import deeplabcut
import os
configpath = os.path.join(
'/home/neudata/Desktop/DeepLabCut/examples/openfield-Pranav-2018-10-30/config.yaml'
)
deeplabcut.load_demo_data(configpath)
deeplabcut.train_network(configpath, maxiters=5) #trains for 5 iterations
#manually test GUI...
deeplabcut.label_frames(configpath)
import os
from pathlib import Path
os.environ["DLClight"] = "True"
import deeplabcut
import numpy as np
# Loading example data set
path_config_file = os.path.join(os.getcwd(),
"openfield-Pranav-2018-10-30/config.yaml")
cfg = deeplabcut.auxiliaryfunctions.read_config(path_config_file)
maxiters = 10000
deeplabcut.load_demo_data(path_config_file)
## Create one split and make Shuffle 2 and 3 have the same split.
###Note that the new function in DLC 2.1 simplifies network/augmentation comparisons greatly:
deeplabcut.create_training_model_comparison(
path_config_file,
num_shuffles=1,
net_types=["resnet_50", "efficientnet-b3"],
augmenter_types=["imgaug", "scalecrop", "tensorpack"],
)
## here is an "old way" to do this
"""
trainIndices, testIndices=deeplabcut.mergeandsplit(path_config_file,trainindex=0,uniform=True)
deeplabcut.create_training_dataset(path_config_file,Shuffles=[2],trainIndices=trainIndices,testIndices=testIndices)
deeplabcut.create_training_dataset(path_config_file,Shuffles=[3],trainIndices=trainIndices,testIndices=testIndices)
import os
os.environ["CUDA_VISIBLE_DEVICES"] = str(0)
import deeplabcut
import numpy as np
# Loading example data set
path_config_file = os.path.join(os.getcwd(), "openfield-Pranav-2018-10-30/config.yaml")
cfg = deeplabcut.auxiliaryfunctions.read_config(path_config_file)
maxiters = 50000
saveiters = 10000
displayiters = 500
deeplabcut.load_demo_data(path_config_file, createtrainingset=False)
## Create one identical splits for 3 networks and 3 augmentations
###Note that the new function in DLC 2.1 simplifies network/augmentation comparisons greatly:
Shuffles = deeplabcut.create_training_model_comparison(
path_config_file,
num_shuffles=1,
net_types=["mobilenet_v2_0.35", "resnet_50", "efficientnet-b3"],
augmenter_types=["imgaug", "scalecrop", "tensorpack"],
)
for idx, shuffle in enumerate(Shuffles):
posefile, _, _ = deeplabcut.return_train_network_path(
path_config_file, shuffle=shuffle
)
