PiecewiseLinear#

class ignite.handlers.param_scheduler.PiecewiseLinear(optimizer, param_name, milestones_values, save_history=False, param_group_index=None)[source]#

Piecewise linear parameter scheduler

Parameters

optimizer (Optimizer) – torch optimizer or any object with attribute param_groups as a sequence.
param_name (str) – name of optimizer’s parameter to update.
milestones_values (List[Tuple[int, float]]) – list of tuples (event index, parameter value) represents milestones and parameter. Milestones should be increasing integers.
save_history (bool) – whether to log the parameter values to engine.state.param_history, (default=False).
param_group_index (Optional[int]) – optimizer’s parameters group to use.

scheduler = PiecewiseLinear(optimizer, "lr",
                            milestones_values=[(10, 0.5), (20, 0.45), (21, 0.3), (30, 0.1), (40, 0.1)])
# Attach to the trainer
trainer.add_event_handler(Events.ITERATION_STARTED, scheduler)
#
# Sets the learning rate to 0.5 over the first 10 iterations, then decreases linearly from 0.5 to 0.45 between
# 10th and 20th iterations. Next there is a jump to 0.3 at the 21st iteration and LR decreases linearly
# from 0.3 to 0.1 between 21st and 30th iterations and remains 0.1 until the end of the iterations.

Examples

from collections import OrderedDict

import torch
from torch import nn, optim

from ignite.engine import *
from ignite.handlers import *
from ignite.metrics import *
from ignite.metrics.regression import *
from ignite.utils import *

# create default evaluator for doctests

def eval_step(engine, batch):
    return batch

default_evaluator = Engine(eval_step)

# create default optimizer for doctests

param_tensor = torch.zeros([1], requires_grad=True)
default_optimizer = torch.optim.SGD([param_tensor], lr=0.1)

# create default trainer for doctests
# as handlers could be attached to the trainer,
# each test must define his own trainer using `.. testsetup:`

def get_default_trainer():

    def train_step(engine, batch):
        return batch

    return Engine(train_step)

# create default model for doctests

default_model = nn.Sequential(OrderedDict([
    ('base', nn.Linear(4, 2)),
    ('fc', nn.Linear(2, 1))
]))

manual_seed(666)

default_trainer = get_default_trainer()

milestones_values = [(1, 1.0), (3, 0.8), (5, 0.2)]
scheduler = PiecewiseLinear(
    default_optimizer, "lr", milestones_values=milestones_values)
# Sets lr equal to 1 for till the first iteration
# Then linearly reduces lr from 1 to 0.8 till the third iteration
# Then linearly reduces lr from 0.8 to 0.5 till the fifth iteration

default_trainer.add_event_handler(Events.ITERATION_STARTED, scheduler)

@default_trainer.on(Events.ITERATION_COMPLETED)
def print_lr():
    print(default_optimizer.param_groups[0]["lr"])

default_trainer.run([0] * 6, max_epochs=1)

default_trainer = get_default_trainer()

optimizer = torch.optim.SGD(
    [
        {"params": default_model.base.parameters(), "lr": 0.1},
        {"params": default_model.fc.parameters(), "lr": 1.0},
    ]
)

milestones_values1 = [(1, 0.1), (3, 0.08), (5, 0.02)]
scheduler2 = PiecewiseLinear(
    optimizer, "lr", milestones_values=milestones_values1, param_group_index=0)
# Sets lr equal to 0.1 for till the first iteration
# Then linearly reduces lr from 0.1 to 0.08 till the third iteration
# Then linearly reduces lr from 0.08 to 0.05 till the fifth iteration

milestones_values2 = [(1, 1.0), (3, 0.8), (5, 0.2)]
scheduler1 = PiecewiseLinear(
    optimizer, "lr", milestones_values=milestones_values2, param_group_index=1)
# Sets lr equal to 1 for till the first iteration
# Then linearly reduces lr from 1 to 0.8 till the third iteration
# Then linearly reduces lr from 0.8 to 0.5 till the fifth iteration

default_trainer.add_event_handler(Events.ITERATION_STARTED, scheduler1)
default_trainer.add_event_handler(Events.ITERATION_STARTED, scheduler2)

@default_trainer.on(Events.ITERATION_COMPLETED)
def print_lr():
    print(optimizer.param_groups[0]["lr"],
          optimizer.param_groups[1]["lr"])

default_trainer.run([0] * 6, max_epochs=1)

New in version 0.4.5.

Methods

get_param

Method to get current parameter values

get_param()[source]#

Method to get current parameter values

Returns: list of params, or scalar param
Return type: float