def create_training_dataset(config,
num_shuffles=1,
Shuffles=None,
windows2linux=False):
"""
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.
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])
--------
"""
from skimage import io
import scipy.io as sio
import deeplabcut
import subprocess
# 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) #Path concatenation OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(
os.path.join(project_path, str(trainingsetfolder))),
recursive=True)
Data = merge_annotateddatasets(
cfg, project_path, Path(os.path.join(project_path, trainingsetfolder)),
windows2linux)
Data = Data[scorer] #extract labeled data
#set model type. we will allow more in the future.
if cfg['resnet'] == 50:
net_type = 'resnet_' + str(cfg['resnet'])
resnet_path = str(
Path(deeplabcut.__file__).parents[0] /
'pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt')
elif cfg['resnet'] == 101:
net_type = 'resnet_' + str(cfg['resnet'])
resnet_path = str(
Path(deeplabcut.__file__).parents[0] /
'pose_estimation_tensorflow/models/pretrained/resnet_v1_101.ckpt')
else:
print(
"Currently only ResNet 50 or 101 supported, please change 'resnet' entry in config.yaml!"
)
num_shuffles = -1 #thus the loop below is empty...
if not Path(resnet_path).is_file():
"""
Downloads the ImageNet pretrained weights for ResNet.
"""
start = os.getcwd()
os.chdir(str(Path(resnet_path).parents[0]))
print("Downloading the pretrained model (ResNets)....")
subprocess.call("download.sh", shell=True)
os.chdir(start)
if Shuffles == None:
Shuffles = range(1, num_shuffles + 1, 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
bodyparts = cfg['bodyparts']
TrainingFraction = cfg['TrainingFraction']
for shuffle in Shuffles: # Creating shuffles starting from 1
for trainFraction in TrainingFraction:
trainIndexes, testIndexes = SplitTrials(range(len(Data.index)),
trainFraction)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
data = []
for jj in trainIndexes:
H = {}
# load image to get dimensions:
filename = Data.index[jj]
im = io.imread(os.path.join(cfg['project_path'], filename))
H['image'] = filename
if np.ndim(im) == 3:
H['size'] = np.array(
[np.shape(im)[2],
np.shape(im)[0],
np.shape(im)[1]])
else:
# print "Grayscale!"
H['size'] = np.array([1, np.shape(im)[0], np.shape(im)[1]])
indexjoints = 0
joints = np.zeros((len(bodyparts), 3)) * np.nan
for bpindex, bodypart in enumerate(bodyparts):
if Data[bodypart]['x'][jj] < np.shape(
im)[1] and Data[bodypart]['y'][jj] < np.shape(
im)[0]: #are labels in image?
joints[indexjoints, 0] = int(bpindex)
joints[indexjoints, 1] = Data[bodypart]['x'][jj]
joints[indexjoints, 2] = Data[bodypart]['y'][jj]
indexjoints += 1
joints = joints[np.where(np.prod(
np.isfinite(joints),
1))[0], :] # drop NaN, i.e. lines for missing body parts
assert (np.prod(np.array(joints[:, 2]) < np.shape(im)[0])
) # y coordinate within image?
assert (np.prod(np.array(joints[:, 1]) < np.shape(im)[1])
) # x coordinate within image?
H['joints'] = np.array(joints, dtype=int)
if np.size(joints) > 0: #exclude images without labels
data.append(H)
if len(trainIndexes) > 0:
datafilename, metadatafilename = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
################################################################################
# Saving metadata (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(
os.path.join(project_path, metadatafilename), data,
trainIndexes, testIndexes, trainFraction)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
DTYPE = [('image', 'O'), ('size', 'O'), ('joints', 'O')]
MatlabData = np.array(
[(np.array([data[item]['image']],
dtype='U'), np.array([data[item]['size']]),
boxitintoacell(data[item]['joints']))
for item in range(len(data))],
dtype=DTYPE)
sio.savemat(os.path.join(project_path, datafilename),
{'dataset': MatlabData})
################################################################################
# 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": resnet_path,
"project_path": str(cfg['project_path']),
"net_type": net_type
}
defaultconfigfile = str(
Path(deeplabcut.__file__).parents[0] / 'pose_cfg.yaml')
trainingdata = MakeTrain_pose_yaml(items2change,
path_train_config,
defaultconfigfile)
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!"
)
def create_multianimaltraining_dataset(
config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
net_type=None,
numdigits=2,
paf_graph=None,
):
"""
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_video' 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!).
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.
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
paf_graph: list of lists, 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.
Example
--------
>>> deeplabcut.create_multianimaltraining_dataset('/analysis/project/reaching-task/config.yaml',num_shuffles=1)
Windows:
>>> deeplabcut.create_multianimaltraining_dataset(r'C:\\Users\\Ulf\\looming-task\\config.yaml',Shuffles=[3,17,5])
--------
"""
# 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, windows2linux)
if Data is None:
return
Data = Data[scorer]
def strip_cropped_image_name(path):
# utility function to split different crops from same image into either train or test!
head, filename = os.path.split(path)
if cfg["croppedtraining"]:
filename = filename.split("c")[0]
return os.path.join(head, filename)
img_names = Data.index.map(strip_cropped_image_name).unique()
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")):
raise ValueError(f"Unsupported network {net_type}.")
multi_stage = False
if net_type == "dlcrnet_ms5":
net_type = "resnet_50"
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
partaffinityfield_graph = [
list(edge)
for edge in combinations(range(len(multianimalbodyparts)), 2)
]
else:
# 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)
partaffinityfield_predict = True
# 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, 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
TrainingFraction = cfg["TrainingFraction"]
for shuffle in Shuffles: # Creating shuffles starting from 1
for trainFraction in TrainingFraction:
train_inds_temp, test_inds_temp = SplitTrials(
range(len(img_names)), trainFraction)
# Map back to the original indices.
temp = [
re.escape(name) for i, name in enumerate(img_names)
if i in test_inds_temp
]
mask = Data.index.str.contains("|".join(temp))
testIndices = np.flatnonzero(mask)
trainIndices = np.flatnonzero(~mask)
####################################################
# 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.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",
))
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,
}
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,
) # 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 evaluate_multianimal_full(
config,
Shuffles=[1],
trainingsetindex=0,
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None,
modelprefix="",
c_engine=False,
):
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.nnet import (
predict_multianimal as predictma, )
from deeplabcut.utils import auxiliaryfunctions, auxfun_multianimal
import tensorflow as tf
if "TF_CUDNN_USE_AUTOTUNE" in os.environ:
del os.environ[
"TF_CUDNN_USE_AUTOTUNE"] # was potentially set during training
tf.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
start_path = os.getcwd()
##################################################
# Load data...
##################################################
cfg = auxiliaryfunctions.read_config(config)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
TrainingFractions = [cfg["TrainingFraction"][trainingsetindex]]
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Handle data previously annotated on a different platform
sep = "/" if "/" in Data.index[0] else "\\"
if sep != os.path.sep:
Data.index = Data.index.str.replace(sep, os.path.sep)
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
all_bpts = np.asarray(
len(cfg["individuals"]) * cfg["multianimalbodyparts"] +
cfg["uniquebodyparts"])
colors = visualization.get_cmap(len(comparisonbodyparts),
name=cfg["colormap"])
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in TrainingFractions:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, trainFraction))
# TODO: IMPLEMENT for different batch sizes?
dlc_cfg["batch_size"] = 1 # due to differently sized images!!!
joints = dlc_cfg["all_joints_names"]
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0]
for fn in os.listdir(os.path.join(str(modelfolder), "train"))
if "index" in fn
])
if len(Snapshots) == 0:
print(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
else:
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
final_result = []
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split(
"-"
)[-1] # read how many training siterations that corresponds to.
# name for deeplabcut net (based on its parameters)
DLCscorer, DLCscorerlegacy = auxiliaryfunctions.GetScorerName(
cfg,
shuffle,
trainFraction,
trainingsiterations,
modelprefix=modelprefix,
)
print(
"Running ",
DLCscorer,
" with # of trainingiterations:",
trainingsiterations,
)
(
notanalyzed,
resultsfilename,
DLCscorer,
) = auxiliaryfunctions.CheckifNotEvaluated(
str(evaluationfolder),
DLCscorer,
DLCscorerlegacy,
Snapshots[snapindex],
)
if os.path.isfile(
resultsfilename.split(".h5")[0] + "_full.pickle"):
print("Model already evaluated.", resultsfilename)
else:
if plotting:
foldername = os.path.join(
str(evaluationfolder),
"LabeledImages_" + DLCscorer + "_" +
Snapshots[snapindex],
)
auxiliaryfunctions.attempttomakefolder(foldername)
# print(dlc_cfg)
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(
dlc_cfg)
PredicteData = {}
dist = np.full((len(Data), len(all_bpts)), np.nan)
conf = np.full_like(dist, np.nan)
distnorm = np.full(len(Data), np.nan)
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(
Data.index)):
image_path = os.path.join(cfg["project_path"],
imagename)
image = io.imread(image_path)
frame = img_as_ubyte(skimage.color.gray2rgb(image))
GT = Data.iloc[imageindex]
df = GT.unstack("coords").reindex(
joints, level='bodyparts')
# Evaluate PAF edge lengths to calibrate `distnorm`
temp = GT.unstack("bodyparts")[joints]
xy = temp.values.reshape(
(-1, 2, temp.shape[1])).swapaxes(1, 2)
edges = xy[:, dlc_cfg["partaffinityfield_graph"]]
lengths = np.sum(
(edges[:, :, 0] - edges[:, :, 1])**2, axis=2)
distnorm[imageindex] = np.nanmax(lengths)
# FIXME Is having an empty array vs nan really that necessary?!
groundtruthidentity = list(
df.index.get_level_values(
"individuals").to_numpy().reshape((-1, 1)))
groundtruthcoordinates = list(
df.values[:, np.newaxis])
for i, coords in enumerate(groundtruthcoordinates):
if np.isnan(coords).any():
groundtruthcoordinates[i] = np.empty(
(0, 2), dtype=float)
groundtruthidentity[i] = np.array(
[], dtype=str)
PredicteData[imagename] = {}
PredicteData[imagename]["index"] = imageindex
pred = predictma.get_detectionswithcostsandGT(
frame,
groundtruthcoordinates,
dlc_cfg,
sess,
inputs,
outputs,
outall=False,
nms_radius=dlc_cfg.nmsradius,
det_min_score=dlc_cfg.minconfidence,
c_engine=c_engine,
)
PredicteData[imagename]["prediction"] = pred
PredicteData[imagename]["groundtruth"] = [
groundtruthidentity,
groundtruthcoordinates,
GT,
]
coords_pred = pred["coordinates"][0]
probs_pred = pred["confidence"]
for bpt, xy_gt in df.groupby(level="bodyparts"):
inds_gt = np.flatnonzero(
np.all(~np.isnan(xy_gt), axis=1))
n_joint = joints.index(bpt)
xy = coords_pred[n_joint]
if inds_gt.size and xy.size:
# Pick the predictions closest to ground truth,
# rather than the ones the model has most confident in
d = cdist(xy_gt.iloc[inds_gt], xy)
rows, cols = linear_sum_assignment(d)
min_dists = d[rows, cols]
inds = np.flatnonzero(all_bpts == bpt)
sl = imageindex, inds[inds_gt[rows]]
dist[sl] = min_dists
conf[sl] = probs_pred[n_joint][
cols].squeeze()
if plotting:
fig = visualization.make_multianimal_labeled_image(
frame,
groundtruthcoordinates,
coords_pred,
probs_pred,
colors,
cfg["dotsize"],
cfg["alphavalue"],
cfg["pcutoff"],
)
visualization.save_labeled_frame(
fig,
image_path,
foldername,
imageindex in trainIndices,
)
sess.close() # closes the current tf session
# Compute all distance statistics
df_dist = pd.DataFrame(dist, columns=df.index)
df_conf = pd.DataFrame(conf, columns=df.index)
df_joint = pd.concat([df_dist, df_conf],
keys=["rmse", "conf"],
names=["metrics"],
axis=1)
df_joint = df_joint.reorder_levels(list(
np.roll(df_joint.columns.names, -1)),
axis=1)
df_joint.sort_index(axis=1,
level=["individuals", "bodyparts"],
ascending=[True, True],
inplace=True)
write_path = os.path.join(
evaluationfolder,
f"dist_{trainingsiterations}.csv")
df_joint.to_csv(write_path)
# Calculate overall prediction error
error = df_joint.xs("rmse", level="metrics", axis=1)
mask = df_joint.xs("conf", level="metrics",
axis=1) >= cfg["pcutoff"]
error_masked = error[mask]
error_train = np.nanmean(error.iloc[trainIndices])
error_train_cut = np.nanmean(
error_masked.iloc[trainIndices])
error_test = np.nanmean(error.iloc[testIndices])
error_test_cut = np.nanmean(
error_masked.iloc[testIndices])
results = [
trainingsiterations,
int(100 * trainFraction),
shuffle,
np.round(error_train, 2),
np.round(error_test, 2),
cfg["pcutoff"],
np.round(error_train_cut, 2),
np.round(error_test_cut, 2),
]
final_result.append(results)
# For OKS/PCK, compute the standard deviation error across all frames
sd = df_dist.groupby("bodyparts",
axis=1).mean().std(axis=0)
sd["distnorm"] = np.sqrt(np.nanmax(distnorm))
sd.to_csv(write_path.replace("dist.csv", "sd.csv"))
if show_errors:
string = "Results for {} training iterations: {}, shuffle {}:\n" \
"Train error: {} pixels. Test error: {} pixels.\n" \
"With pcutoff of {}:\n" \
"Train error: {} pixels. Test error: {} pixels."
print(string.format(*results))
print("##########################################")
print(
"Average Euclidean distance to GT per individual (in pixels)"
)
print(
error_masked.groupby(
'individuals',
axis=1).mean().mean().to_string())
print(
"Average Euclidean distance to GT per bodypart (in pixels)"
)
print(
error_masked.groupby(
'bodyparts',
axis=1).mean().mean().to_string())
PredicteData["metadata"] = {
"nms radius":
dlc_cfg.nmsradius,
"minimal confidence":
dlc_cfg.minconfidence,
"PAFgraph":
dlc_cfg.partaffinityfield_graph,
"all_joints":
[[i] for i in range(len(dlc_cfg.all_joints))],
"all_joints_names": [
dlc_cfg.all_joints_names[i]
for i in range(len(dlc_cfg.all_joints))
],
"stride":
dlc_cfg.get("stride", 8),
}
print(
"Done and results stored for snapshot: ",
Snapshots[snapindex],
)
dictionary = {
"Scorer": DLCscorer,
"DLC-model-config file": dlc_cfg,
"trainIndices": trainIndices,
"testIndices": testIndices,
"trainFraction": trainFraction,
}
metadata = {"data": dictionary}
auxfun_multianimal.SaveFullMultiAnimalData(
PredicteData, metadata, resultsfilename)
tf.reset_default_graph()
if len(final_result
) > 0: # Only append if results were calculated
make_results_file(final_result, evaluationfolder,
DLCscorer)
# returning to intial folder
os.chdir(str(start_path))
def extract_maps(
config,
shuffle=0,
trainingsetindex=0,
gputouse=None,
rescale=False,
Indices=None,
modelprefix="",
):
"""
Extracts the scoremap, locref, partaffinityfields (if available).
Returns a dictionary indexed by: trainingsetfraction, snapshotindex, and imageindex
for those keys, each item contains: (image,scmap,locref,paf,bpt names,partaffinity graph, imagename, True/False if this image was in trainingset)
----------
config : string
Full path of the config.yaml file as a string.
shuffle: integer
integers specifying shuffle index of the training dataset. The default is 0.
trainingsetindex: int, optional
Integer specifying which TrainingsetFraction to use. By default the first (note that TrainingFraction is a list in config.yaml). This
variable can also be set to "all".
rescale: bool, default False
Evaluate the model at the 'global_scale' variable (as set in the test/pose_config.yaml file for a particular project). I.e. every
image will be resized according to that scale and prediction will be compared to the resized ground truth. The error will be reported
in pixels at rescaled to the *original* size. I.e. For a [200,200] pixel image evaluated at global_scale=.5, the predictions are calculated
on [100,100] pixel images, compared to 1/2*ground truth and this error is then multiplied by 2!. The evaluation images are also shown for the
original size!
Examples
--------
If you want to extract the data for image 0 and 103 (of the training set) for model trained with shuffle 0.
>>> deeplabcut.extract_maps(configfile,0,Indices=[0,103])
"""
from deeplabcut.utils.auxfun_videos import imread, imresize
from deeplabcut.pose_estimation_tensorflow.nnet import predict
from deeplabcut.pose_estimation_tensorflow.nnet import (
predict_multianimal as predictma, )
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions
from tqdm import tqdm
import tensorflow as tf
vers = (tf.__version__).split(".")
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
import pandas as pd
from pathlib import Path
import numpy as np
TF.reset_default_graph()
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: # gpu selectinon
os.environ["CUDA_VISIBLE_DEVICES"] = str(gputouse)
if trainingsetindex == "all":
TrainingFractions = cfg["TrainingFraction"]
else:
if trainingsetindex < len(
cfg["TrainingFraction"]) and trainingsetindex >= 0:
TrainingFractions = [
cfg["TrainingFraction"][int(trainingsetindex)]
]
else:
raise Exception(
"Please check the trainingsetindex! ",
trainingsetindex,
" should be an integer from 0 .. ",
int(len(cfg["TrainingFraction"]) - 1),
)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(
cfg["project_path"],
str(trainingsetfolder),
"CollectedData_" + cfg["scorer"] + ".h5",
),
"df_with_missing",
)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
Maps = {}
for trainFraction in TrainingFractions:
Maps[trainFraction] = {}
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(trainFraction,
shuffle,
cfg,
modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
(
data,
trainIndices,
testIndices,
trainFraction,
) = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, trainFraction))
# change batch size, if it was edited during analysis!
dlc_cfg["batch_size"] = 1 # in case this was edited for analysis.
# Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg, modelprefix=modelprefix)),
)
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
# path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split(".")[0]
for fn in os.listdir(os.path.join(str(modelfolder), "train"))
if "index" in fn
])
try: # check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
increasing_indices = np.argsort(
[int(m.split("-")[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
########################### RESCALING (to global scale)
scale = dlc_cfg["global_scale"] if rescale else 1
Data *= scale
bptnames = [
dlc_cfg["all_joints_names"][i]
for i in range(len(dlc_cfg["all_joints"]))
]
for snapindex in snapindices:
dlc_cfg["init_weights"] = os.path.join(
str(modelfolder), "train", Snapshots[snapindex]
) # setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg["init_weights"].split(os.sep)[-1]
).split("-")[
-1] # read how many training siterations that corresponds to.
# Name for deeplabcut net (based on its parameters)
# DLCscorer,DLCscorerlegacy = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations)
# notanalyzed, resultsfilename, DLCscorer=auxiliaryfunctions.CheckifNotEvaluated(str(evaluationfolder),DLCscorer,DLCscorerlegacy,Snapshots[snapindex])
# print("Extracting maps for ", DLCscorer, " with # of trainingiterations:", trainingsiterations)
# if notanalyzed: #this only applies to ask if h5 exists...
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = predict.setup_pose_prediction(dlc_cfg)
Numimages = len(Data.index)
PredicteData = np.zeros(
(Numimages, 3 * len(dlc_cfg["all_joints_names"])))
print("Analyzing data...")
if Indices is None:
Indices = enumerate(Data.index)
else:
Ind = [Data.index[j] for j in Indices]
Indices = enumerate(Ind)
DATA = {}
for imageindex, imagename in tqdm(Indices):
image = imread(os.path.join(cfg["project_path"], imagename),
mode="RGB")
if scale != 1:
image = imresize(image, scale)
image_batch = data_to_input(image)
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
if cfg.get("multianimalproject", False):
scmap, locref, paf = predictma.extract_cnn_output(
outputs_np, dlc_cfg)
pagraph = dlc_cfg["partaffinityfield_graph"]
else:
scmap, locref = predict.extract_cnn_output(
outputs_np, dlc_cfg)
paf = None
pagraph = []
if imageindex in testIndices:
trainingfram = False
else:
trainingfram = True
DATA[imageindex] = [
image,
scmap,
locref,
paf,
bptnames,
pagraph,
imagename,
trainingfram,
]
Maps[trainFraction][Snapshots[snapindex]] = DATA
os.chdir(str(start_path))
return Maps
print("Checking labels...")
deeplabcut.check_labels(config_path, draw_skeleton=False)
print("Labels checked.")
print("Creating train dataset...")
deeplabcut.create_multianimaltraining_dataset(
config_path, net_type=NET, crop_size=(200, 200)
)
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]["image"]) == 3 for i in range(num_images))
print("Editing pose config...")
model_folder = auxiliaryfunctions.GetModelFolder(
TRAIN_SIZE, 1, cfg, cfg["project_path"]
)
pose_config_path = os.path.join(model_folder, "train", "pose_cfg.yaml")
edits = {
"global_scale": 0.5,
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
def create_pretrained_human_project(project,
experimenter,
videos,
working_directory=None,
copy_videos=False,
videotype='.avi',
createlabeledvideo=True,
analyzevideo=True):
"""
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!
Parameters
----------
project : string
String containing the name of the project.
experimenter : string
String containing the name of the experimenter.
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
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
Example
--------
Linux/MacOs
>>> deeplabcut.create_pretrained_human_project('human','Linus',['/data/videos/mouse1.avi'],'/analysis/project/',copy_videos=False)
Windows:
>>> deeplabcut.create_pretrained_human_project('human','Bill',[r'C:\yourusername\rig-95\Videos\reachingvideo1.avi'],r'C:\yourusername\analysis\project' copy_videos=False)
Users must format paths with either: r'C:\ OR 'C:\\ <- i.e. a double backslash \ \ )
--------
"""
cfg = deeplabcut.create_new_project(project, experimenter, videos,
working_directory, copy_videos,
videotype)
config = auxiliaryfunctions.read_config(cfg)
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'
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
cwd = os.getcwd()
os.chdir(train_dir)
print(
"Checking if the weights are already available, otherwise I will download them!"
)
weightfilename = auxfun_models.download_mpii_weigths(train_dir)
os.chdir(cwd)
# 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)
bodyparts = config['bodyparts']
net_type = 'resnet_101'
num_shuffles = 1
model_path, num_shuffles = auxfun_models.Check4weights(
net_type, parent_path, num_shuffles)
items2change = {
"dataset": 'dataset-test.mat', #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":
weightfilename.split('.index')[0], #'models/mpii/snapshot-1030000',
"project_path": str(config['project_path']),
"net_type": net_type,
"dataset_type": "default"
}
trainingdata = MakeTrain_pose_yaml(items2change, path_train_config,
defaultconfigfile)
keys2save = [
"dataset", "dataset_type", "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)
video_dir = os.path.join(config['project_path'], 'videos')
if analyzevideo == True:
# Analyze the videos
deeplabcut.analyze_videos(cfg, [video_dir],
videotype,
save_as_csv=True)
if createlabeledvideo == True:
deeplabcut.create_labeled_video(cfg, [video_dir],
videotype,
draw_skeleton=True)
deeplabcut.plot_trajectories(cfg, [video_dir], videotype)
return cfg, path_train_config
def create_training_dataset(config,num_shuffles=1,Shuffles=None,windows2linux=False,userfeedback=False,
trainIndexes=None,testIndexes=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.
trainIndexes: 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.
testIndexes: list of lists, optional (default=None)
List of 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)
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,project_path,Path(os.path.join(project_path,trainingsetfolder)),windows2linux)
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', 'default')
else:
if augmenter_type in ['default','imgaug','tensorpack','deterministic']:
pass
else:
raise ValueError('Invalid augmenter type:', augmenter_type)
import deeplabcut
parent_path = Path(os.path.dirname(deeplabcut.__file__))
defaultconfigfile = str(parent_path / 'pose_cfg.yaml')
model_path,num_shuffles=auxfun_models.Check4weights(net_type,parent_path,num_shuffles) #if the model does not exist >> throws error!
if Shuffles is None:
Shuffles = range(1, num_shuffles + 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
if trainIndexes is None and testIndexes is None:
splits = [(trainFraction, shuffle, SplitTrials(range(len(Data.index)), trainFraction))
for trainFraction in cfg['TrainingFraction'] for shuffle in Shuffles]
else:
if len(trainIndexes) != len(testIndexes):
raise ValueError('Number of train and test indexes should be equal.')
splits = []
for shuffle, (train_inds, test_inds) in enumerate(zip(trainIndexes, testIndexes)):
trainFraction = len(train_inds) / (len(train_inds) + len(test_inds))
print(f"You passed a split with the following fraction: {int(100 * trainFraction)}%")
splits.append((trainFraction, shuffle, (train_inds, test_inds)))
bodyparts = cfg['bodyparts']
nbodyparts = len(bodyparts)
for trainFraction, shuffle, (trainIndexes, testIndexes) in splits:
if len(trainIndexes)>0:
if userfeedback:
trainposeconfigfile, _, _ = training.return_train_network_path(config, shuffle=shuffle, trainFraction=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, trainIndexes, 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, trainIndexes, testIndexes, 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,
}
trainingdata = MakeTrain_pose_yaml(items2change,path_train_config,defaultconfigfile)
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!")
def create_training_dataset(config,num_shuffles=1,Shuffles=None,windows2linux=False,userfeedback=False,
trainIndexes=None,testIndexes=None,
net_type=None,augmenter_type=None,defaultconfigfile=None,items2change_pose={}):
"""
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.
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])
--------
"""
from skimage import io
import scipy.io as sio
# 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) #Path concatenation OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(os.path.join(project_path,str(trainingsetfolder))),recursive=True)
Data = merge_annotateddatasets(cfg,project_path,Path(os.path.join(project_path,trainingsetfolder)),windows2linux)
Data = Data[scorer] #extract labeled data
#%%
# check if we need to update the netwoek
items2change_flag = bool(items2change_pose)
if items2change_flag: # not empty
net_type = items2change_pose.get('net_type', None)
#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', 'default')
else:
if augmenter_type in ['default','imgaug','tensorpack','deterministic']:
pass
else:
raise ValueError('Invalid augmenter type:', augmenter_type)
import deeplabcut
if defaultconfigfile is None:
parent_path = Path(os.path.dirname(deeplabcut.__file__))
defaultconfigfile = str(parent_path / 'pose_cfg.yaml')
model_path,num_shuffles=auxfun_models.Check4weights(net_type,parent_path,num_shuffles) #if the model does not exist >> throws error!
if Shuffles==None:
Shuffles=range(1,num_shuffles+1,1)
else:
Shuffles=[i for i in Shuffles if isinstance(i,int)]
bodyparts = cfg['bodyparts']
TrainingFraction = cfg['TrainingFraction']
for shuffle in Shuffles: # Creating shuffles starting from 1
for trainingsetindex,trainFraction in enumerate(TrainingFraction):
if userfeedback:
trainposeconfigfile,testposeconfigfile,snapshotfolder = training.return_train_network_path(config,shuffle=shuffle,trainingsetindex=trainingsetindex)
if os.path.isfile(trainposeconfigfile):
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.")
else:
pass
#trainIndexes, testIndexes = SplitTrials(range(len(Data.index)), trainFraction)
if trainIndexes is None and testIndexes is None:
trainIndexes, testIndexes = SplitTrials(range(len(Data.index)), trainFraction)
else:
print("You passed a split with the following fraction:", len(trainIndexes)*1./(len(testIndexes)+len(trainIndexes))*100)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
data = []
for jj in trainIndexes:
H = {}
# load image to get dimensions:
filename = Data.index[jj]
im = io.imread(os.path.join(cfg['project_path'],filename))
H['image'] = filename
if np.ndim(im)==3:
H['size'] = np.array(
[np.shape(im)[2],
np.shape(im)[0],
np.shape(im)[1]])
else:
# print "Grayscale!"
H['size'] = np.array([1, np.shape(im)[0], np.shape(im)[1]])
indexjoints=0
joints=np.zeros((len(bodyparts),3))*np.nan
for bpindex,bodypart in enumerate(bodyparts):
# check whether the labels are positive and inside the img
x_pos_n_inside = 0 <= Data[bodypart]['x'][jj] < np.shape(im)[1]
y_pos_n_inside = 0 <= Data[bodypart]['y'][jj] < np.shape(im)[0]
if x_pos_n_inside and y_pos_n_inside:
joints[indexjoints,0]=int(bpindex)
joints[indexjoints,1]=Data[bodypart]['x'][jj]
joints[indexjoints,2]=Data[bodypart]['y'][jj]
indexjoints+=1
joints = joints[np.where(
np.prod(np.isfinite(joints),
1))[0], :] # drop NaN, i.e. lines for missing body parts
assert (np.prod(np.array(joints[:, 2]) < np.shape(im)[0])
) # y coordinate within image?
assert (np.prod(np.array(joints[:, 1]) < np.shape(im)[1])
) # x coordinate within image?
H['joints'] = np.array(joints, dtype=int)
if np.size(joints)>0: #exclude images without labels
data.append(H)
if len(trainIndexes)>0:
datafilename,metadatafilename=auxiliaryfunctions.GetDataandMetaDataFilenames(trainingsetfolder,trainFraction,shuffle,cfg)
################################################################################
# Saving metadata (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(os.path.join(project_path,metadatafilename),data, trainIndexes, testIndexes, trainFraction)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
DTYPE = [('image', 'O'), ('size', 'O'), ('joints', 'O')]
MatlabData = np.array(
[(np.array([data[item]['image']], dtype='U'),
np.array([data[item]['size']]),
boxitintoacell(data[item]['joints']))
for item in range(len(data))],
dtype=DTYPE)
sio.savemat(os.path.join(project_path,datafilename), {'dataset': MatlabData})
################################################################################
# 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
}
items2change.update(items2change_pose)
trainingdata = MakeTrain_pose_yaml(items2change,path_train_config,defaultconfigfile)
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
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_CLARA(config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
trainIndexes=None,
testIndexes=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.
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])
--------
"""
from skimage import io
import scipy.io as sio
from deeplabcut.utils import auxiliaryfunctions, auxfun_models
# 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) #Path concatenation OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(
os.path.join(project_path, str(trainingsetfolder))),
recursive=True)
"""
Merges all the h5 files for all labeled-datasets (from individual videos).
"""
AnnotationData = None
data_path = Path(os.path.join(project_path, 'labeled-data'))
videos = cfg['video_sets'].keys()
video_names = [Path(i).stem for i in videos]
for i in video_names:
try:
data = pd.read_hdf((str(data_path / Path(i)) + '/CollectedData_' +
cfg['scorer'] + '.h5'), 'df_with_missing')
smlData = data.dropna(how='all')
smlKeys = list(smlData.index.values)
smlKeyLong = list()
for sk in smlKeys:
smlKeyLong.append('labeled-data/' + str(Path(i)) + '/' + sk)
smlData.index = smlKeyLong
data = smlData
if AnnotationData is None:
AnnotationData = data
else:
AnnotationData = pd.concat([AnnotationData, data])
except FileNotFoundError:
print((str(data_path / Path(i)) + '/CollectedData_' +
cfg['scorer'] + '.h5'),
" not found (perhaps not annotated)")
trainingsetfolder_full = Path(os.path.join(project_path,
trainingsetfolder))
filename = str(
str(trainingsetfolder_full) + '/' + '/CollectedData_' + cfg['scorer'])
AnnotationData.to_hdf(filename + '.h5', key='df_with_missing', mode='w')
AnnotationData.to_csv(filename + '.csv') #human readable.
Data = AnnotationData
Data = Data[scorer] #extract labeled data
#loading & linking pretrained models
net_type = 'resnet_' + str(cfg['resnet'])
import deeplabcut
parent_path = Path(os.path.dirname(deeplabcut.__file__))
defaultconfigfile = str(parent_path / 'pose_cfg.yaml')
model_path, num_shuffles = auxfun_models.Check4weights(
net_type, parent_path, num_shuffles)
if Shuffles == None:
Shuffles = range(1, num_shuffles + 1, 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
bodyparts = cfg['bodyparts']
if isinstance(bodyparts, list):
parts = bodyparts
else:
parts = list()
categories = list()
for cat in bodyparts.keys():
categories.append(cat)
for key in categories:
for ptname in bodyparts[key]:
parts.append(ptname)
bodyparts = parts
TrainingFraction = cfg['TrainingFraction']
for shuffle in Shuffles: # Creating shuffles starting from 1
for trainFraction in TrainingFraction:
#trainIndexes, testIndexes = SplitTrials(range(len(Data.index)), trainFraction)
if trainIndexes is None and testIndexes is None:
trainIndexes, testIndexes = SplitTrials_CLARA(
range(len(Data.index)), trainFraction)
else:
print(
"You passed a split with the following fraction:",
len(trainIndexes) * 1. /
(len(testIndexes) + len(trainIndexes)) * 100)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
data = []
for jj in trainIndexes:
H = {}
# load image to get dimensions:
filename = Data.index[jj]
im = io.imread(os.path.join(cfg['project_path'], filename))
H['image'] = filename
if np.ndim(im) == 3:
H['size'] = np.array(
[np.shape(im)[2],
np.shape(im)[0],
np.shape(im)[1]])
else:
# print "Grayscale!"
H['size'] = np.array([1, np.shape(im)[0], np.shape(im)[1]])
indexjoints = 0
joints = np.zeros((len(bodyparts), 3)) * np.nan
for bpindex, bodypart in enumerate(bodyparts):
if Data[bodypart]['x'][jj] < np.shape(
im)[1] and Data[bodypart]['y'][jj] < np.shape(
im)[0]: #are labels in image?
joints[indexjoints, 0] = int(bpindex)
joints[indexjoints, 1] = Data[bodypart]['x'][jj]
joints[indexjoints, 2] = Data[bodypart]['y'][jj]
indexjoints += 1
joints = joints[np.where(np.prod(
np.isfinite(joints),
1))[0], :] # drop NaN, i.e. lines for missing body parts
assert (np.prod(np.array(joints[:, 2]) < np.shape(im)[0])
) # y coordinate within image?
assert (np.prod(np.array(joints[:, 1]) < np.shape(im)[1])
) # x coordinate within image?
H['joints'] = np.array(joints, dtype=int)
if np.size(joints) > 0: #exclude images without labels
data.append(H)
if len(trainIndexes) > 0:
datafilename, metadatafilename = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
################################################################################
# Saving metadata (Pickle file)
################################################################################
auxiliaryfunctions.SaveMetadata(
os.path.join(project_path, metadatafilename), data,
trainIndexes, testIndexes, trainFraction)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
DTYPE = [('image', 'O'), ('size', 'O'), ('joints', 'O')]
MatlabData = np.array(
[(np.array([data[item]['image']],
dtype='U'), np.array([data[item]['size']]),
boxitintoacell_CLARA(data[item]['joints']))
for item in range(len(data))],
dtype=DTYPE)
sio.savemat(os.path.join(project_path, datafilename),
{'dataset': MatlabData})
################################################################################
# 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,
"crop": 'False'
}
trainingdata = MakeTrain_pose_yaml_CLARA(
items2change, path_train_config, defaultconfigfile)
keys2save = [
"dataset", "num_joints", "all_joints", "all_joints_names",
"net_type", 'init_weights', 'global_scale',
'location_refinement', 'locref_stdev'
]
MakeTest_pose_yaml_CLARA(trainingdata, keys2save,
path_test_config)
deeplabcut.train_network(config)
def create_multianimaltraining_dataset(
config,
num_shuffles=1,
Shuffles=None,
windows2linux=False,
net_type=None,
numdigits=2,
):
"""
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_video' 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!).
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.
net_type: string
Type of networks. Currently resnet_50, resnet_101, and resnet_152 are supported (not the MobileNets!)
numdigits: int, optional
Example
--------
>>> deeplabcut.create_multianimaltraining_dataset('/analysis/project/reaching-task/config.yaml',num_shuffles=1)
Windows:
>>> deeplabcut.create_multianimaltraining_dataset(r'C:\\Users\\Ulf\\looming-task\\config.yaml',Shuffles=[3,17,5])
--------
"""
from skimage import io
# 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) # Path concatenatn OS platform independent
auxiliaryfunctions.attempttomakefolder(Path(
os.path.join(project_path, str(trainingsetfolder))),
recursive=True)
Data = trainingsetmanipulation.merge_annotateddatasets(
cfg, Path(os.path.join(project_path, trainingsetfolder)),
windows2linux)
if Data is None:
return
Data = Data[scorer] # extract labeled data
# actualbpts=set(Data.columns.get_level_values(0))
def strip_cropped_image_name(path):
# utility function to split different crops from same image into either train or test!
filename = os.path.split(path)[1]
return filename.split("c")[0]
img_names = Data.index.map(strip_cropped_image_name).unique()
# loading & linking pretrained models
# CURRENTLY ONLY ResNet supported!
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("Currently only resnet is supported.")
# multianimal case:
dataset_type = "multi-animal-imgaug"
partaffinityfield_graph = auxfun_multianimal.getpafgraph(cfg,
printnames=False)
# ATTENTION: order has to be multibodyparts, then uniquebodyparts (for indexing)
print("Utilizing the following graph:", partaffinityfield_graph)
num_limbs = len(partaffinityfield_graph)
partaffinityfield_predict = True
# 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 == None:
Shuffles = range(1, num_shuffles + 1, 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
(
individuals,
uniquebodyparts,
multianimalbodyparts,
) = auxfun_multianimal.extractindividualsandbodyparts(cfg)
TrainingFraction = cfg["TrainingFraction"]
for shuffle in Shuffles: # Creating shuffles starting from 1
for trainFraction in TrainingFraction:
train_inds_temp, test_inds_temp = trainingsetmanipulation.SplitTrials(
range(len(img_names)), trainFraction)
# Map back to the original indices.
temp = [
name for i, name in enumerate(img_names) if i in test_inds_temp
]
mask = Data.index.str.contains("|".join(temp))
testIndices = np.flatnonzero(mask)
trainIndices = np.flatnonzero(~mask)
####################################################
# Generating data structure with labeled information & frame metadata (for deep cut)
####################################################
# Make training file!
data = []
print("Creating training data for ", shuffle, trainFraction)
print("This can take some time...")
for jj in tqdm(trainIndices):
jointsannotated = False
H = {}
# load image to get dimensions:
filename = Data.index[jj]
im = io.imread(os.path.join(cfg["project_path"], filename))
H["image"] = filename
try:
H["size"] = np.array(
[np.shape(im)[2],
np.shape(im)[0],
np.shape(im)[1]])
except:
# print "Grayscale!"
H["size"] = np.array([1, np.shape(im)[0], np.shape(im)[1]])
Joints = {}
for prfxindex, prefix in enumerate(individuals):
joints = (np.zeros(
(len(uniquebodyparts) + len(multianimalbodyparts), 3))
* np.nan)
if prefix != "single": # first ones are multianimalparts!
indexjoints = 0
for bpindex, bodypart in enumerate(
multianimalbodyparts):
socialbdpt = bodypart # prefix+bodypart #build names!
# if socialbdpt in actualbpts:
try:
x, y = (
Data[prefix][socialbdpt]["x"][jj],
Data[prefix][socialbdpt]["y"][jj],
)
joints[indexjoints, 0] = int(bpindex)
joints[indexjoints, 1] = round(x, numdigits)
joints[indexjoints, 2] = round(y, numdigits)
indexjoints += 1
except:
pass
else:
indexjoints = len(multianimalbodyparts)
for bpindex, bodypart in enumerate(uniquebodyparts):
socialbdpt = bodypart # prefix+bodypart #build names!
# if socialbdpt in actualbpts:
try:
x, y = (
Data[prefix][socialbdpt]["x"][jj],
Data[prefix][socialbdpt]["y"][jj],
)
joints[indexjoints, 0] = len(
multianimalbodyparts) + int(bpindex)
joints[indexjoints, 1] = round(x, 2)
joints[indexjoints, 2] = round(y, 2)
indexjoints += 1
except:
pass
# Drop missing body parts
joints = joints[~np.isnan(joints).any(axis=1)]
# Drop points lying outside the image
inside = np.logical_and.reduce((
joints[:, 1] < im.shape[1],
joints[:, 1] > 0,
joints[:, 2] < im.shape[0],
joints[:, 2] > 0,
))
joints = joints[inside]
if np.size(joints) > 0: # exclude images without labels
jointsannotated = True
Joints[prfxindex] = joints # np.array(joints, dtype=int)
H["joints"] = Joints
if jointsannotated: # exclude images without labels
data.append(H)
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.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",
))
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,
"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,
}
defaultconfigfile = os.path.join(dlcparent_path,
"pose_cfg.yaml")
trainingdata = trainingsetmanipulation.MakeTrain_pose_yaml(
items2change, path_train_config, defaultconfigfile)
keys2save = [
"dataset",
"num_joints",
"all_joints",
"all_joints_names",
"net_type",
"init_weights",
"global_scale",
"location_refinement",
"locref_stdev",
"dataset_type",
"partaffinityfield_predict",
"pairwise_predict",
"partaffinityfield_graph",
"num_limbs",
"dataset_type",
]
trainingsetmanipulation.MakeTest_pose_yaml(
trainingdata,
keys2save,
path_test_config,
nmsradius=5.0,
minconfidence=0.01,
) # 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),
}
# TODO: "distnormalization": could be calculated here based on data and set
# >> now we calculate this during evaluation (which is a good spot...)
trainingsetmanipulation.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
data_info.model_data_dir,
scorer=data_info.scorer,
date=date)
# Load pretrained weights
dlc_cfg = get_train_config(cfg, shuffle)
# load training file
trainingsnapshot_name, trainingsnapshot, dlc_cfg = load_dlc_snapshot(
dlc_cfg, overwrite_snapshot=49999)
# Load metadata
from deeplabcut.utils import auxiliaryfunctions
import os
trainingsetindex = 0
trainFraction = cfg["TrainingFraction"][trainingsetindex]
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(auxiliaryfunctions.GetModelFolder(trainFraction, shuffle, cfg)))
data, trainIndices, testIndices, trainFraction = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
#%%
scale = dlc_cfg['global_scale']
Data = pd.read_hdf(
os.path.join(cfg["project_path"], str(trainingsetfolder), 'CollectedData_'
+ cfg["scorer"] + '.h5'), 'df_with_missing') * scale
#%%
num_labels, _ = Data.values.shape
labeled_frames = np.empty(num_labels).astype('int')
for frame_idx in range(num_labels):
def evaluate_multiview_network(config,videos,projection_matrices,multiview_step,snapshot_index=None,Shuffles=[1],plotting = None,show_errors = True,comparisonbodyparts="all",gputouse=None):
"""
Evaluates the network based on the saved models at different stages of the training network.\n
The evaluation results are stored in the .h5 and .csv file under the subdirectory 'evaluation_results'.
Change the snapshotindex parameter in the config file to 'all' in order to evaluate all the saved models.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
videos: list of strings
Name of each video, one per viewpoint. Must be in the same order that it was in for training
projection_matrices: list of arrays
Projection matrix for each viewpoint. Each is a 3x4 array
multiview_step:
1 or 2. Indicates whether network was trained with train_multiview_network_step_1 or train_multiview_network_step_2
Shuffles: list, optional
List of integers specifying the shuffle indices of the training dataset. The default is [1]
plotting: bool, optional
Plots the predictions on the train and test images. The default is ``False``; if provided it must be either ``True`` or ``False``
show_errors: bool, optional
Display train and test errors. The default is `True``
comparisonbodyparts: list of bodyparts, Default is "all".
The average error will be computed for those body parts only (Has to be a subset of the body parts).
gputouse: int, optional. Natural number indicating the number of your GPU (see number in nvidia-smi). If you do not have a GPU put None.
See: https://nvidia.custhelp.com/app/answers/detail/a_id/3751/~/useful-nvidia-smi-queries
Examples
--------
If you do not want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml', shuffle=[1])
--------
If you want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml',shuffle=[1],True)
"""
import os
from skimage import io
import skimage.color
from deeplabcut.pose_estimation_tensorflow.nnet import predict as ptf_predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions, visualization
import tensorflow as tf
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ['TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
tf.reset_default_graph()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path=os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
# Loading human annotatated data
trainingsetfolder=auxiliaryfunctions.GetTrainingSetFolder(cfg)
Datas = [pd.read_hdf(os.path.join(cfg['project_path'], 'labeled-data', video, 'CollectedData_'+cfg['scorer']+'.h5'), 'df_with_missing') for video in videos]
# Get list of body parts to evaluate network for
comparisonbodyparts=auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(cfg,comparisonbodyparts)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(str(cfg["project_path"]+"/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in cfg["TrainingFraction"]:
##################################################
# Load and setup CNN part detector
##################################################
datafn,metadatafn=auxiliaryfunctions.GetDataandMetaDataFilenames(trainingsetfolder,trainFraction,shuffle,cfg)
modelfolder=os.path.join(cfg["project_path"],str(auxiliaryfunctions.GetModelFolder(trainFraction,shuffle,cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
# Load meta data
metadatas = []
for video in videos:
m = ('-'+video).join(os.path.splitext(metadatafn))
data, trainIndices, testIndices, trainFraction=auxiliaryfunctions.LoadMetadata(os.path.join(cfg["project_path"],m))
metadatas.append(data)
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError("It seems the model for shuffle %s and trainFraction %s does not exist."%(shuffle,trainFraction))
#change batch size, if it was edited during analysis!
dlc_cfg['batch_size']=1 #in case this was edited for analysis.
#Create folder structure to store results.
evaluationfolder=os.path.join(cfg["project_path"],str(auxiliaryfunctions.GetEvaluationFolder(trainFraction,shuffle,cfg)))
auxiliaryfunctions.attempttomakefolder(evaluationfolder,recursive=True)
#path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
dlc_cfg.multiview_step = multiview_step
dlc_cfg.projection_matrices = projection_matrices
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([fn.split('.')[0]for fn in os.listdir(os.path.join(str(modelfolder), 'train'))if "index" in fn])
try: #check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError("Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."%(shuffle,trainFraction))
increasing_indices = np.argsort([int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if snapshot_index is not None:
snapindices = [i for i in range(len(Snapshots)) if int(Snapshots[i].split('-')[1].split('.')[0])==snapshot_index]
elif cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"]<len(Snapshots):
snapindices=[cfg["snapshotindex"]]
else:
print("Invalid choice, only -1 (last), any integer up to last, or all (as string)!")
final_result=[]
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(str(modelfolder),'train',Snapshots[snapindex]) #setting weights to corresponding snapshot.
trainingsiterations = (dlc_cfg['init_weights'].split(os.sep)[-1]).split('-')[-1] #read how many training siterations that corresponds to.
#name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(cfg,shuffle,trainFraction,trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:", trainingsiterations)
resultsfilename=os.path.join(str(evaluationfolder),DLCscorer + '-' + Snapshots[snapindex]+ '.h5')
try:
DataMachine = pd.read_hdf(resultsfilename,'df_with_missing')
print("This net has already been evaluated!")
except FileNotFoundError:
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(dlc_cfg)
Numimages = len(Datas[0].index)
PredicteDatas = np.zeros((Numimages,len(Datas), 3 * len(dlc_cfg['all_joints_names'])))
imagesizes = []
print("Analyzing data...")
if multiview_step == 1:
for imageindex in tqdm(range(len(Datas[0].index))):
imagenames = [Data.index[imageindex] for Data in Datas]
images = [io.imread(os.path.join(cfg['project_path'],imagename),mode='RGB') for imagename in imagenames]
images = [skimage.color.gray2rgb(image) for image in images]
image_batch = images
imagesizes.append([image.shape for image in images])
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
scmap, locref = ptf_predict.extract_cnn_output(outputs_np, dlc_cfg)
# Extract maximum scoring location from the heatmap, assume 1 person
pose = ptf_predict.argmax_pose_predict(scmap, locref, dlc_cfg.stride)
PredicteDatas[imageindex] = pose.reshape([pose.shape[0], -1]) # NOTE: thereby cfg_test['all_joints_names'] should be same order as bodyparts!
sess.close() #closes the current tf session
index = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'], ['x', 'y', 'likelihood']],
names=['scorer', 'bodyparts', 'coords'])
# Saving results
for i, video in enumerate(videos):
print('Evaluating 2D predictions on video %s'%video)
Data = Datas[i]
DataMachine = pd.DataFrame(PredicteDatas[:,i], columns=index, index=Data.index.values)
r = ('-'+video).join(os.path.splitext(resultsfilename))
DataMachine.to_hdf(r,'df_with_missing',format='table',mode='w')
print("Done and results stored for snapshot: ", Snapshots[snapindex])
DataCombined = pd.concat([Data.T, DataMachine.T], axis=0).T
RMSE,RMSEpcutoff = pairwisedistances(DataCombined, cfg["scorer"], DLCscorer,cfg["pcutoff"],comparisonbodyparts)
testerror = np.nanmean(RMSE.iloc[testIndices].values.flatten())
trainerror = np.nanmean(RMSE.iloc[trainIndices].values.flatten())
testerrorpcutoff = np.nanmean(RMSEpcutoff.iloc[testIndices].values.flatten())
trainerrorpcutoff = np.nanmean(RMSEpcutoff.iloc[trainIndices].values.flatten())
results = [trainingsiterations,int(100 * trainFraction),shuffle,np.round(trainerror,2),np.round(testerror,2),cfg["pcutoff"],np.round(trainerrorpcutoff,2), np.round(testerrorpcutoff,2)]
final_result.append(results)
if show_errors == True:
print("Results for",trainingsiterations," training iterations:", int(100 * trainFraction), shuffle, "train error:",np.round(trainerror,2), "pixels. Test error:", np.round(testerror,2)," pixels.")
print("With pcutoff of", cfg["pcutoff"]," train error:",np.round(trainerrorpcutoff,2), "pixels. Test error:", np.round(testerrorpcutoff,2), "pixels")
print("Thereby, the errors are given by the average distances between the labels by DLC and the scorer.")
if plotting == True:
print("Plotting...")
colors = visualization.get_cmap(len(comparisonbodyparts),name=cfg['colormap'])
foldername=os.path.join(str(evaluationfolder),'LabeledImages_' + DLCscorer + '_' + Snapshots[snapindex]+'_'+video)
auxiliaryfunctions.attempttomakefolder(foldername)
NumFrames=np.size(DataCombined.index)
for ind in np.arange(NumFrames):
visualization.PlottingandSaveLabeledFrame(DataCombined,ind,trainIndices,cfg,colors,comparisonbodyparts,DLCscorer,foldername)
# get predictions in homogeneous pixel coordinates
# pixel coordinates have (0,0) in the top-left, and the bottom-right coordinate is (h,w)
predictions = PredicteDatas.reshape(Numimages, len(Datas), len(dlc_cfg['all_joints_names']), 3)
scores = np.copy(predictions[:,:,:,2])
predictions[:,:,:,2] = 1.0 # homogeneous coordinates; (x,y,1). Top-left corner is (-width/2, -height/2, 1); Bottom-right corner is opposite. Shape is num_images x num_views x num_joints x 3
num_ims, num_views, num_joints, _ = predictions.shape
# get labels in homogeneous pixel coordinates
labels = np.array([Data.values.reshape(num_ims, num_joints, 2) for Data in Datas]) # num_views x num_ims x num_joints x (x,y)
labels = np.transpose(labels, [1, 2, 0, 3]) # num_ims x num_joints x num_views x (x,y)
labels = np.concatenate([labels, np.ones([num_ims, num_joints, num_views, 1])], axis=3)
# solve linear system to get labels in 3D
# helpful explanation of equation found on pg 5 here: https://hal.inria.fr/inria-00524401/PDF/Sturm-cvpr05.pdf
labs = labels.reshape([num_ims * num_joints, num_views, 3]).astype(np.float)
confidences = ~np.isnan(np.sum(labs, axis=2))
valid = np.sum(~np.isnan(np.sum(labs, axis=2)), axis=1) >= 2
labs[~confidences] = 0
labels3d = project_3d(projection_matrices, labs, confidences=confidences)
labels3d[~valid] = np.nan
labels3d = labels3d.reshape([num_ims, num_joints, 3])
# solve linear system to get 3D predictions
preds = np.transpose(predictions, [0, 2, 1, 3]) # num_ims x num_joints x num_views x 3
preds = preds.reshape([num_ims*num_joints, num_views, 3])
preds3d = project_3d(projection_matrices, preds)
preds3d = preds3d.reshape([num_ims, num_joints, 3])
# try it with confidence weighting
scores = np.transpose(scores, [0, 2, 1]) # num_images x num_joints x num_views
scores = np.reshape(scores, [num_ims*num_joints, num_views])
preds3d_weighted = project_3d(projection_matrices, preds, confidences=scores)
preds3d_weighted = preds3d_weighted.reshape([num_ims, num_joints, 3])
# try it with the pcutoff
scores2 = np.copy(scores)
scores2[scores2 < cfg["pcutoff"]] = 0
preds3d_weighted_cutoff = project_3d(projection_matrices, preds, confidences=scores2)
preds3d_weighted_cutoff = preds3d_weighted_cutoff.reshape([num_ims, num_joints, 3])
print("\n\n3D errors:")
RMSE_train = np.nanmean(np.nansum((preds3d[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test = np.nanmean(np.nansum((preds3d[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
RMSE_train_weighted = np.nanmean(np.nansum((preds3d_weighted[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test_weighted = np.nanmean(np.nansum((preds3d_weighted[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
RMSE_train_weighted_cutoff = np.nanmean(np.nansum((preds3d_weighted_cutoff[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test_weighted_cutoff = np.nanmean(np.nansum((preds3d_weighted_cutoff[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
print("RMSE train: ", RMSE_train)
print("RMSE test: ", RMSE_test)
print("RMSE train weighted: ", RMSE_train_weighted)
print("RMSE test weighted: ", RMSE_test_weighted)
print("RMSE train weighted cutoff: ", RMSE_train_weighted_cutoff)
print("RMSE test weighted cutoff: ", RMSE_test_weighted_cutoff)
tail = np.nansum((preds3d_weighted - labels3d)**2, axis=2)**0.5
tail = np.sort(tail[~np.isnan(tail)])
tail = tail[-10:]
print('10 worst predictions: ', tail)
tf.reset_default_graph()
elif multiview_step==2:
preds3d = []
for imageindex in tqdm(range(len(Datas[0].index))):
imagenames = [Data.index[imageindex] for Data in Datas]
images = [io.imread(os.path.join(cfg['project_path'],imagename),mode='RGB') for imagename in imagenames]
images = [skimage.color.gray2rgb(image) for image in images]
image_batch = images
# Compute prediction with the CNN
outputs_np = sess.run(outputs, feed_dict={inputs: image_batch})
pred_3d = outputs_np[2]
preds3d.append(pred_3d)
sess.close() #closes the current tf session
preds3d = np.array(preds3d) # num_ims x num_joints x (x,y,z)
num_ims, num_joints = preds3d.shape[:2]
num_views = dlc_cfg.num_views
# get labels in homogeneous pixel coordinates
labels = np.array([Data.values.reshape(num_ims, num_joints, 2) for Data in Datas]) # num_views x num_ims x num_joints x (x,y)
labels = np.transpose(labels, [1, 2, 0, 3]) # num_ims x num_joints x num_views x (x,y)
labels = np.concatenate([labels, np.ones([num_ims, num_joints, num_views, 1])], axis=3)
# solve linear system to get labels in 3D
# helpful explanation of equation found on pg 5 here: https://hal.inria.fr/inria-00524401/PDF/Sturm-cvpr05.pdf
labs = labels.reshape([num_ims * num_joints, num_views, 3]).astype(np.float)
confidences = ~np.isnan(np.sum(labs, axis=2))
valid = np.sum(~np.isnan(np.sum(labs, axis=2)), axis=1) >= 2
labs[~confidences] = 0
labels3d = project_3d(projection_matrices, labs, confidences=confidences)
labels3d[~valid] = np.nan
labels3d = labels3d.reshape([num_ims, num_joints, 3])
print("\n\n3D errors (units are determined by projection matrices):")
RMSE_train = np.nanmean(np.nansum((preds3d[trainIndices] - labels3d[trainIndices])**2, axis=2)**0.5)
RMSE_test = np.nanmean(np.nansum((preds3d[testIndices] - labels3d[testIndices])**2, axis=2)**0.5)
print("RMSE train: ", RMSE_train)
print("RMSE test: ", RMSE_test)
tail = np.nansum((preds3d- labels3d)**2, axis=2)**0.5
tail = np.sort(tail[~np.isnan(tail)])
tail = tail[-10:]
print('10 worst predictions: ', tail)
tf.reset_default_graph()
else:
print('invalid multiview_step given')
return
make_results_file(final_result,evaluationfolder,DLCscorer)
print("The network is evaluated and the results are stored in the subdirectory 'evaluation_results'.")
print("If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos.")
print("Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)")
#returning to intial folder
os.chdir(str(start_path))
def 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.GetModelFolder(trainFraction,
shuffle,
cfg,
modelprefix=modelprefix)),
)
path_test_config = Path(modelfolder) / "test" / "pose_cfg.yaml"
# Load meta data
data, trainIndices, testIndices, trainFraction = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, trainFraction))
########################### 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.GetEvaluationFolder(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 evaluate_network(config,
Shuffles=[1],
plotting=None,
show_errors=True,
comparisonbodyparts="all",
gputouse=None):
"""
Evaluates the network based on the saved models at different stages of the training network.\n
The evaluation results are stored in the .h5 and .csv file under the subdirectory 'evaluation_results'.
Change the snapshotindex parameter in the config file to 'all' in order to evaluate all the saved models.
Parameters
----------
config : string
Full path of the config.yaml file as a string.
Shuffles: list, optional
List of integers specifying the shuffle indices of the training dataset. The default is [1]
plotting: bool, optional
Plots the predictions on the train and test images. The default is ``False``; if provided it must be either ``True`` or ``False``
show_errors: bool, optional
Display train and test errors. The default is `True``
comparisonbodyparts: list of bodyparts, Default is "all".
The average error will be computed for those body parts only (Has to be a subset of the body parts).
gputouse: int, optional. Natural number indicating the number of your GPU (see number in nvidia-smi). If you do not have a GPU put None.
See: https://nvidia.custhelp.com/app/answers/detail/a_id/3751/~/useful-nvidia-smi-queries
Examples
--------
If you do not want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml', shuffle=[1])
--------
If you want to plot
>>> deeplabcut.evaluate_network('/analysis/project/reaching-task/config.yaml',shuffle=[1],True)
"""
import os
from skimage import io
import skimage.color
from deeplabcut.pose_estimation_tensorflow.nnet import predict as ptf_predict
from deeplabcut.pose_estimation_tensorflow.config import load_config
from deeplabcut.pose_estimation_tensorflow.dataset.pose_dataset import data_to_input
from deeplabcut.utils import auxiliaryfunctions, visualization
import tensorflow as tf
if 'TF_CUDNN_USE_AUTOTUNE' in os.environ:
del os.environ[
'TF_CUDNN_USE_AUTOTUNE'] #was potentially set during training
vers = (tf.__version__).split('.')
if int(vers[0]) == 1 and int(vers[1]) > 12:
TF = tf.compat.v1
else:
TF = tf
TF.reset_default_graph()
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' #
# tf.logging.set_verbosity(tf.logging.WARN)
start_path = os.getcwd()
# Read file path for pose_config file. >> pass it on
cfg = auxiliaryfunctions.read_config(config)
if gputouse is not None: #gpu selectinon
os.environ['CUDA_VISIBLE_DEVICES'] = str(gputouse)
# Loading human annotatated data
trainingsetfolder = auxiliaryfunctions.GetTrainingSetFolder(cfg)
Data = pd.read_hdf(
os.path.join(cfg["project_path"], str(trainingsetfolder),
'CollectedData_' + cfg["scorer"] + '.h5'),
'df_with_missing')
# Get list of body parts to evaluate network for
comparisonbodyparts = auxiliaryfunctions.IntersectionofBodyPartsandOnesGivenbyUser(
cfg, comparisonbodyparts)
# Make folder for evaluation
auxiliaryfunctions.attempttomakefolder(
str(cfg["project_path"] + "/evaluation-results/"))
for shuffle in Shuffles:
for trainFraction in cfg["TrainingFraction"]:
##################################################
# Load and setup CNN part detector
##################################################
datafn, metadatafn = auxiliaryfunctions.GetDataandMetaDataFilenames(
trainingsetfolder, trainFraction, shuffle, cfg)
modelfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetModelFolder(trainFraction, shuffle,
cfg)))
path_test_config = Path(modelfolder) / 'test' / 'pose_cfg.yaml'
# Load meta data
data, trainIndices, testIndices, trainFraction = auxiliaryfunctions.LoadMetadata(
os.path.join(cfg["project_path"], metadatafn))
try:
dlc_cfg = load_config(str(path_test_config))
except FileNotFoundError:
raise FileNotFoundError(
"It seems the model for shuffle %s and trainFraction %s does not exist."
% (shuffle, trainFraction))
#change batch size, if it was edited during analysis!
dlc_cfg['batch_size'] = 1 #in case this was edited for analysis.
#Create folder structure to store results.
evaluationfolder = os.path.join(
cfg["project_path"],
str(
auxiliaryfunctions.GetEvaluationFolder(
trainFraction, shuffle, cfg)))
auxiliaryfunctions.attempttomakefolder(evaluationfolder,
recursive=True)
#path_train_config = modelfolder / 'train' / 'pose_cfg.yaml'
# Check which snapshots are available and sort them by # iterations
Snapshots = np.array([
fn.split('.')[0]
for fn in os.listdir(os.path.join(str(modelfolder), 'train'))
if "index" in fn
])
try: #check if any where found?
Snapshots[0]
except IndexError:
raise FileNotFoundError(
"Snapshots not found! It seems the dataset for shuffle %s and trainFraction %s is not trained.\nPlease train it before evaluating.\nUse the function 'train_network' to do so."
% (shuffle, trainFraction))
increasing_indices = np.argsort(
[int(m.split('-')[1]) for m in Snapshots])
Snapshots = Snapshots[increasing_indices]
if cfg["snapshotindex"] == -1:
snapindices = [-1]
elif cfg["snapshotindex"] == "all":
snapindices = range(len(Snapshots))
elif cfg["snapshotindex"] < len(Snapshots):
snapindices = [cfg["snapshotindex"]]
else:
print(
"Invalid choice, only -1 (last), any integer up to last, or all (as string)!"
)
final_result = []
##################################################
# Compute predictions over images
##################################################
for snapindex in snapindices:
dlc_cfg['init_weights'] = os.path.join(
str(modelfolder), 'train', Snapshots[snapindex]
) #setting weights to corresponding snapshot.
trainingsiterations = (
dlc_cfg['init_weights'].split(os.sep)[-1]
).split(
'-'
)[-1] #read how many training siterations that corresponds to.
#name for deeplabcut net (based on its parameters)
DLCscorer = auxiliaryfunctions.GetScorerName(
cfg, shuffle, trainFraction, trainingsiterations)
print("Running ", DLCscorer, " with # of trainingiterations:",
trainingsiterations)
resultsfilename = os.path.join(
str(evaluationfolder),
DLCscorer + '-' + Snapshots[snapindex] + '.h5')
try:
DataMachine = pd.read_hdf(resultsfilename,
'df_with_missing')
print("This net has already been evaluated!")
except FileNotFoundError:
# Specifying state of model (snapshot / training state)
sess, inputs, outputs = ptf_predict.setup_pose_prediction(
dlc_cfg)
Numimages = len(Data.index)
PredicteData = np.zeros(
(Numimages, 3 * len(dlc_cfg['all_joints_names'])))
print("Analyzing data...")
for imageindex, imagename in tqdm(enumerate(Data.index)):
image = io.imread(os.path.join(cfg['project_path'],
imagename),
mode='RGB')
image = skimage.color.gray2rgb(image)
image_batch = data_to_input(image)
# Compute prediction with the CNN
outputs_np = sess.run(outputs,
feed_dict={inputs: image_batch})
scmap, locref = ptf_predict.extract_cnn_output(
outputs_np, dlc_cfg)
# Extract maximum scoring location from the heatmap, assume 1 person
pose = ptf_predict.argmax_pose_predict(
scmap, locref, dlc_cfg.stride)
PredicteData[imageindex, :] = pose.flatten(
) # NOTE: thereby cfg_test['all_joints_names'] should be same order as bodyparts!
sess.close() #closes the current tf session
index = pd.MultiIndex.from_product(
[[DLCscorer], dlc_cfg['all_joints_names'],
['x', 'y', 'likelihood']],
names=['scorer', 'bodyparts', 'coords'])
# Saving results
DataMachine = pd.DataFrame(PredicteData,
columns=index,
index=Data.index.values)
DataMachine.to_hdf(resultsfilename,
'df_with_missing',
format='table',
mode='w')
print("Done and results stored for snapshot: ",
Snapshots[snapindex])
DataCombined = pd.concat([Data.T, DataMachine.T], axis=0).T
RMSE, RMSEpcutoff = pairwisedistances(
DataCombined, cfg["scorer"], DLCscorer, cfg["pcutoff"],
comparisonbodyparts)
testerror = np.nanmean(
RMSE.iloc[testIndices].values.flatten())
trainerror = np.nanmean(
RMSE.iloc[trainIndices].values.flatten())
testerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[testIndices].values.flatten())
trainerrorpcutoff = np.nanmean(
RMSEpcutoff.iloc[trainIndices].values.flatten())
results = [
trainingsiterations,
int(100 * trainFraction), shuffle,
np.round(trainerror, 2),
np.round(testerror, 2), cfg["pcutoff"],
np.round(trainerrorpcutoff, 2),
np.round(testerrorpcutoff, 2)
]
final_result.append(results)
if show_errors == True:
print("Results for",
trainingsiterations, " training iterations:",
int(100 * trainFraction), shuffle,
"train error:",
np.round(trainerror, 2), "pixels. Test error:",
np.round(testerror, 2), " pixels.")
print("With pcutoff of",
cfg["pcutoff"], " train error:",
np.round(trainerrorpcutoff,
2), "pixels. Test error:",
np.round(testerrorpcutoff, 2), "pixels")
print(
"Thereby, the errors are given by the average distances between the labels by DLC and the scorer."
)
if plotting == True:
print("Plotting...")
colors = visualization.get_cmap(
len(comparisonbodyparts), name=cfg['colormap'])
foldername = os.path.join(
str(evaluationfolder), 'LabeledImages_' +
DLCscorer + '_' + Snapshots[snapindex])
auxiliaryfunctions.attempttomakefolder(foldername)
NumFrames = np.size(DataCombined.index)
for ind in np.arange(NumFrames):
visualization.PlottingandSaveLabeledFrame(
DataCombined, ind, trainIndices, cfg, colors,
comparisonbodyparts, DLCscorer, foldername)
TF.reset_default_graph()
#print(final_result)
make_results_file(final_result, evaluationfolder, DLCscorer)
print(
"The network is evaluated and the results are stored in the subdirectory 'evaluation_results'."
)
print(
"If it generalizes well, choose the best model for prediction and update the config file with the appropriate index for the 'snapshotindex'.\nUse the function 'analyze_video' to make predictions on new videos."
)
print(
"Otherwise consider retraining the network (see DeepLabCut workflow Fig 2)"
)
#returning to intial folder
os.chdir(str(start_path))
def 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.GetModelFolder(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 create_training_dataset(config,
num_shuffles=1,
Shuffles=None,
windows2linux=False):
"""
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.
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])
--------
"""
from skimage import io
import scipy.io as sio
import deeplabcut
import subprocess
# Loading metadata from config file:
cfg = auxiliaryfunctions.read_config(config)
scorer = cfg['scorer']
project_path = cfg['project_path']
# TODO: fix training set folder!!!
#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,project_path,Path(os.path.join(project_path,trainingsetfolder)),windows2linux)
#Data = Data[scorer] #extract labeled data
#set model type. we will allow more in the future.
if cfg['resnet'] == 50:
net_type = 'resnet_' + str(cfg['resnet'])
resnet_path = str(
Path(deeplabcut.__file__).parents[0] /
'pose_estimation_tensorflow/models/pretrained/resnet_v1_50.ckpt')
elif cfg['resnet'] == 101:
net_type = 'resnet_' + str(cfg['resnet'])
resnet_path = str(
Path(deeplabcut.__file__).parents[0] /
'pose_estimation_tensorflow/models/pretrained/resnet_v1_101.ckpt')
else:
print(
"Currently only ResNet 50 or 101 supported, please change 'resnet' entry in config.yaml!"
)
num_shuffles = -1 #thus the loop below is empty...
if not Path(resnet_path).is_file():
"""
Downloads the ImageNet pretrained weights for ResNet.
"""
start = os.getcwd()
os.chdir(str(Path(resnet_path).parents[0]))
print("Downloading the pretrained model (ResNets)....")
subprocess.call("download.sh", shell=True)
os.chdir(start)
if Shuffles == None:
Shuffles = range(1, num_shuffles + 1, 1)
else:
Shuffles = [i for i in Shuffles if isinstance(i, int)]
#images = []
num_images = 0
data = []
for video in cfg['video_sets']:
imgs_path = os.path.join(project_path, 'pretrain/training-datasets',
Path(video).stem)
images = [img for img in os.listdir(imgs_path) if img.endswith(".png")]
num_images += len(images)
for image in images:
H = {}
im = io.imread(os.path.join(imgs_path, image))
H['image'] = os.path.join('pretrain/training-datasets',
Path(video).stem, image)
if np.ndim(im) == 3:
H['size'] = np.array(
[np.shape(im)[2],
np.shape(im)[0],
np.shape(im)[1]])
else:
# print "Grayscale!"
H['size'] = np.array([1, np.shape(im)[0], np.shape(im)[1]])
data.append(H)
################################################################################
# Saving data file (convert to training file for deeper cut (*.mat))
################################################################################
trainFraction = cfg['TrainingFraction'][0]
data_path = os.path.join(project_path, 'pretrain/training-datasets')
datafilename, metadatafilename = auxiliaryfunctions.GetDataandMetaDataFilenames(
data_path, trainFraction, Shuffles[0], cfg)
trainIndexes, testIndexes = SplitTrials(range(num_images), trainFraction)
auxiliaryfunctions.SaveMetadata(metadatafilename, data, trainIndexes,
testIndexes, trainFraction)
DTYPE = [('image', 'O'), ('size', 'O')]
MatlabData = np.array([(np.array(
[data[item]['image']], dtype='U'), np.array([data[item]['size']]))
for item in range(len(data))],
dtype=DTYPE)
sio.savemat(os.path.join(data_path, datafilename), {'dataset': MatlabData})
modelfoldername = Path('pretrain/dlc-models/trainset')
#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',
'pretrain_pose_cfg.yaml'))
path_test_config = str(
os.path.join(cfg['project_path'], Path(modelfoldername), 'test',
'pretrain_pose_cfg.yaml'))
#str(cfg['proj_path']+'/'+Path(modelfoldername) / 'test' / 'pose_cfg.yaml')
items2change = {
"dataset": datafilename,
"metadataset": metadatafilename,
"init_weights": resnet_path,
"project_path": str(cfg['project_path']),
"net_type": net_type
}
defaultconfigfile = str(
Path(config).parents[0].parents[0] / 'pretrain_pose_cfg.yaml')
trainingdata = MakeTrain_pose_yaml(items2change, path_train_config,
defaultconfigfile)
keys2save = ["dataset", "net_type", 'init_weights', 'global_scale']
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!"
)