def return_train_network_path(config, shuffle=1, trainingsetindex=0, modelprefix=""):
"""Returns the training and test pose config file names as well as the folder where the snapshot is
Parameters
----------
config : string
Full path of the config.yaml file as a string.
shuffle: int
Integer value specifying the shuffle index to select for training.
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml).
Returns the triple: trainposeconfigfile, testposeconfigfile, snapshotfolder
"""
from deeplabcut.utils import auxiliaryfunctions
cfg = auxiliaryfunctions.read_config(config)
modelfoldername = auxiliaryfunctions.get_model_folder(
cfg["TrainingFraction"][trainingsetindex], shuffle, cfg, modelprefix=modelprefix
)
trainposeconfigfile = Path(
os.path.join(
cfg["project_path"], str(modelfoldername), "train", "pose_cfg.yaml"
)
)
testposeconfigfile = Path(
os.path.join(cfg["project_path"], str(modelfoldername), "test", "pose_cfg.yaml")
)
snapshotfolder = Path(
os.path.join(cfg["project_path"], str(modelfoldername), "train")
)
return trainposeconfigfile, testposeconfigfile, snapshotfolder
def edit_pose_config(self, event):
"""
"""
self.shuffles.Enable(True)
#self.trainingindex.Enable(True)
self.display_iters.Enable(True)
self.save_iters.Enable(True)
self.max_iters.Enable(True)
self.snapshots.Enable(True)
# Read the pose config file
cfg = auxiliaryfunctions.read_config(self.config)
trainFraction = cfg["TrainingFraction"]
#print(trainFraction[-1])
# print(os.path.join(cfg['project_path'],auxiliaryfunctions.get_model_folder(trainFraction, self.shuffles.GetValue(),cfg),'train','pose_cfg.yaml'))
self.pose_cfg_path = os.path.join(
cfg["project_path"],
auxiliaryfunctions.get_model_folder(trainFraction[-1],
self.shuffles.GetValue(), cfg),
"train",
"pose_cfg.yaml",
)
# let the user open the file with default text editor. Also make it mac compatible
if sys.platform == "darwin":
self.file_open_bool = subprocess.call(["open", self.pose_cfg_path])
self.file_open_bool = True
else:
self.file_open_bool = webbrowser.open(self.pose_cfg_path)
if self.file_open_bool:
self.pose_cfg = auxiliaryfunctions.read_plainconfig(
self.pose_cfg_path)
else:
raise FileNotFoundError("File not found!")
def edit_inf_config(self, event):
# Read the infer config file
cfg = auxiliaryfunctions.read_config(self.config)
#trainFraction = cfg["TrainingFraction"][trainingsetindex]
self.inf_cfg_path = os.path.join(
cfg["project_path"],
auxiliaryfunctions.get_model_folder(trainFraction,
self.shuffle.GetValue(), cfg),
"test",
"inference_cfg.yaml",
)
# let the user open the file with default text editor. Also make it mac compatible
if sys.platform == "darwin":
self.file_open_bool = subprocess.call(["open", self.inf_cfg_path])
self.file_open_bool = True
else:
self.file_open_bool = webbrowser.open(self.inf_cfg_path)
if self.file_open_bool:
self.inf_cfg = auxiliaryfunctions.read_config(self.inf_cfg_path)
else:
raise FileNotFoundError("File not found!")
def create_multianimaltraining_dataset(
config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
net_type=None,
numdigits=2,
crop_size=(400, 400),
crop_sampling="hybrid",
paf_graph=None,
trainIndices=None,
testIndices=None,
n_edges_threshold=105,
paf_graph_degree=6,
):
"""
Creates a training dataset for multi-animal datasets. 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_videos' at any stage of the project to add more videos to the project.
Imporant differences to standard:
- stores coordinates with numdigits as many digits
- creates
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!).
net_type: string
Type of networks. Currently resnet_50, resnet_101, and resnet_152, efficientnet-b0, efficientnet-b1, efficientnet-b2, efficientnet-b3,
efficientnet-b4, efficientnet-b5, and efficientnet-b6 as well as dlcrnet_ms5 are supported (not the MobileNets!).
See Lauer et al. 2021 https://www.biorxiv.org/content/10.1101/2021.04.30.442096v1
numdigits: int, optional
crop_size: tuple of int, optional
Dimensions (width, height) of the crops for data augmentation.
Default is 400x400.
crop_sampling: str, optional
Crop centers sampling method. Must be either:
"uniform" (randomly over the image),
"keypoints" (randomly over the annotated keypoints),
"density" (weighing preferentially dense regions of keypoints),
or "hybrid" (alternating randomly between "uniform" and "density").
Default is "hybrid".
paf_graph: list of lists, or "config" optional (default=None)
If not None, overwrite the default complete graph. This is useful for advanced users who
already know a good graph, or simply want to use a specific one. Note that, in that case,
the data-driven selection procedure upon model evaluation will be skipped.
"config" will use the skeleton defined in the config file.
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.
n_edges_threshold: int, optional (default=105)
Number of edges above which the graph is automatically pruned.
paf_graph_degree: int, optional (default=6)
Degree of paf_graph when automatically pruning it (before training).
Example
--------
>>> deeplabcut.create_multianimaltraining_dataset('/analysis/project/reaching-task/config.yaml',num_shuffles=1)
>>> deeplabcut.create_multianimaltraining_dataset('/analysis/project/reaching-task/config.yaml', Shuffles=[0,1,2], trainIndices=[trainInd1, trainInd2, trainInd3], testIndices=[testInd1, testInd2, testInd3])
Windows:
>>> deeplabcut.create_multianimaltraining_dataset(r'C:\\Users\\Ulf\\looming-task\\config.yaml',Shuffles=[3,17,5])
--------
"""
if windows2linux:
warnings.warn(
"`windows2linux` has no effect since 2.2.0.4 and will be removed in 2.2.1.",
FutureWarning,
)
if len(crop_size) != 2 or not all(isinstance(v, int) for v in crop_size):
raise ValueError("Crop size must be a tuple of two integers (width, height).")
if crop_sampling not in ("uniform", "keypoints", "density", "hybrid"):
raise ValueError(
f"Invalid sampling {crop_sampling}. Must be "
f"either 'uniform', 'keypoints', 'density', or 'hybrid."
)
# Loading metadata from config file:
cfg = auxiliaryfunctions.read_config(config)
scorer = cfg["scorer"]
project_path = cfg["project_path"]
# Create path for training sets & store data there
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
full_training_path = Path(project_path, trainingsetfolder)
auxiliaryfunctions.attempttomakefolder(full_training_path, recursive=True)
Data = merge_annotateddatasets(cfg, full_training_path)
if Data is None:
return
Data = Data[scorer]
if net_type is None: # loading & linking pretrained models
net_type = cfg.get("default_net_type", "dlcrnet_ms5")
elif not any(net in net_type for net in ("resnet", "eff", "dlc", "mob")):
raise ValueError(f"Unsupported network {net_type}.")
multi_stage = False
### dlcnet_ms5: backbone resnet50 + multi-fusion & multi-stage module
### dlcr101_ms5/dlcr152_ms5: backbone resnet101/152 + multi-fusion & multi-stage module
if all(net in net_type for net in ("dlcr", "_ms5")):
num_layers = re.findall("dlcr([0-9]*)", net_type)[0]
if num_layers == "":
num_layers = 50
net_type = "resnet_{}".format(num_layers)
multi_stage = True
dataset_type = "multi-animal-imgaug"
(
individuals,
uniquebodyparts,
multianimalbodyparts,
) = auxfun_multianimal.extractindividualsandbodyparts(cfg)
if paf_graph is None: # Automatically form a complete PAF graph
n_bpts = len(multianimalbodyparts)
partaffinityfield_graph = [
list(edge) for edge in combinations(range(n_bpts), 2)
]
n_edges_orig = len(partaffinityfield_graph)
# If the graph is unnecessarily large (with 15+ keypoints by default),
# we randomly prune it to a size guaranteeing an average node degree of 6;
# see Suppl. Fig S9c in Lauer et al., 2022.
if n_edges_orig >= n_edges_threshold:
partaffinityfield_graph = auxfun_multianimal.prune_paf_graph(
partaffinityfield_graph, average_degree=paf_graph_degree,
)
else:
if paf_graph == "config":
# Use the skeleton defined in the config file
skeleton = cfg["skeleton"]
paf_graph = [
sorted(
(multianimalbodyparts.index(bpt1), multianimalbodyparts.index(bpt2))
)
for bpt1, bpt2 in skeleton
]
print(
"Using `skeleton` from the config file as a paf_graph. Data-driven skeleton will not be computed."
)
# Ignore possible connections between 'multi' and 'unique' body parts;
# one can never be too careful...
to_ignore = auxfun_multianimal.filter_unwanted_paf_connections(cfg, paf_graph)
partaffinityfield_graph = [
edge for i, edge in enumerate(paf_graph) if i not in to_ignore
]
auxfun_multianimal.validate_paf_graph(cfg, partaffinityfield_graph)
print("Utilizing the following graph:", partaffinityfield_graph)
# Disable the prediction of PAFs if the graph is empty
partaffinityfield_predict = bool(partaffinityfield_graph)
# 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.check_for_weights(
net_type, Path(dlcparent_path), num_shuffles
)
if Shuffles is None:
Shuffles = range(1, num_shuffles + 1, 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 = []
for shuffle in Shuffles: # Creating shuffles starting from 1
for train_frac in cfg["TrainingFraction"]:
train_inds, test_inds = SplitTrials(range(len(Data)), train_frac)
splits.append((train_frac, shuffle, (train_inds, test_inds)))
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)))
for trainFraction, shuffle, (trainIndices, testIndices) in splits:
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
print(
"Creating training data for: Shuffle:",
shuffle,
"TrainFraction: ",
trainFraction,
)
# Make training file!
data = format_multianimal_training_data(
Data,
trainIndices,
cfg["project_path"],
numdigits,
)
if len(trainIndices) > 0:
(
datafilename,
metadatafilename,
) = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg
)
################################################################################
# Saving metadata and data file (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(
os.path.join(project_path, metadatafilename),
data,
trainIndices,
testIndices,
trainFraction,
)
datafilename = datafilename.split(".mat")[0] + ".pickle"
import pickle
with open(os.path.join(project_path, datafilename), "wb") as f:
# Pickle the 'labeled-data' dictionary using the highest protocol available.
pickle.dump(data, f, pickle.HIGHEST_PROTOCOL)
################################################################################
# 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",
)
)
path_inference_config = str(
os.path.join(
cfg["project_path"],
Path(modelfoldername),
"test",
"inference_cfg.yaml",
)
)
jointnames = [str(bpt) for bpt in multianimalbodyparts]
jointnames.extend([str(bpt) for bpt in uniquebodyparts])
items2change = {
"dataset": datafilename,
"metadataset": metadatafilename,
"num_joints": len(multianimalbodyparts)
+ len(uniquebodyparts), # cfg["uniquebodyparts"]),
"all_joints": [
[i] for i in range(len(multianimalbodyparts) + len(uniquebodyparts))
], # cfg["uniquebodyparts"]))],
"all_joints_names": jointnames,
"init_weights": model_path,
"project_path": str(cfg["project_path"]),
"net_type": net_type,
"multi_stage": multi_stage,
"pairwise_loss_weight": 0.1,
"pafwidth": 20,
"partaffinityfield_graph": partaffinityfield_graph,
"partaffinityfield_predict": partaffinityfield_predict,
"weigh_only_present_joints": False,
"num_limbs": len(partaffinityfield_graph),
"dataset_type": dataset_type,
"optimizer": "adam",
"batch_size": 8,
"multi_step": [[1e-4, 7500], [5 * 1e-5, 12000], [1e-5, 200000]],
"save_iters": 10000,
"display_iters": 500,
"num_idchannel": len(cfg["individuals"])
if cfg.get("identity", False)
else 0,
"crop_size": list(crop_size),
"crop_sampling": crop_sampling,
}
trainingdata = MakeTrain_pose_yaml(
items2change, path_train_config, defaultconfigfile
)
keys2save = [
"dataset",
"num_joints",
"all_joints",
"all_joints_names",
"net_type",
"multi_stage",
"init_weights",
"global_scale",
"location_refinement",
"locref_stdev",
"dataset_type",
"partaffinityfield_predict",
"pairwise_predict",
"partaffinityfield_graph",
"num_limbs",
"dataset_type",
"num_idchannel",
]
MakeTest_pose_yaml(
trainingdata,
keys2save,
path_test_config,
nmsradius=5.0,
minconfidence=0.01,
sigma=1,
locref_smooth=False,
) # setting important def. values for inference
# Setting inference cfg file:
defaultinference_configfile = os.path.join(
dlcparent_path, "inference_cfg.yaml"
)
items2change = {
"minimalnumberofconnections": int(len(cfg["multianimalbodyparts"]) / 2),
"topktoretain": len(cfg["individuals"])
+ 1 * (len(cfg["uniquebodyparts"]) > 0),
"withid": cfg.get("identity", False),
}
MakeInference_yaml(
items2change, path_inference_config, defaultinference_configfile
)
print(
"The training dataset is successfully created. Use the function 'train_network' to start training. Happy training!"
)
else:
pass
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.get_model_folder(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.compat.v1.get_default_graph().get_operations()[0].name
return sess, input, output, dlc_cfg
print("Train dataset created.")
# Check the training image paths are correctly stored as arrays of strings
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
datafile, _ = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, 0.8, 1, cfg,
)
datafile = datafile.split(".mat")[0] + ".pickle"
with open(os.path.join(cfg["project_path"], datafile), "rb") as f:
pickledata = pickle.load(f)
num_images = len(pickledata)
assert all(len(pickledata[i]["joints"]) == 3 for i in range(num_images))
print("Editing pose config...")
model_folder = auxiliaryfunctions.get_model_folder(
TRAIN_SIZE, 1, cfg, cfg["project_path"]
)
pose_config_path = os.path.join(model_folder, "train", "pose_cfg.yaml")
edits = {
"global_scale": 0.5,
"batch_size": 1,
"save_iters": N_ITER,
"display_iters": N_ITER // 2,
"crop_size": [200, 200],
# "multi_step": [[0.001, N_ITER]],
}
deeplabcut.auxiliaryfunctions.edit_config(pose_config_path, edits)
print("Pose config edited.")
print("Training network...")
deeplabcut.train_network(config_path, maxiters=N_ITER)
def evaluate_network(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=False,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
rescale=False,
modelprefix="",
):
"""Evaluates the network.
Evaluates the network based on the saved models at different stages of the training
network. 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.
Shuffles: list, optional, default=[1]
List of integers specifying the shuffle indices of the training dataset.
trainingsetindex: int or str, optional, default=0
Integer specifying which "TrainingsetFraction" to use.
Note that "TrainingFraction" is a list in config.yaml. This variable can also
be set to "all".
plotting: bool or str, optional, default=False
Plots the predictions on the train and test images.
If provided it must be either ``True``, ``False``, ``"bodypart"``, or
``"individual"``. Setting to ``True`` defaults as ``"bodypart"`` for
multi-animal projects.
show_errors: bool, optional, default=True
Display train and test errors.
comparisonbodyparts: str or list, optional, default="all"
The average error will be computed for those body parts only.
The provided list has to be a subset of the defined body parts.
gputouse: int or None, optional, default=None
Indicates the GPU to use (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, optional, default=False
Evaluate the model at the ``'global_scale'`` variable (as set in the
``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!
modelprefix: str, optional, default=""
Directory containing the deeplabcut models to use when evaluating the network.
By default, the models are assumed to exist in the project folder.
Returns
-------
None
Examples
--------
If you do not want to plot and evaluate with shuffle set to 1.
>>> deeplabcut.evaluate_network(
'/analysis/project/reaching-task/config.yaml', Shuffles=[1],
)
If you want to plot and evaluate with shuffle set to 0 and 1.
>>> deeplabcut.evaluate_network(
'/analysis/project/reaching-task/config.yaml',
Shuffles=[0, 1],
plotting=True,
)
If you want to plot assemblies for a maDLC project
>>> deeplabcut.evaluate_network(
'/analysis/project/reaching-task/config.yaml',
Shuffles=[1],
plotting="individual",
)
Note: This defaults to standard plotting for single-animal projects.
"""
if plotting not in (True, False, "bodypart", "individual"):
raise ValueError(f"Unknown value for `plotting`={plotting}")
import os
start_path = os.getcwd()
from deeplabcut.utils import auxiliaryfunctions
cfg = auxiliaryfunctions.read_config(config)
if cfg.get("multianimalproject", False):
from .evaluate_multianimal import evaluate_multianimal_full
# TODO: Make this code not so redundant!
evaluate_multianimal_full(
config=config,
Shuffles=Shuffles,
trainingsetindex=trainingsetindex,
plotting=plotting,
comparisonbodyparts=comparisonbodyparts,
gputouse=gputouse,
modelprefix=modelprefix,
)
else:
from deeplabcut.utils.auxfun_videos import imread, imresize
from deeplabcut.pose_estimation_tensorflow.core import predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.datasets.utils import data_to_input
from deeplabcut.utils import auxiliaryfunctions, conversioncode
import tensorflow as tf
# If a string was passed in, auto-convert to True for backward compatibility
plotting = bool(plotting)
if "TF_CUDNN_USE_AUTOTUNE" in os.environ:
del os.environ[
"TF_CUDNN_USE_AUTOTUNE"
] # was potentially set during training
tf.compat.v1.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",
)
)
# 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.get_model_folder(
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.get_evaluation_folder(
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:
scale = dlc_cfg["global_scale"]
Data = (
pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
)
)
* scale
)
else:
scale = 1
conversioncode.guarantee_multiindex_rows(Data)
##################################################
# 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 training iterations:",
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("Running evaluation ...")
for imageindex, imagename in tqdm(enumerate(Data.index)):
image = imread(
os.path.join(cfg["project_path"], *imagename),
mode="skimage",
)
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
)
DataMachine.to_hdf(resultsfilename, "df_with_missing")
print(
"Analysis is done and the results are stored (see evaluation-results) 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:
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:
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.compat.v1.reset_default_graph()
# print(final_result)
else:
DataMachine = pd.read_hdf(resultsfilename)
conversioncode.guarantee_multiindex_rows(DataMachine)
if plotting:
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(
"Please check the results, then choose the best model (snapshot) for prediction. You can update the config.yaml file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos."
)
print(
"Otherwise, consider adding more labeled-data and retraining the network (see DeepLabCut workflow Fig 2, Nath 2019)"
)
# returning to initial folder
os.chdir(str(start_path))
def calculatepafdistancebounds(
config, shuffle=0, trainingsetindex=0, modelprefix="", numdigits=0, onlytrain=False
):
"""
Returns distances along paf edges in train/test data
----------
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".
numdigits: number of digits to round for distances.
"""
import os
from deeplabcut.utils import auxiliaryfunctions, auxfun_multianimal
from deeplabcut.pose_estimation_tensorflow.config import load_config
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if cfg["multianimalproject"]:
(
individuals,
uniquebodyparts,
multianimalbodyparts,
) = auxfun_multianimal.extractindividualsandbodyparts(cfg)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
trainFraction = cfg["TrainingFraction"][trainingsetindex]
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg
)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.get_model_folder(
trainFraction, shuffle, cfg, modelprefix=modelprefix
)
),
)
# Load meta data & annotations
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn)
)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
)
)[cfg["scorer"]]
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
dlc_cfg = load_config(str(path_test_config))
# get the graph!
partaffinityfield_graph = dlc_cfg["partaffinityfield_graph"]
jointnames = [
dlc_cfg["all_joints_names"][i] for i in range(len(dlc_cfg["all_joints"]))
]
path_inferencebounds_config = (
Path(modelfolder) / "test" / "inferencebounds.yaml"
)
inferenceboundscfg = {}
for pi, edge in enumerate(partaffinityfield_graph):
j1, j2 = jointnames[edge[0]], jointnames[edge[1]]
ds_within = []
ds_across = []
for ind in individuals:
for ind2 in individuals:
if ind != "single" and ind2 != "single":
if (ind, j1, "x") in Data.keys() and (
ind2,
j2,
"y",
) in Data.keys():
distances = (
np.sqrt(
(Data[ind, j1, "x"] - Data[ind2, j2, "x"]) ** 2
+ (Data[ind, j1, "y"] - Data[ind2, j2, "y"]) ** 2
)
/ dlc_cfg["stride"]
)
else:
distances = None
if distances is not None:
if onlytrain:
distances = distances.iloc[trainIndices]
if ind == ind2:
ds_within.extend(distances.values.flatten())
else:
ds_across.extend(distances.values.flatten())
edgeencoding = str(edge[0]) + "_" + str(edge[1])
inferenceboundscfg[edgeencoding] = {}
if len(ds_within) > 0:
inferenceboundscfg[edgeencoding]["intra_max"] = str(
round(np.nanmax(ds_within), numdigits)
)
inferenceboundscfg[edgeencoding]["intra_min"] = str(
round(np.nanmin(ds_within), numdigits)
)
else:
inferenceboundscfg[edgeencoding]["intra_max"] = str(
1e5
) # large number (larger than any image diameter)
inferenceboundscfg[edgeencoding]["intra_min"] = str(0)
# NOTE: the inter-animal distances are currently not used, but are interesting to compare to intra_*
if len(ds_across) > 0:
inferenceboundscfg[edgeencoding]["inter_max"] = str(
round(np.nanmax(ds_across), numdigits)
)
inferenceboundscfg[edgeencoding]["inter_min"] = str(
round(np.nanmin(ds_across), numdigits)
)
else:
inferenceboundscfg[edgeencoding]["inter_max"] = str(
1e5
) # large number (larger than image diameters in typical experiments)
inferenceboundscfg[edgeencoding]["inter_min"] = str(0)
auxiliaryfunctions.write_plainconfig(
str(path_inferencebounds_config), dict(inferenceboundscfg)
)
return inferenceboundscfg
else:
print("You might as well bring owls to Athens.")
return {}
def return_evaluate_network_data(
config,
shuffle=0,
trainingsetindex=0,
comparisonbodyparts="all",
Snapindex=None,
rescale=False,
fulldata=False,
show_errors=True,
modelprefix="",
returnjustfns=True,
):
"""
Returns the results for (previously evaluated) network. deeplabcut.evaluate_network(..)
Returns list of (per model): [trainingsiterations,trainfraction,shuffle,trainerror,testerror,pcutoff,trainerrorpcutoff,testerrorpcutoff,Snapshots[snapindex],scale,net_type]
If fulldata=True, also returns (the complete annotation and prediction array)
Returns list of: (DataMachine, Data, data, trainIndices, testIndices, trainFraction, DLCscorer,comparisonbodyparts, cfg, Snapshots[snapindex])
----------
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".
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).
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_data('/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 deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.utils import auxiliaryfunctions
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
# 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
)
##################################################
# Load data...
##################################################
trainFraction = cfg["TrainingFraction"][trainingsetindex]
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg
)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.get_model_folder(
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)
)
########################### RESCALING (to global scale)
if rescale == True:
scale = dlc_cfg["global_scale"]
print("Rescaling Data to ", scale)
Data = (
pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
)
)
* scale
)
else:
scale = 1
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
)
)
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.get_evaluation_folder(
trainFraction, shuffle, cfg, modelprefix=modelprefix
)
),
)
# 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)
)
snapindices = []
else:
increasing_indices = np.argsort([int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if Snapindex == None:
Snapindex = cfg["snapshotindex"]
if Snapindex == -1:
snapindices = [-1]
elif Snapindex == "all":
snapindices = range(len(Snapshots))
elif Snapindex < len(Snapshots):
snapindices = [Snapindex]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
DATA = []
results = []
resultsfns = []
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
)
if not returnjustfns:
print(
"Retrieving ",
DLCscorer,
" with # of trainingiterations:",
trainingsiterations,
)
(
notanalyzed,
resultsfilename,
DLCscorer,
) = auxiliaryfunctions.CheckifNotEvaluated(
str(evaluationfolder), DLCscorer, DLCscorerlegacy, Snapshots[snapindex]
)
# resultsfilename=os.path.join(str(evaluationfolder),DLCscorer + '-' + str(Snapshots[snapindex])+ '.h5') # + '-' + str(snapshot)+ ' #'-' + Snapshots[snapindex]+ '.h5')
print(resultsfilename)
resultsfns.append(resultsfilename)
if not returnjustfns:
if not notanalyzed and os.path.isfile(resultsfilename): # data exists..
DataMachine = pd.read_hdf(resultsfilename)
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()
)
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("Snapshot", Snapshots[snapindex])
r = [
trainingsiterations,
int(100 * trainFraction),
shuffle,
np.round(trainerror, 2),
np.round(testerror, 2),
cfg["pcutoff"],
np.round(trainerrorpcutoff, 2),
np.round(testerrorpcutoff, 2),
Snapshots[snapindex],
scale,
dlc_cfg["net_type"],
]
results.append(r)
else:
print("Model not trained/evaluated!")
if fulldata == True:
DATA.append(
[
DataMachine,
Data,
data,
trainIndices,
testIndices,
trainFraction,
DLCscorer,
comparisonbodyparts,
cfg,
evaluationfolder,
Snapshots[snapindex],
]
)
os.chdir(start_path)
if returnjustfns:
return resultsfns
else:
if fulldata == True:
return DATA, results
else:
return results
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.core import (
predict,
predict_multianimal as predictma,
)
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.datasets.utils import data_to_input
from deeplabcut.utils import auxiliaryfunctions
from tqdm import tqdm
import tensorflow as tf
import pandas as pd
from pathlib import Path
import numpy as np
tf.compat.v1.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",
))
# 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.get_model_folder(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.get_evaluation_folder(
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="skimage")
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 = []
peaks = outputs_np[-1]
if imageindex in testIndices:
trainingfram = False
else:
trainingfram = True
DATA[imageindex] = [
image,
scmap,
locref,
paf,
peaks,
bptnames,
pagraph,
imagename,
trainingfram,
]
Maps[trainFraction][Snapshots[snapindex]] = DATA
os.chdir(str(start_path))
return Maps
def train_network(
config,
shuffle=1,
trainingsetindex=0,
max_snapshots_to_keep=5,
displayiters=None,
saveiters=None,
maxiters=None,
allow_growth=True,
gputouse=None,
autotune=False,
keepdeconvweights=True,
modelprefix="",
):
"""Trains the network with the labels in the training dataset.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
shuffle: int, optional, default=1
Integer value specifying the shuffle index to select for training.
trainingsetindex: int, optional, default=0
Integer specifying which TrainingsetFraction to use.
Note that TrainingFraction is a list in config.yaml.
max_snapshots_to_keep: int or None
Sets how many snapshots are kept, i.e. states of the trained network. Every
saving interation many times a snapshot is stored, however only the last
``max_snapshots_to_keep`` many are kept! If you change this to None, then all
are kept.
See: https://github.com/DeepLabCut/DeepLabCut/issues/8#issuecomment-387404835
displayiters: optional, default=None
This variable is actually set in ``pose_config.yaml``. However, you can
overwrite it with this hack. Don't use this regularly, just if you are too lazy
to dig out the ``pose_config.yaml`` file for the corresponding project. If
``None``, the value from there is used, otherwise it is overwritten!
saveiters: optional, default=None
This variable is actually set in ``pose_config.yaml``. However, you can
overwrite it with this hack. Don't use this regularly, just if you are too lazy
to dig out the ``pose_config.yaml`` file for the corresponding project.
If ``None``, the value from there is used, otherwise it is overwritten!
maxiters: optional, default=None
This variable is actually set in ``pose_config.yaml``. However, you can
overwrite it with this hack. Don't use this regularly, just if you are too lazy
to dig out the ``pose_config.yaml`` file for the corresponding project.
If ``None``, the value from there is used, otherwise it is overwritten!
allow_growth: bool, optional, default=True.
For some smaller GPUs the memory issues happen. If ``True``, the memory
allocator does not pre-allocate the entire specified GPU memory region, instead
starting small and growing as needed.
See issue: https://forum.image.sc/t/how-to-stop-running-out-of-vram/30551/2
gputouse: optional, default=None
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
autotune: bool, optional, default=False
Property of TensorFlow, somehow faster if ``False``
(as Eldar found out, see https://github.com/tensorflow/tensorflow/issues/13317).
keepdeconvweights: bool, optional, default=True
Also restores the weights of the deconvolution layers (and the backbone) when
training from a snapshot. Note that if you change the number of bodyparts, you
need to set this to false for re-training.
modelprefix: str, optional, default=""
Directory containing the deeplabcut models to use when evaluating the network.
By default, the models are assumed to exist in the project folder.
Returns
-------
None
Examples
--------
To train the network for first shuffle of the training dataset
>>> deeplabcut.train_network('/analysis/project/reaching-task/config.yaml')
To train the network for second shuffle of the training dataset
>>> deeplabcut.train_network(
'/analysis/project/reaching-task/config.yaml',
shuffle=2,
keepdeconvweights=True,
)
"""
import tensorflow as tf
# reload logger.
import importlib
import logging
importlib.reload(logging)
logging.shutdown()
from deeplabcut.utils import auxiliaryfunctions
tf.compat.v1.reset_default_graph()
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
modelfoldername = auxiliaryfunctions.get_model_folder(
cfg["TrainingFraction"][trainingsetindex], shuffle, cfg, modelprefix=modelprefix
)
poseconfigfile = Path(
os.path.join(
cfg["project_path"], str(modelfoldername), "train", "pose_cfg.yaml"
)
)
if not poseconfigfile.is_file():
print("The training datafile ", poseconfigfile, " is not present.")
print(
"Probably, the training dataset for this specific shuffle index was not created."
)
print(
"Try with a different shuffle/trainingsetfraction or use function 'create_training_dataset' to create a new trainingdataset with this shuffle index."
)
else:
# Set environment variables
if (
autotune is not False
): # see: https://github.com/tensorflow/tensorflow/issues/13317
os.environ["TF_CUDNN_USE_AUTOTUNE"] = "0"
if gputouse is not None:
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
try:
cfg_dlc = auxiliaryfunctions.read_plainconfig(poseconfigfile)
if "multi-animal" in cfg_dlc["dataset_type"]:
from deeplabcut.pose_estimation_tensorflow.core.train_multianimal import (
train,
)
print("Selecting multi-animal trainer")
train(
str(poseconfigfile),
displayiters,
saveiters,
maxiters,
max_to_keep=max_snapshots_to_keep,
keepdeconvweights=keepdeconvweights,
allow_growth=allow_growth,
) # pass on path and file name for pose_cfg.yaml!
else:
from deeplabcut.pose_estimation_tensorflow.core.train import train
print("Selecting single-animal trainer")
train(
str(poseconfigfile),
displayiters,
saveiters,
maxiters,
max_to_keep=max_snapshots_to_keep,
keepdeconvweights=keepdeconvweights,
allow_growth=allow_growth,
) # pass on path and file name for pose_cfg.yaml!
except BaseException as e:
raise e
finally:
os.chdir(str(start_path))
print(
"The network is now trained and ready to evaluate. Use the function 'evaluate_network' to evaluate the network."
)
def evaluate_multianimal_full(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=False,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
modelprefix="",
):
from deeplabcut.pose_estimation_tensorflow.core import (
predict,
predict_multianimal as predictma,
)
from deeplabcut.utils import (
auxiliaryfunctions,
auxfun_multianimal,
auxfun_videos,
conversioncode,
)
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.compat.v1.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()
if plotting is True:
plotting = "bodypart"
##################################################
# 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",
))
conversioncode.guarantee_multiindex_rows(Data)
# 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.get_model_folder(
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))
pipeline = iaa.Sequential(random_order=False)
pre_resize = dlc_cfg.get("pre_resize")
if pre_resize:
width, height = pre_resize
pipeline.add(iaa.Resize({"height": height, "width": width}))
# TODO: IMPLEMENT for different batch sizes?
dlc_cfg["batch_size"] = 1 # due to differently sized images!!!
stride = dlc_cfg["stride"]
# Ignore best edges possibly defined during a prior evaluation
_ = dlc_cfg.pop("paf_best", None)
joints = dlc_cfg["all_joints_names"]
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.get_evaluation_folder(
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],
)
data_path = resultsfilename.split(
".h5")[0] + "_full.pickle"
if plotting:
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
if plotting == "bodypart":
fig, ax = visualization.create_minimal_figure()
if os.path.isfile(data_path):
print("Model already evaluated.", resultsfilename)
else:
(
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)
print("Network Evaluation underway...")
for imageindex, imagename in tqdm(enumerate(
Data.index)):
image_path = os.path.join(cfg["project_path"],
*imagename)
frame = auxfun_videos.imread(image_path,
mode="skimage")
GT = Data.iloc[imageindex]
if not GT.any():
continue
# Pass the image and the keypoints through the resizer;
# this has no effect if no augmenters were added to it.
keypoints = [
GT.to_numpy().reshape((-1, 2)).astype(float)
]
frame_, keypoints = pipeline(images=[frame],
keypoints=keypoints)
frame = frame_[0]
GT[:] = keypoints[0].flatten()
df = GT.unstack("coords").reindex(
joints, level="bodyparts")
# 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)
# Form 2D array of shape (n_rows, 4) where the last dimension
# is (sample_index, peak_y, peak_x, bpt_index) to slice the PAFs.
temp = df.reset_index(level="bodyparts").dropna()
temp["bodyparts"].replace(
dict(zip(joints, range(len(joints)))),
inplace=True,
)
temp["sample"] = 0
peaks_gt = temp.loc[:, [
"sample", "y", "x", "bodyparts"
]].to_numpy()
peaks_gt[:, 1:3] = (peaks_gt[:, 1:3] -
stride // 2) / stride
pred = predictma.predict_batched_peaks_and_costs(
dlc_cfg,
np.expand_dims(frame, axis=0),
sess,
inputs,
outputs,
peaks_gt.astype(int),
)
if not pred:
continue
else:
pred = pred[0]
PredicteData[imagename] = {}
PredicteData[imagename]["index"] = imageindex
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
xy_gt_values = xy_gt.iloc[inds_gt].values
neighbors = _find_closest_neighbors(
xy_gt_values, xy, k=3)
found = neighbors != -1
min_dists = np.linalg.norm(
xy_gt_values[found] -
xy[neighbors[found]],
axis=1,
)
inds = np.flatnonzero(all_bpts == bpt)
sl = imageindex, inds[inds_gt[found]]
dist[sl] = min_dists
conf[sl] = probs_pred[n_joint][
neighbors[found]].squeeze()
if plotting == "bodypart":
temp_xy = GT.unstack(
"bodyparts")[joints].values
gt = temp_xy.reshape(
(-1, 2,
temp_xy.shape[1])).T.swapaxes(1, 2)
h, w, _ = np.shape(frame)
fig.set_size_inches(w / 100, h / 100)
ax.set_xlim(0, w)
ax.set_ylim(0, h)
ax.invert_yaxis()
ax = visualization.make_multianimal_labeled_image(
frame,
gt,
coords_pred,
probs_pred,
colors,
cfg["dotsize"],
cfg["alphavalue"],
cfg["pcutoff"],
ax=ax,
)
visualization.save_labeled_frame(
fig,
image_path,
foldername,
imageindex in trainIndices,
)
visualization.erase_artists(ax)
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)
if show_errors:
string = (
"Results for {} training iterations, training fraction of {}, and 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; test-only)"
)
print(error_masked.iloc[testIndices].groupby(
"individuals",
axis=1).mean().mean().to_string())
print(
"Average Euclidean distance to GT per bodypart (in pixels; test-only)"
)
print(error_masked.iloc[testIndices].groupby(
"bodyparts", axis=1).mean().mean().to_string())
PredicteData["metadata"] = {
"nms radius":
dlc_cfg["nmsradius"],
"minimal confidence":
dlc_cfg["minconfidence"],
"sigma":
dlc_cfg.get("sigma", 1),
"PAFgraph":
dlc_cfg["partaffinityfield_graph"],
"PAFinds":
np.arange(len(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.compat.v1.reset_default_graph()
n_multibpts = len(cfg["multianimalbodyparts"])
if n_multibpts == 1:
continue
# Skip data-driven skeleton selection unless
# the model was trained on the full graph.
max_n_edges = n_multibpts * (n_multibpts - 1) // 2
n_edges = len(dlc_cfg["partaffinityfield_graph"])
if n_edges == max_n_edges:
print("Selecting best skeleton...")
n_graphs = 10
paf_inds = None
else:
n_graphs = 1
paf_inds = [list(range(n_edges))]
(
results,
paf_scores,
best_assemblies,
) = crossvalutils.cross_validate_paf_graphs(
config,
str(path_test_config).replace("pose_", "inference_"),
data_path,
data_path.replace("_full.", "_meta."),
n_graphs=n_graphs,
paf_inds=paf_inds,
oks_sigma=dlc_cfg.get("oks_sigma", 0.1),
margin=dlc_cfg.get("bbox_margin", 0),
symmetric_kpts=dlc_cfg.get("symmetric_kpts"),
)
if plotting == "individual":
assemblies, assemblies_unique, image_paths = best_assemblies
fig, ax = visualization.create_minimal_figure()
n_animals = len(cfg["individuals"])
if cfg["uniquebodyparts"]:
n_animals += 1
colors = visualization.get_cmap(n_animals,
name=cfg["colormap"])
for k, v in tqdm(assemblies.items()):
imname = image_paths[k]
image_path = os.path.join(cfg["project_path"],
*imname)
frame = auxfun_videos.imread(image_path,
mode="skimage")
h, w, _ = np.shape(frame)
fig.set_size_inches(w / 100, h / 100)
ax.set_xlim(0, w)
ax.set_ylim(0, h)
ax.invert_yaxis()
gt = [
s.to_numpy().reshape((-1, 2)) for _, s in
Data.loc[imname].groupby("individuals")
]
coords_pred = []
coords_pred += [ass.xy for ass in v]
probs_pred = []
probs_pred += [ass.data[:, 2:3] for ass in v]
if assemblies_unique is not None:
unique = assemblies_unique.get(k, None)
if unique is not None:
coords_pred.append(unique[:, :2])
probs_pred.append(unique[:, 2:3])
while len(coords_pred) < len(gt):
coords_pred.append(np.full((1, 2), np.nan))
probs_pred.append(np.full((1, 2), np.nan))
ax = visualization.make_multianimal_labeled_image(
frame,
gt,
coords_pred,
probs_pred,
colors,
cfg["dotsize"],
cfg["alphavalue"],
cfg["pcutoff"],
ax=ax,
)
visualization.save_labeled_frame(
fig,
image_path,
foldername,
k in trainIndices,
)
visualization.erase_artists(ax)
df = results[1].copy()
df.loc(axis=0)[("mAP_train", "mean")] = [
d[0]["mAP"] for d in results[2]
]
df.loc(axis=0)[("mAR_train", "mean")] = [
d[0]["mAR"] for d in results[2]
]
df.loc(axis=0)[("mAP_test", "mean")] = [
d[1]["mAP"] for d in results[2]
]
df.loc(axis=0)[("mAR_test", "mean")] = [
d[1]["mAR"] for d in results[2]
]
with open(data_path.replace("_full.", "_map."),
"wb") as file:
pickle.dump((df, paf_scores), file)
if len(final_result
) > 0: # Only append if results were calculated
make_results_file(final_result, evaluationfolder,
DLCscorer)
os.chdir(str(start_path))
def create_pretrained_project(
project,
experimenter,
videos,
model="full_human",
working_directory=None,
copy_videos=False,
videotype="",
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://modelzoo.deeplabcut.org
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 analyzed 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 analyzing video /homosapiens1.avi
>>> deeplabcut.create_pretrained_project('humanstrokestudy','Linus',['/data/videos/homosapiens1.avi'], copy_videos=False)
Loading full_cat model and analyzing 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": [trainFraction]})
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.get_model_folder(
trainFraction=config["TrainingFraction"][0],
shuffle=1,
cfg=config,
)),
"train",
))
test_dir = Path(
os.path.join(
config["project_path"],
str(
auxiliaryfunctions.get_model_folder(
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.get_model_folder(
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("Downloading weights...")
auxfun_models.download_model(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"],
"dotsize": 6,
}
auxiliaryfunctions.edit_config(cfg, dict_)
# 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
