57  Hyperparameter Tuning with spotpython and PyTorch Lightning Using a CondNet Model

• We use the Diabetes dataset to illustrate the hyperparameter tuning process of a CondNet model using the spotpython package.
• The CondNet model is a conditional neural network that can be used to model conditional distributions [LINK].

from spotpython.data.diabetes import Diabetes
from spotpython.hyperdict.light_hyper_dict import LightHyperDict
from spotpython.fun.hyperlight import HyperLight
from spotpython.utils.init import (fun_control_init, surrogate_control_init, design_control_init)
from spotpython.utils.eda import print_exp_table
from spotpython.spot import Spot
from spotpython.utils.file import get_experiment_filename
from math import inf
from spotpython.hyperparameters.values import set_hyperparameter

PREFIX="CondNet_01"

data_set = Diabetes()
input_dim = 10
output_dim = 1
cond_dim = 2

fun_control = fun_control_init(
    PREFIX=PREFIX,
    fun_evals=inf,
    max_time=1,
    data_set = data_set,
    core_model_name="light.regression.NNCondNetRegressor",
    hyperdict=LightHyperDict,
    _L_in=input_dim - cond_dim,
    _L_out=1,
    _L_cond=cond_dim,)

fun = HyperLight().fun


set_hyperparameter(fun_control, "optimizer", [ "Adadelta", "Adam", "Adamax"])
set_hyperparameter(fun_control, "l1", [3,4])
set_hyperparameter(fun_control, "epochs", [3,7])
set_hyperparameter(fun_control, "batch_size", [4,5])
set_hyperparameter(fun_control, "dropout_prob", [0.0, 0.025])
set_hyperparameter(fun_control, "patience", [2,3])
set_hyperparameter(fun_control, "lr_mult", [0.1, 20.0])

design_control = design_control_init(init_size=10)

print_exp_table(fun_control)

module_name: light
submodule_name: regression
model_name: NNCondNetRegressor
| name           | type   | default   |   lower |   upper | transform             |
|----------------|--------|-----------|---------|---------|-----------------------|
| l1             | int    | 3         |     3   |   4     | transform_power_2_int |
| epochs         | int    | 4         |     3   |   7     | transform_power_2_int |
| batch_size     | int    | 4         |     4   |   5     | transform_power_2_int |
| act_fn         | factor | ReLU      |     0   |   5     | None                  |
| optimizer      | factor | SGD       |     0   |   2     | None                  |
| dropout_prob   | float  | 0.01      |     0   |   0.025 | None                  |
| lr_mult        | float  | 1.0       |     0.1 |  20     | None                  |
| patience       | int    | 2         |     2   |   3     | transform_power_2_int |
| batch_norm     | factor | 0         |     0   |   1     | None                  |
| initialization | factor | Default   |     0   |   4     | None                  |

spot_tuner = Spot(fun=fun,fun_control=fun_control, design_control=design_control)
res = spot_tuner.run()

train_model result: {'val_loss': 24159.23828125, 'hp_metric': 24159.23828125}

train_model result: {'val_loss': 23455.20703125, 'hp_metric': 23455.20703125}

train_model result: {'val_loss': 43761.7265625, 'hp_metric': 43761.7265625}

train_model result: {'val_loss': 24069.580078125, 'hp_metric': 24069.580078125}

train_model result: {'val_loss': 22378.6015625, 'hp_metric': 22378.6015625}

train_model result: {'val_loss': 23910.111328125, 'hp_metric': 23910.111328125}

train_model result: {'val_loss': 23796.3828125, 'hp_metric': 23796.3828125}

train_model result: {'val_loss': 3585.37548828125, 'hp_metric': 3585.37548828125}

train_model result: {'val_loss': 22366.2421875, 'hp_metric': 22366.2421875}
train_model result: {'val_loss': 22662.296875, 'hp_metric': 22662.296875}

train_model result: {'val_loss': 4858.8212890625, 'hp_metric': 4858.8212890625}
spotpython tuning: 3585.37548828125 [#---------] 7.34% 

train_model result: {'val_loss': 2978.2021484375, 'hp_metric': 2978.2021484375}
spotpython tuning: 2978.2021484375 [#---------] 11.90% 

train_model result: {'val_loss': 3981.192626953125, 'hp_metric': 3981.192626953125}
spotpython tuning: 2978.2021484375 [#---------] 14.81% 

train_model result: {'val_loss': 2909.39208984375, 'hp_metric': 2909.39208984375}
spotpython tuning: 2909.39208984375 [##--------] 19.10% 

train_model result: {'val_loss': 5174.12109375, 'hp_metric': 5174.12109375}
spotpython tuning: 2909.39208984375 [##--------] 22.47% 

train_model result: {'val_loss': 22454.35546875, 'hp_metric': 22454.35546875}
spotpython tuning: 2909.39208984375 [###-------] 31.92% 

train_model result: {'val_loss': 3955.571044921875, 'hp_metric': 3955.571044921875}
spotpython tuning: 2909.39208984375 [####------] 36.37% 

train_model result: {'val_loss': 16310.7568359375, 'hp_metric': 16310.7568359375}
spotpython tuning: 2909.39208984375 [######----] 62.05% 

train_model result: {'val_loss': 4214.85009765625, 'hp_metric': 4214.85009765625}
spotpython tuning: 2909.39208984375 [#######---] 66.75% 

train_model result: {'val_loss': 4863.47119140625, 'hp_metric': 4863.47119140625}
spotpython tuning: 2909.39208984375 [#######---] 71.48% 

train_model result: {'val_loss': 4874.6474609375, 'hp_metric': 4874.6474609375}
spotpython tuning: 2909.39208984375 [########--] 76.25% 

train_model result: {'val_loss': 3189.736083984375, 'hp_metric': 3189.736083984375}
spotpython tuning: 2909.39208984375 [########--] 84.34% 

train_model result: {'val_loss': 4701.22802734375, 'hp_metric': 4701.22802734375}
spotpython tuning: 2909.39208984375 [#########-] 90.56% 

train_model result: {'val_loss': 3343.5302734375, 'hp_metric': 3343.5302734375}
spotpython tuning: 2909.39208984375 [##########] 97.07% 

train_model result: {'val_loss': 6690.5732421875, 'hp_metric': 6690.5732421875}
spotpython tuning: 2909.39208984375 [##########] 100.00% Done...

Experiment saved to CondNet_01_res.pkl

57.1 Looking at the Results

57.1.1 Tuning Progress

After the hyperparameter tuning run is finished, the progress of the hyperparameter tuning can be visualized with spotpython’s method plot_progress. The black points represent the performace values (score or metric) of hyperparameter configurations from the initial design, whereas the red points represents the hyperparameter configurations found by the surrogate model based optimization.

spot_tuner.plot_progress()

57.1.2 Tuned Hyperparameters and Their Importance

Results can be printed in tabular form.

from spotpython.utils.eda import print_res_table
print_res_table(spot_tuner)

| name           | type   | default   |   lower |   upper | tuned              | transform             |   importance | stars   |
|----------------|--------|-----------|---------|---------|--------------------|-----------------------|--------------|---------|
| l1             | int    | 3         |     3.0 |     4.0 | 3.0                | transform_power_2_int |         0.00 |         |
| epochs         | int    | 4         |     3.0 |     7.0 | 7.0                | transform_power_2_int |         0.00 |         |
| batch_size     | int    | 4         |     4.0 |     5.0 | 4.0                | transform_power_2_int |         0.00 |         |
| act_fn         | factor | ReLU      |     0.0 |     5.0 | Swish              | None                  |         0.00 |         |
| optimizer      | factor | SGD       |     0.0 |     2.0 | Adadelta           | None                  |       100.00 | ***     |
| dropout_prob   | float  | 0.01      |     0.0 |   0.025 | 0.0                | None                  |         0.00 |         |
| lr_mult        | float  | 1.0       |     0.1 |    20.0 | 10.272087717464348 | None                  |         0.00 |         |
| patience       | int    | 2         |     2.0 |     3.0 | 2.0                | transform_power_2_int |         0.00 |         |
| batch_norm     | factor | 0         |     0.0 |     1.0 | 1                  | None                  |         0.00 |         |
| initialization | factor | Default   |     0.0 |     4.0 | kaiming_uniform    | None                  |        25.44 | *       |

A histogram can be used to visualize the most important hyperparameters.

spot_tuner.plot_importance(threshold=1.0)

spot_tuner.plot_important_hyperparameter_contour(max_imp=3)

l1:  0.0013410962465474079
epochs:  0.0013410962465474079
batch_size:  0.0013410962465474079
act_fn:  0.0013410962465474079
optimizer:  100.0
dropout_prob:  0.0013410962465474079
lr_mult:  0.0013410962465474079
patience:  0.0013410962465474079
batch_norm:  0.0013410962465474079
initialization:  25.4376252100281

57.1.3 Get the Tuned Architecture

import pprint
from spotpython.hyperparameters.values import get_tuned_architecture
config = get_tuned_architecture(spot_tuner)
pprint.pprint(config)

{'act_fn': Swish(),
 'batch_norm': True,
 'batch_size': 16,
 'dropout_prob': 0.0,
 'epochs': 128,
 'initialization': 'kaiming_uniform',
 'l1': 8,
 'lr_mult': 10.272087717464348,
 'optimizer': 'Adadelta',
 'patience': 4}