualization.PlottingandSaveLabeledFrame(
DataCombined, ind, trainIndices, cfg, colors,
comparisonbodyparts, DLCscorer, foldername)
TF.reset_default_graph()
#print(final_result)
make_results_file(final_result, evaluationfolder, DLCscorer)
print(
"The network is evaluated and the results are stored in the subdirectory 'evaluation_results'."
)
print(
"If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos."
)
print(
"Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)"
)
#returning to intial folder
os.chdir(str(start_path))
def evaluate_multianimal_full(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
modelprefix="",
c_engine=False,
):
"""
WIP multi animal project.
"""
import os
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.nnet import (
predict_multianimal as predictma, )
from deeplabcut.utils import auxiliaryfunctions, auxfun_multianimal
import tensorflow as tf
if "TF_CUDNN_USE_AUTOTUNE" in os.environ:
del os.environ[
"TF_CUDNN_USE_AUTOTUNE"] # was potentially set during training
tf.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
start_path = os.getcwd()
##################################################
# Load data...
##################################################
cfg = auxiliaryfunctions.read_config(config)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
TrainingFractions = [cfg["TrainingFraction"][trainingsetindex]]
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
colors = visualization.get_cmap(len(comparisonbodyparts),
name=cfg["colormap"])
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in TrainingFractions:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
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))
# TODO: IMPLEMENT for different batch sizes?
dlc_cfg["batch_size"] = 1 # due to differently sized images!!!
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0]
for fn in os.listdir(os.path.join(str(modelfolder), "train"))
if "index" in fn
])
if len(Snapshots) == 0:
print(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
else:
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
(
individuals,
uniquebodyparts,
multianimalbodyparts,
) = auxfun_multianimal.extractindividualsandbodyparts(cfg)
final_result = []
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split(
"-"
)[-1] # read how many training siterations that corresponds to.
# name for deeplabcut net (based on its parameters)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg,
shuffle,
trainFraction,
trainingsiterations,
modelprefix=modelprefix,
)
print(
"Running ",
DLCscorer,
" with # of trainingiterations:",
trainingsiterations,
)
(
notanalyzed,
resultsfilename,
DLCscorer,
) = auxiliaryfunctions.CheckifNotEvaluated(
str(evaluationfolder),
DLCscorer,
DLCscorerlegacy,
Snapshots[snapindex],
)
if os.path.isfile(
resultsfilename.split(".h5")[0] + "_full.pickle"):
print("Model already evaluated.", resultsfilename)
else:
if plotting:
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
# print(dlc_cfg)
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(
dlc_cfg)
PredicteData = {}
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(
Data.index)):
image_path = os.path.join(cfg["project_path"],
imagename)
image = io.imread(image_path)
frame = img_as_ubyte(skimage.color.gray2rgb(image))
GT = Data.iloc[imageindex]
# Storing GT data as dictionary, so it can be used for calculating connection costs
groundtruthcoordinates = []
groundtruthidentity = []
for bptindex, bpt in enumerate(
dlc_cfg["all_joints_names"]):
coords = np.zeros([len(individuals), 2
]) * np.nan
identity = []
for prfxindex, prefix in enumerate(
individuals):
if bpt in uniquebodyparts and prefix == "single":
coords[prfxindex, :] = np.array([
GT[cfg["scorer"]][prefix][bpt]
["x"],
GT[cfg["scorer"]][prefix][bpt]
["y"],
])
identity.append(prefix)
elif (bpt in multianimalbodyparts
and prefix != "single"):
coords[prfxindex, :] = np.array([
GT[cfg["scorer"]][prefix][bpt]
["x"],
GT[cfg["scorer"]][prefix][bpt]
["y"],
])
identity.append(prefix)
else:
identity.append("nix")
groundtruthcoordinates.append(
coords[np.isfinite(coords[:, 0]), :])
groundtruthidentity.append(
np.array(identity)[np.isfinite(coords[:,
0])])
PredicteData[imagename] = {}
PredicteData[imagename]["index"] = imageindex
pred = predictma.get_detectionswithcostsandGT(
frame,
groundtruthcoordinates,
dlc_cfg,
sess,
inputs,
outputs,
outall=False,
nms_radius=dlc_cfg.nmsradius,
det_min_score=dlc_cfg.minconfidence,
c_engine=c_engine,
)
PredicteData[imagename]["prediction"] = pred
PredicteData[imagename]["groundtruth"] = [
groundtruthidentity,
groundtruthcoordinates,
GT,
]
if plotting:
coords_pred = pred["coordinates"][0]
probs_pred = pred["confidence"]
fig = visualization.make_multianimal_labeled_image(
frame,
groundtruthcoordinates,
coords_pred,
probs_pred,
colors,
cfg["dotsize"],
cfg["alphavalue"],
cfg["pcutoff"],
)
visualization.save_labeled_frame(
fig,
image_path,
foldername,
imageindex in trainIndices,
)
sess.close() # closes the current tf session
PredicteData["metadata"] = {
"nms radius":
dlc_cfg.nmsradius,
"minimal confidence":
dlc_cfg.minconfidence,
"PAFgraph":
dlc_cfg.partaffinityfield_graph,
"all_joints":
[[i] for i in range(len(dlc_cfg.all_joints))],
"all_joints_names": [
dlc_cfg.all_joints_names[i]
for i in range(len(dlc_cfg.all_joints))
],
"stride":
dlc_cfg.get("stride", 8),
}
print(
"Done and results stored for snapshot: ",
Snapshots[snapindex],
)
dictionary = {
"Scorer": DLCscorer,
"DLC-model-config file": dlc_cfg,
"trainIndices": trainIndices,
"testIndices": testIndices,
"trainFraction": trainFraction,
}
metadata = {"data": dictionary}
auxfun_multianimal.SaveFullMultiAnimalData(
PredicteData, metadata, resultsfilename)
tf.reset_default_graph()
# returning to intial folder
os.chdir(str(start_path))
def analyze_stream(config,
destfolder,
shuffle=1,
trainingsetindex=0,
gputouse=0,
save_as_csv=False,
save_frames=True,
cropping=None,
baseline=True,
name="default_animal"):
"""
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')
You can crop the video (before analysis), by changing 'cropping'=True and setting 'x1','x2','y1','y2' in the config file. The same cropping parameters will then be used for creating the video.
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.
destfolder : string
Full path of the directory to which you want to output data and (optionally) saved frames.
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``
save_frames: bool, optional
Labels and saves each frame of the stream to the destfolder defined above. The default is ``False``; if provided it must be either ``True`` or ``False``
cropping: bool, optional
Selects whether to apply cropping to each frame or not. Not recommended as it increases computational overhead.
baseline: bool, optional
Selects whether the current trial is a baseline trial (movement tracking but no reinforcement) or a training trial (movement tracking with reinforcement
via water reward). If True, current trial is baseline trial; else (e.g. False), current trial is training trial.
name: string, optional
Pass in the name/subject ID of the animal to be observed in the current trial. This will ensure that the animal is named consistently in data output and
trial metadata.
Examples
--------
If you want to analyze a stream without saving anything
>>> deeplabcut.analyze_stream('/analysis/project/reaching-task/config.yaml','/analysis/project/reaching-task/output')
--------
If you want to analyze a stream and save just the labelled frames
>>> deeplabcut.analyze_stream('/analysis/project/reaching-task/config.yaml','/analysis/project/reaching-task/output', save_frames=True)
--------
If you want to analyze a stream and save both the frames and a .csv file with the coordinates of the labels
>>> deeplabcut.analyze_stream('/analysis/project/reaching-task/config.yaml','/analysis/project/reaching-task/output', save_as_csv=True, save_frames=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.reset_default_graph()
start_path = os.getcwd(
) # record cwd to return to this directory in the end
cfg = auxiliaryfunctions.read_config(config)
if cropping is not None:
cfg['cropping'] = True
cfg['x1'], cfg['x2'], cfg['y1'], cfg['y2'] = cropping
print("Overwriting cropping parameters:", cropping)
print(
"These are used for all videos, but won't be save to the cfg file."
)
trainFraction = cfg['TrainingFraction'][trainingsetindex]
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 batchsize (based on parameters in config.yaml)
dlc_cfg['batch_size'] = cfg['batch_size']
# Name for scorer:
DLCscorer = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations=trainingsiterations)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
pdindex = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],
names=['scorer', 'bodyparts', 'coords'])
if gputouse is not None: # gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
##################################################
# Set up data buffer and global variables to be used in threads
##################################################
global PredicteData
PredicteData = np.zeros((50000, 3 * len(dlc_cfg['all_joints_names'])))
global led_arr
led_arr = np.zeros((50000, 7))
global x_range
global y_range
global acc_range
x_range = list(range(0, (3 * len(dlc_cfg['all_joints_names'])), 3))
y_range = list(range(1, (3 * len(dlc_cfg['all_joints_names'])), 3))
acc_range = list(range(2, (3 * len(dlc_cfg['all_joints_names'])), 3))
global colors
colors = [(0, 0, 255), (0, 165, 255), (0, 255, 255), (0, 255, 0),
(255, 0, 0), (240, 32, 160), (0, 0, 255), (0, 165, 255)]
global empty_count
empty_count = 0
global threshold_count
AnalyzeStream(DLCscorer, trainFraction, cfg, dlc_cfg, sess, inputs,
outputs, pdindex, save_as_csv, save_frames, destfolder, name,
baseline)
