Skip to content

[1859] fix lr finder #1865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rijobro merged 4 commits into from
Mar 26, 2021
Merged

[1859] fix lr finder #1865

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ba18485
fix lr finder
rijobro Mar 26, 2021
c011c75
pil not needed directly
rijobro Mar 26, 2021
b32f835
Merge branch 'master' into 1859_lr_finder
rijobro Mar 26, 2021
0f6d50b
Merge branch 'master' into 1859_lr_finder
wyli Mar 26, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions tests/test_lr_finder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
import random
import sys
import unittest
from typing import TYPE_CHECKING

import torch
from torch.utils.data import DataLoader
Expand All @@ -23,7 +24,14 @@
from monai.transforms import AddChanneld, Compose, LoadImaged, ScaleIntensityd, ToTensord
from monai.utils import optional_import, set_determinism

PILImage, has_pil = optional_import("PIL.Image")
if TYPE_CHECKING:
import matplotlib.pyplot as plt

has_matplotlib = True
has_pil = True
else:
plt, has_matplotlib = optional_import("matplotlib.pyplot")
_, has_pil = optional_import("PIL.Image")

RAND_SEED = 42
random.seed(RAND_SEED)
Expand Down Expand Up @@ -73,7 +81,14 @@ def test_lr_finder(self):
lr_finder = LearningRateFinder(model, optimizer, loss_function, device=device)
lr_finder.range_test(train_loader, val_loader=train_loader, end_lr=10, num_iter=5)
print(lr_finder.get_steepest_gradient(0, 0)[0])
lr_finder.plot(0, 0) # to inspect the loss-learning rate graph

if has_matplotlib:
ax = plt.subplot()
plt.show(block=False)
lr_finder.plot(0, 0, ax=ax) # to inspect the loss-learning rate graph
plt.pause(3)
plt.close()

lr_finder.reset() # to reset the model and optimizer to their initial state


Expand Down