def cross_validate_paf_graphs(
config,
inference_config,
full_data_file,
metadata_file,
output_name="",
pcutoff=0.1,
greedy=False,
add_discarded=True,
calibrate=False,
overwrite_config=True,
):
cfg = auxiliaryfunctions.read_config(config)
inf_cfg = auxiliaryfunctions.read_plainconfig(inference_config)
inf_cfg_temp = inf_cfg.copy()
inf_cfg_temp["pcutoff"] = pcutoff
with open(full_data_file, "rb") as file:
data = pickle.load(file)
with open(metadata_file, "rb") as file:
metadata = pickle.load(file)
params = _set_up_evaluation(data)
to_ignore = _filter_unwanted_paf_connections(config, params["paf_graph"])
paf_inds, paf_scores = _get_n_best_paf_graphs(
data, metadata, params["paf_graph"], ignore_inds=to_ignore
)
if calibrate:
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
calibration_file = os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
)
else:
calibration_file = ""
results = _benchmark_paf_graphs(
cfg,
inf_cfg_temp,
data,
paf_inds,
greedy,
add_discarded,
calibration_file=calibration_file,
)
# Select optimal PAF graph
df = results[1]
size_opt = np.argmax((1 - df.loc["miss", "mean"]) * df.loc["purity", "mean"])
pose_config = inference_config.replace("inference_cfg", "pose_cfg")
if not overwrite_config:
shutil.copy(pose_config, pose_config.replace(".yaml", "_old.yaml"))
inds = list(paf_inds[size_opt])
auxiliaryfunctions.edit_config(
pose_config, {"paf_best": [int(ind) for ind in inds]}
)
if output_name:
with open(output_name, "wb") as file:
pickle.dump([results], file)
def create_training_dataset(
config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
userfeedback=False,
trainIndices=None,
testIndices=None,
net_type=None,
augmenter_type=None,
):
"""
Creates a training dataset. Labels from all the extracted frames are merged into a single .h5 file.\n
Only the videos included in the config file are used to create this dataset.\n
[OPTIONAL] Use the function 'add_new_video' at any stage of the project to add more videos to the project.
Parameter
----------
config : string
Full path of the config.yaml file as a string.
num_shuffles : int, optional
Number of shuffles of training dataset to create, i.e. [1,2,3] for num_shuffles=3. Default is set to 1.
Shuffles: list of shuffles.
Alternatively the user can also give a list of shuffles (integers!).
windows2linux: bool.
The annotation files contain path formated according to your operating system. If you label on windows
but train & evaluate on a unix system (e.g. ubunt, colab, Mac) set this variable to True to convert the paths.
userfeedback: bool, optional
If this is set to false, then all requested train/test splits are created (no matter if they already exist). If you
want to assure that previous splits etc. are not overwritten, then set this to True and you will be asked for each split.
trainIndices: list of lists, optional (default=None)
List of one or multiple lists containing train indexes.
A list containing two lists of training indexes will produce two splits.
testIndices: list of lists, optional (default=None)
List of one or multiple lists containing test indexes.
net_type: string
Type of networks. Currently resnet_50, resnet_101, resnet_152, mobilenet_v2_1.0,mobilenet_v2_0.75, mobilenet_v2_0.5, and mobilenet_v2_0.35 are supported.
augmenter_type: string
Type of augmenter. Currently default, imgaug, tensorpack, and deterministic are supported.
Example
--------
>>> deeplabcut.create_training_dataset('/analysis/project/reaching-task/config.yaml',num_shuffles=1)
Windows:
>>> deeplabcut.create_training_dataset('C:\\Users\\Ulf\\looming-task\\config.yaml',Shuffles=[3,17,5])
--------
"""
import scipy.io as sio
# Loading metadata from config file:
cfg = auxiliaryfunctions.read_config(config)
if cfg.get("multianimalproject", False):
from deeplabcut.generate_training_dataset.multiple_individuals_trainingsetmanipulation import (
create_multianimaltraining_dataset, )
create_multianimaltraining_dataset(config, num_shuffles, Shuffles,
windows2linux, net_type)
else:
scorer = cfg["scorer"]
project_path = cfg["project_path"]
# Create path for training sets & store data there
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(
cfg) # Path concatenation OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(
os.path.join(project_path, str(trainingsetfolder))),
recursive=True)
Data = merge_annotateddatasets(
cfg, Path(os.path.join(project_path, trainingsetfolder)),
windows2linux)
if Data is None:
return
Data = Data[scorer] # extract labeled data
# loading & linking pretrained models
if net_type is None: # loading & linking pretrained models
net_type = cfg.get("default_net_type", "resnet_50")
else:
if "resnet" in net_type or "mobilenet" in net_type:
pass
else:
raise ValueError("Invalid network type:", net_type)
if augmenter_type is None:
augmenter_type = cfg.get("default_augmenter", "imgaug")
if augmenter_type is None: # this could be in config.yaml for old projects!
# updating variable if null/None! #backwardscompatability
auxiliaryfunctions.edit_config(config,
{"default_augmenter": "imgaug"})
augmenter_type = "imgaug"
else:
if augmenter_type in [
"default",
"scalecrop",
"imgaug",
"tensorpack",
"deterministic",
]:
pass
else:
raise ValueError("Invalid augmenter type:", augmenter_type)
# Loading the encoder (if necessary downloading from TF)
dlcparent_path = auxiliaryfunctions.get_deeplabcut_path()
defaultconfigfile = os.path.join(dlcparent_path, "pose_cfg.yaml")
model_path, num_shuffles = auxfun_models.Check4weights(
net_type, Path(dlcparent_path), num_shuffles)
if Shuffles is None:
Shuffles = range(1, num_shuffles + 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
# print(trainIndices,testIndices, Shuffles, augmenter_type,net_type)
if trainIndices is None and testIndices is None:
splits = [(
trainFraction,
shuffle,
SplitTrials(range(len(Data.index)), trainFraction),
) for trainFraction in cfg["TrainingFraction"]
for shuffle in Shuffles]
else:
if len(trainIndices) != len(testIndices) != len(Shuffles):
raise ValueError(
"Number of Shuffles and train and test indexes should be equal."
)
splits = []
for shuffle, (train_inds, test_inds) in enumerate(
zip(trainIndices, testIndices)):
trainFraction = round(
len(train_inds) * 1.0 / (len(train_inds) + len(test_inds)),
2)
print(
f"You passed a split with the following fraction: {int(100 * trainFraction)}%"
)
splits.append((trainFraction, Shuffles[shuffle], (train_inds,
test_inds)))
bodyparts = cfg["bodyparts"]
nbodyparts = len(bodyparts)
for trainFraction, shuffle, (trainIndices, testIndices) in splits:
if len(trainIndices) > 0:
if userfeedback:
trainposeconfigfile, _, _ = training.return_train_network_path(
config,
shuffle=shuffle,
trainingsetindex=cfg["TrainingFraction"].index(
trainFraction),
)
if trainposeconfigfile.is_file():
askuser = input(
"The model folder is already present. If you continue, it will overwrite the existing model (split). Do you want to continue?(yes/no): "
)
if (askuser == "no" or askuser == "No"
or askuser == "N" or askuser == "No"):
raise Exception(
"Use the Shuffles argument as a list to specify a different shuffle index. Check out the help for more details."
)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
(
datafilename,
metadatafilename,
) = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
data, MatlabData = format_training_data(
Data, trainIndices, nbodyparts, project_path)
sio.savemat(os.path.join(project_path, datafilename),
{"dataset": MatlabData})
################################################################################
# Saving metadata (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(
os.path.join(project_path, metadatafilename),
data,
trainIndices,
testIndices,
trainFraction,
)
################################################################################
# Creating file structure for training &
# Test files as well as pose_yaml files (containing training and testing information)
#################################################################################
modelfoldername = auxiliaryfunctions.GetModelFolder(
trainFraction, shuffle, cfg)
auxiliaryfunctions.attempttomakefolder(
Path(config).parents[0] / modelfoldername, recursive=True)
auxiliaryfunctions.attempttomakefolder(
str(Path(config).parents[0] / modelfoldername) + "/train")
auxiliaryfunctions.attempttomakefolder(
str(Path(config).parents[0] / modelfoldername) + "/test")
path_train_config = str(
os.path.join(
cfg["project_path"],
Path(modelfoldername),
"train",
"pose_cfg.yaml",
))
path_test_config = str(
os.path.join(
cfg["project_path"],
Path(modelfoldername),
"test",
"pose_cfg.yaml",
))
# str(cfg['proj_path']+'/'+Path(modelfoldername) / 'test' / 'pose_cfg.yaml')
items2change = {
"dataset": datafilename,
"metadataset": metadatafilename,
"num_joints": len(bodyparts),
"all_joints": [[i] for i in range(len(bodyparts))],
"all_joints_names": [str(bpt) for bpt in bodyparts],
"init_weights": model_path,
"project_path": str(cfg["project_path"]),
"net_type": net_type,
"dataset_type": augmenter_type,
}
items2drop = {}
if augmenter_type == "scalecrop":
# these values are dropped as scalecrop
# doesn't have rotation implemented
items2drop = {"rotation": 0, "rotratio": 0.0}
trainingdata = MakeTrain_pose_yaml(items2change,
path_train_config,
defaultconfigfile,
items2drop)
keys2save = [
"dataset",
"num_joints",
"all_joints",
"all_joints_names",
"net_type",
"init_weights",
"global_scale",
"location_refinement",
"locref_stdev",
]
MakeTest_pose_yaml(trainingdata, keys2save, path_test_config)
print(
"The training dataset is successfully created. Use the function 'train_network' to start training. Happy training!"
)
return splits
basepath, "openfield-Pranav-2018-10-30", "videos", video + ".mp4"
)
print("Creating project...")
config_path = deeplabcut.create_new_project(
TASK, SCORER, [video_path], copy_videos=True, multianimal=True
)
print("Project created.")
print("Editing config...")
cfg = auxiliaryfunctions.edit_config(
config_path,
{
"numframes2pick": NUM_FRAMES,
"TrainingFraction": [TRAIN_SIZE],
"identity": True,
"uniquebodyparts": ["corner1", "corner2"],
},
)
print("Config edited.")
print("Extracting frames...")
deeplabcut.extract_frames(config_path, mode="automatic", userfeedback=False)
print("Frames extracted.")
print("Creating artificial data...")
rel_folder = os.path.join("labeled-data", os.path.splitext(video)[0])
image_folder = os.path.join(cfg["project_path"], rel_folder)
n_animals = len(cfg["individuals"])
(
basepath = os.path.dirname(os.path.realpath(__file__))
video = "m3v1mp4"
video_path = os.path.join(basepath, "openfield-Pranav-2018-10-30",
"videos", video + ".mp4")
print("Creating project...")
config_path = deeplabcut.create_new_project(TASK,
SCORER, [video_path],
copy_videos=True,
multianimal=True)
print("Project created.")
print("Editing config...")
cfg = auxiliaryfunctions.edit_config(config_path, {
"numframes2pick": NUM_FRAMES,
"TrainingFraction": [TRAIN_SIZE]
})
print("Config edited.")
print("Extracting frames...")
deeplabcut.extract_frames(config_path,
mode="automatic",
userfeedback=False)
print("Frames extracted.")
print("Creating artificial data...")
rel_folder = os.path.join("labeled-data", os.path.splitext(video)[0])
image_folder = os.path.join(cfg["project_path"], rel_folder)
n_animals = len(cfg["individuals"])
(
animals,
def create_pretrained_project(
project,
experimenter,
videos,
model="full_human",
working_directory=None,
copy_videos=False,
videotype=None,
analyzevideo=True,
filtered=True,
createlabeledvideo=True,
trainFraction=None,
):
"""
Creates a new project directory, sub-directories and a basic configuration file.
Change its parameters to your projects need.
The project will also be initialized with a pre-trained model from the DeepLabCut model zoo!
http://www.mousemotorlab.org/dlc-modelzoo
Parameters
----------
project : string
String containing the name of the project.
experimenter : string
String containing the name of the experimenter.
model: string, options see http://www.mousemotorlab.org/dlc-modelzoo
Current option and default: 'full_human' Creates a demo human project and analyzes a video with ResNet 101 weights pretrained on MPII Human Pose. This is from the DeeperCut paper
by Insafutdinov et al. https://arxiv.org/abs/1605.03170 Please make sure to cite it too if you use this code!
videos : list
A list of string containing the full paths of the videos to include in the project.
working_directory : string, optional
The directory where the project will be created. The default is the ``current working directory``; if provided, it must be a string.
copy_videos : bool, optional ON WINDOWS: TRUE is often necessary!
If this is set to True, the videos are copied to the ``videos`` directory. If it is False,symlink of the videos are copied to the project/videos directory. The default is ``False``; if provided it must be either
``True`` or ``False``.
analyzevideo " bool, optional
If true, then the video is analzyed and a labeled video is created. If false, then only the project will be created and the weights downloaded. You can then access them
filtered: bool, default false
Boolean variable indicating if filtered pose data output should be plotted rather than frame-by-frame predictions.
Filtered version can be calculated with deeplabcut.filterpredictions
trainFraction: By default value from *new* projects. (0.95)
Fraction that will be used in dlc-model/trainingset folder name.
Example
--------
Linux/MacOs loading full_human model and analzying video /homosapiens1.avi
>>> deeplabcut.create_pretrained_project('humanstrokestudy','Linus',['/data/videos/homosapiens1.avi'], copy_videos=False)
Loading full_cat model and analzying video "felixfeliscatus3.avi"
>>> deeplabcut.create_pretrained_project('humanstrokestudy','Linus',['/data/videos/felixfeliscatus3.avi'], model='full_cat')
Windows:
>>> deeplabcut.create_pretrained_project('humanstrokestudy','Bill',[r'C:\yourusername\rig-95\Videos\reachingvideo1.avi'],r'C:\yourusername\analysis\project' copy_videos=True)
Users must format paths with either: r'C:\ OR 'C:\\ <- i.e. a double backslash \ \ )
"""
if model in globals()["Modeloptions"]:
cwd = os.getcwd()
cfg = deeplabcut.create_new_project(project, experimenter, videos,
working_directory, copy_videos,
videotype)
if trainFraction is not None:
auxiliaryfunctions.edit_config(
cfg, {"TrainingFraction": [tranFraction]})
config = auxiliaryfunctions.read_config(cfg)
if model == "full_human":
config["bodyparts"] = [
"ankle1",
"knee1",
"hip1",
"hip2",
"knee2",
"ankle2",
"wrist1",
"elbow1",
"shoulder1",
"shoulder2",
"elbow2",
"wrist2",
"chin",
"forehead",
]
config["skeleton"] = [
["ankle1", "knee1"],
["ankle2", "knee2"],
["knee1", "hip1"],
["knee2", "hip2"],
["hip1", "hip2"],
["shoulder1", "shoulder2"],
["shoulder1", "hip1"],
["shoulder2", "hip2"],
["shoulder1", "elbow1"],
["shoulder2", "elbow2"],
["chin", "forehead"],
["elbow1", "wrist1"],
["elbow2", "wrist2"],
]
config["default_net_type"] = "resnet_101"
else: # just make a case and put the stuff you want.
# TBD: 'partaffinityfield_graph' >> use to set skeleton!
pass
auxiliaryfunctions.write_config(cfg, config)
config = auxiliaryfunctions.read_config(cfg)
train_dir = Path(
os.path.join(
config["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction=config["TrainingFraction"][0],
shuffle=1,
cfg=config,
)),
"train",
))
test_dir = Path(
os.path.join(
config["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction=config["TrainingFraction"][0],
shuffle=1,
cfg=config,
)),
"test",
))
# Create the model directory
train_dir.mkdir(parents=True, exist_ok=True)
test_dir.mkdir(parents=True, exist_ok=True)
modelfoldername = auxiliaryfunctions.GetModelFolder(
trainFraction=config["TrainingFraction"][0], shuffle=1, cfg=config)
path_train_config = str(
os.path.join(config["project_path"], Path(modelfoldername),
"train", "pose_cfg.yaml"))
path_test_config = str(
os.path.join(config["project_path"], Path(modelfoldername), "test",
"pose_cfg.yaml"))
# Download the weights and put then in appropriate directory
print("Dowloading weights...")
auxfun_models.DownloadModel(model, train_dir)
pose_cfg = deeplabcut.auxiliaryfunctions.read_plainconfig(
path_train_config)
print(path_train_config)
# Updating config file:
dict = {
"default_net_type": pose_cfg["net_type"],
"default_augmenter": pose_cfg["dataset_type"],
"bodyparts": pose_cfg["all_joints_names"],
"skeleton": [], # TODO: update with paf_graph
"dotsize": 6,
}
auxiliaryfunctions.edit_config(cfg, dict)
# Create the pose_config.yaml files
parent_path = Path(os.path.dirname(deeplabcut.__file__))
defaultconfigfile = str(parent_path / "pose_cfg.yaml")
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(config)
datafilename, metadatafilename = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder,
trainFraction=config["TrainingFraction"][0],
shuffle=1,
cfg=config,
)
# downloading base encoder / not required unless on re-trains (but when a training set is created this happens anyway)
# model_path, num_shuffles=auxfun_models.Check4weights(pose_cfg['net_type'], parent_path, num_shuffles= 1)
# Updating training and test pose_cfg:
snapshotname = [fn for fn in os.listdir(train_dir)
if ".meta" in fn][0].split(".meta")[0]
dict2change = {
"init_weights": str(os.path.join(train_dir, snapshotname)),
"project_path": str(config["project_path"]),
}
UpdateTrain_pose_yaml(pose_cfg, dict2change, path_train_config)
keys2save = [
"dataset",
"dataset_type",
"num_joints",
"all_joints",
"all_joints_names",
"net_type",
"init_weights",
"global_scale",
"location_refinement",
"locref_stdev",
]
MakeTest_pose_yaml(pose_cfg, keys2save, path_test_config)
video_dir = os.path.join(config["project_path"], "videos")
if analyzevideo == True:
print("Analyzing video...")
deeplabcut.analyze_videos(cfg, [video_dir],
videotype,
save_as_csv=True)
if createlabeledvideo == True:
if filtered:
deeplabcut.filterpredictions(cfg, [video_dir], videotype)
print("Plotting results...")
deeplabcut.create_labeled_video(cfg, [video_dir],
videotype,
draw_skeleton=True,
filtered=filtered)
deeplabcut.plot_trajectories(cfg, [video_dir],
videotype,
filtered=filtered)
os.chdir(cwd)
return cfg, path_train_config
else:
return "N/A", "N/A"
def create_training_dataset(
config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
userfeedback=False,
trainIndices=None,
testIndices=None,
net_type=None,
augmenter_type=None,
posecfg_template=None,
):
"""Creates a training dataset.
Labels from all the extracted frames are merged into a single .h5 file.
Only the videos included in the config file are used to create this dataset.
Parameters
----------
config : string
Full path of the ``config.yaml`` file as a string.
num_shuffles : int, optional, default=1
Number of shuffles of training dataset to create, i.e. ``[1,2,3]`` for
``num_shuffles=3``.
Shuffles: list[int], optional
Alternatively the user can also give a list of shuffles.
userfeedback: bool, optional, default=False
If ``False``, all requested train/test splits are created (no matter if they
already exist). If you want to assure that previous splits etc. are not
overwritten, set this to ``True`` and you will be asked for each split.
trainIndices: list of lists, optional, default=None
List of one or multiple lists containing train indexes.
A list containing two lists of training indexes will produce two splits.
testIndices: list of lists, optional, default=None
List of one or multiple lists containing test indexes.
net_type: list, optional, default=None
Type of networks. Currently supported options are
* ``resnet_50``
* ``resnet_101``
* ``resnet_152``
* ``mobilenet_v2_1.0``
* ``mobilenet_v2_0.75``
* ``mobilenet_v2_0.5``
* ``mobilenet_v2_0.35``
* ``efficientnet-b0``
* ``efficientnet-b1``
* ``efficientnet-b2``
* ``efficientnet-b3``
* ``efficientnet-b4``
* ``efficientnet-b5``
* ``efficientnet-b6``
augmenter_type: string, optional, default=None
Type of augmenter. Currently supported augmenters are
* ``default``
* ``scalecrop``
* ``imgaug``
* ``tensorpack``
* ``deterministic``
posecfg_template: string, optional, default=None
Path to a ``pose_cfg.yaml`` file to use as a template for generating the new
one for the current iteration. Useful if you would like to start with the same
parameters a previous training iteration. None uses the default
``pose_cfg.yaml``.
Returns
-------
list(tuple) or None
If training dataset was successfully created, a list of tuples is returned.
The first two elements in each tuple represent the training fraction and the
shuffle value. The last two elements in each tuple are arrays of integers
representing the training and test indices.
Returns None if training dataset could not be created.
Notes
-----
Use the function ``add_new_videos`` at any stage of the project to add more videos
to the project.
Examples
--------
Linux/MacOS
>>> deeplabcut.create_training_dataset(
'/analysis/project/reaching-task/config.yaml', num_shuffles=1,
)
Windows
>>> deeplabcut.create_training_dataset(
'C:\\Users\\Ulf\\looming-task\\config.yaml', Shuffles=[3,17,5],
)
"""
import scipy.io as sio
if windows2linux:
# DeprecationWarnings are silenced since Python 3.2 unless triggered in __main__
warnings.warn(
"`windows2linux` has no effect since 2.2.0.4 and will be removed in 2.2.1.",
FutureWarning,
)
# Loading metadata from config file:
cfg = auxiliaryfunctions.read_config(config)
if posecfg_template:
if not posecfg_template.endswith("pose_cfg.yaml"):
raise ValueError(
"posecfg_template argument must contain path to a pose_cfg.yaml file"
)
else:
print("Reloading pose_cfg parameters from " + posecfg_template +
'\n')
from deeplabcut.utils.auxiliaryfunctions import read_plainconfig
prior_cfg = read_plainconfig(posecfg_template)
if cfg.get("multianimalproject", False):
from deeplabcut.generate_training_dataset.multiple_individuals_trainingsetmanipulation import (
create_multianimaltraining_dataset, )
create_multianimaltraining_dataset(config,
num_shuffles,
Shuffles,
net_type=net_type)
else:
scorer = cfg["scorer"]
project_path = cfg["project_path"]
# Create path for training sets & store data there
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(
cfg) # Path concatenation OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(
os.path.join(project_path, str(trainingsetfolder))),
recursive=True)
Data = merge_annotateddatasets(
cfg,
Path(os.path.join(project_path, trainingsetfolder)),
)
if Data is None:
return
Data = Data[scorer] # extract labeled data
# loading & linking pretrained models
if net_type is None: # loading & linking pretrained models
net_type = cfg.get("default_net_type", "resnet_50")
else:
if ("resnet" in net_type or "mobilenet" in net_type
or "efficientnet" in net_type):
pass
else:
raise ValueError("Invalid network type:", net_type)
if augmenter_type is None:
augmenter_type = cfg.get("default_augmenter", "imgaug")
if augmenter_type is None: # this could be in config.yaml for old projects!
# updating variable if null/None! #backwardscompatability
auxiliaryfunctions.edit_config(config,
{"default_augmenter": "imgaug"})
augmenter_type = "imgaug"
elif augmenter_type not in [
"default",
"scalecrop",
"imgaug",
"tensorpack",
"deterministic",
]:
raise ValueError("Invalid augmenter type:", augmenter_type)
if posecfg_template:
if net_type != prior_cfg["net_type"]:
print(
"WARNING: Specified net_type does not match net_type from posecfg_template path entered. Proceed with caution."
)
if augmenter_type != prior_cfg["dataset_type"]:
print(
"WARNING: Specified augmenter_type does not match dataset_type from posecfg_template path entered. Proceed with caution."
)
# Loading the encoder (if necessary downloading from TF)
dlcparent_path = auxiliaryfunctions.get_deeplabcut_path()
if not posecfg_template:
defaultconfigfile = os.path.join(dlcparent_path, "pose_cfg.yaml")
elif posecfg_template:
defaultconfigfile = posecfg_template
model_path, num_shuffles = auxfun_models.check_for_weights(
net_type, Path(dlcparent_path), num_shuffles)
if Shuffles is None:
Shuffles = range(1, num_shuffles + 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
# print(trainIndices,testIndices, Shuffles, augmenter_type,net_type)
if trainIndices is None and testIndices is None:
splits = [(
trainFraction,
shuffle,
SplitTrials(range(len(Data.index)), trainFraction),
) for trainFraction in cfg["TrainingFraction"]
for shuffle in Shuffles]
else:
if len(trainIndices) != len(testIndices) != len(Shuffles):
raise ValueError(
"Number of Shuffles and train and test indexes should be equal."
)
splits = []
for shuffle, (train_inds, test_inds) in enumerate(
zip(trainIndices, testIndices)):
trainFraction = round(
len(train_inds) * 1.0 / (len(train_inds) + len(test_inds)),
2)
print(
f"You passed a split with the following fraction: {int(100 * trainFraction)}%"
)
# Now that the training fraction is guaranteed to be correct,
# the values added to pad the indices are removed.
train_inds = np.asarray(train_inds)
train_inds = train_inds[train_inds != -1]
test_inds = np.asarray(test_inds)
test_inds = test_inds[test_inds != -1]
splits.append((trainFraction, Shuffles[shuffle], (train_inds,
test_inds)))
bodyparts = cfg["bodyparts"]
nbodyparts = len(bodyparts)
for trainFraction, shuffle, (trainIndices, testIndices) in splits:
if len(trainIndices) > 0:
if userfeedback:
trainposeconfigfile, _, _ = training.return_train_network_path(
config,
shuffle=shuffle,
trainingsetindex=cfg["TrainingFraction"].index(
trainFraction),
)
if trainposeconfigfile.is_file():
askuser = input(
"The model folder is already present. If you continue, it will overwrite the existing model (split). Do you want to continue?(yes/no): "
)
if (askuser == "no" or askuser == "No"
or askuser == "N" or askuser == "No"):
raise Exception(
"Use the Shuffles argument as a list to specify a different shuffle index. Check out the help for more details."
)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
(
datafilename,
metadatafilename,
) = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
data, MatlabData = format_training_data(
Data, trainIndices, nbodyparts, project_path)
sio.savemat(os.path.join(project_path, datafilename),
{"dataset": MatlabData})
################################################################################
# Saving metadata (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(
os.path.join(project_path, metadatafilename),
data,
trainIndices,
testIndices,
trainFraction,
)
################################################################################
# Creating file structure for training &
# Test files as well as pose_yaml files (containing training and testing information)
#################################################################################
modelfoldername = auxiliaryfunctions.get_model_folder(
trainFraction, shuffle, cfg)
auxiliaryfunctions.attempttomakefolder(
Path(config).parents[0] / modelfoldername, recursive=True)
auxiliaryfunctions.attempttomakefolder(
str(Path(config).parents[0] / modelfoldername) + "/train")
auxiliaryfunctions.attempttomakefolder(
str(Path(config).parents[0] / modelfoldername) + "/test")
path_train_config = str(
os.path.join(
cfg["project_path"],
Path(modelfoldername),
"train",
"pose_cfg.yaml",
))
path_test_config = str(
os.path.join(
cfg["project_path"],
Path(modelfoldername),
"test",
"pose_cfg.yaml",
))
# str(cfg['proj_path']+'/'+Path(modelfoldername) / 'test' / 'pose_cfg.yaml')
items2change = {
"dataset": datafilename,
"metadataset": metadatafilename,
"num_joints": len(bodyparts),
"all_joints": [[i] for i in range(len(bodyparts))],
"all_joints_names": [str(bpt) for bpt in bodyparts],
"init_weights": model_path,
"project_path": str(cfg["project_path"]),
"net_type": net_type,
"dataset_type": augmenter_type,
}
items2drop = {}
if augmenter_type == "scalecrop":
# these values are dropped as scalecrop
# doesn't have rotation implemented
items2drop = {"rotation": 0, "rotratio": 0.0}
# Also drop maDLC smart cropping augmentation parameters
for key in [
"pre_resize", "crop_size", "max_shift", "crop_sampling"
]:
items2drop[key] = None
trainingdata = MakeTrain_pose_yaml(items2change,
path_train_config,
defaultconfigfile,
items2drop)
keys2save = [
"dataset",
"num_joints",
"all_joints",
"all_joints_names",
"net_type",
"init_weights",
"global_scale",
"location_refinement",
"locref_stdev",
]
MakeTest_pose_yaml(trainingdata, keys2save, path_test_config)
print(
"The training dataset is successfully created. Use the function 'train_network' to start training. Happy training!"
)
return splits
