MCPcopy Index your code
hub / github.com/DeepLabCut/DeepLabCut / train_network

Function train_network

deeplabcut/pose_estimation_tensorflow/training.py:48–277  ·  view source on GitHub ↗

Trains the network with the labels in the training dataset. Parameters ---------- config : string Full path of the config.yaml file as a string. shuffle: int, optional, default=1 Integer value specifying the shuffle index to select for traini

(
    config,
    shuffle=1,
    trainingsetindex=0,
    max_snapshots_to_keep=5,
    displayiters=None,
    saveiters=None,
    maxiters=None,
    allow_growth=True,
    gputouse=None,
    autotune=False,
    keepdeconvweights=True,
    modelprefix="",
    superanimal_name="",
    superanimal_transfer_learning=False,
)

Source from the content-addressed store, hash-verified

46
47
48def train_network(
49 config,
50 shuffle=1,
51 trainingsetindex=0,
52 max_snapshots_to_keep=5,
53 displayiters=None,
54 saveiters=None,
55 maxiters=None,
56 allow_growth=True,
57 gputouse=None,
58 autotune=False,
59 keepdeconvweights=True,
60 modelprefix="",
61 superanimal_name="",
62 superanimal_transfer_learning=False,
63):
64 """Trains the network with the labels in the training dataset.
65
66 Parameters
67 ----------
68 config : string
69 Full path of the config.yaml file as a string.
70
71 shuffle: int, optional, default=1
72 Integer value specifying the shuffle index to select for training.
73
74 trainingsetindex: int, optional, default=0
75 Integer specifying which TrainingsetFraction to use.
76 Note that TrainingFraction is a list in config.yaml.
77
78 max_snapshots_to_keep: int or None
79 Sets how many snapshots are kept, i.e. states of the trained network. Every
80 saving iteration many times a snapshot is stored, however only the last
81 ``max_snapshots_to_keep`` many are kept! If you change this to None, then all
82 are kept.
83 See: https://github.com/DeepLabCut/DeepLabCut/issues/8#issuecomment-387404835
84
85 displayiters: optional, default=None
86 This variable is actually set in ``pose_config.yaml``. However, you can
87 overwrite it with this hack. Don't use this regularly, just if you are too lazy
88 to dig out the ``pose_config.yaml`` file for the corresponding project. If
89 ``None``, the value from there is used, otherwise it is overwritten!
90
91 saveiters: optional, default=None
92 This variable is actually set in ``pose_config.yaml``. However, you can
93 overwrite it with this hack. Don't use this regularly, just if you are too lazy
94 to dig out the ``pose_config.yaml`` file for the corresponding project.
95 If ``None``, the value from there is used, otherwise it is overwritten!
96
97 maxiters: optional, default=None
98 This variable is actually set in ``pose_config.yaml``. However, you can
99 overwrite it with this hack. Don't use this regularly, just if you are too lazy
100 to dig out the ``pose_config.yaml`` file for the corresponding project.
101 If ``None``, the value from there is used, otherwise it is overwritten!
102
103 allow_growth: bool, optional, default=True.
104 For some smaller GPUs the memory issues happen. If ``True``, the memory
105 allocator does not pre-allocate the entire specified GPU memory region, instead

Callers

nothing calls this directly

Calls 2

trainFunction · 0.90
read_configMethod · 0.45

Tested by

no test coverage detected