def test_from_filepaths_visualise_multilabel(tmpdir):
tmpdir = Path(tmpdir)
(tmpdir / "a").mkdir()
(tmpdir / "b").mkdir()
image_a = str(tmpdir / "a" / "a_1.png")
image_b = str(tmpdir / "b" / "b_1.png")
_rand_image().save(image_a)
_rand_image().save(image_b)
dm = AudioClassificationData.from_files(
train_files=[image_a, image_b],
train_targets=[[0, 1, 0], [0, 1, 1]],
val_files=[image_b, image_a],
val_targets=[[1, 1, 0], [0, 0, 1]],
test_files=[image_b, image_b],
test_targets=[[0, 0, 1], [1, 1, 0]],
batch_size=2,
transform_kwargs=dict(spectrogram_size=(64, 64)),
)
# disable visualisation for testing
assert dm.data_fetcher.block_viz_window is True
dm.set_block_viz_window(False)
assert dm.data_fetcher.block_viz_window is False
# call show functions
dm.show_train_batch()
dm.show_train_batch("per_sample_transform")
dm.show_val_batch("per_batch_transform")
def test_from_filepaths_visualise(tmpdir):
tmpdir = Path(tmpdir)
_rand_image().save(tmpdir / "e_1.png")
train_images = [
str(tmpdir / "e_1.png"),
str(tmpdir / "e_1.png"),
str(tmpdir / "e_1.png"),
]
dm = AudioClassificationData.from_files(
train_files=train_images,
train_targets=[0, 3, 6],
val_files=train_images,
val_targets=[1, 4, 7],
test_files=train_images,
test_targets=[2, 5, 8],
batch_size=2,
num_workers=0,
)
# disable visualisation for testing
assert dm.data_fetcher.block_viz_window is True
dm.set_block_viz_window(False)
assert dm.data_fetcher.block_viz_window is False
# call show functions
# dm.show_train_batch()
dm.show_train_batch("per_sample_transform")
dm.show_train_batch(["per_sample_transform", "per_batch_transform"])
def test_from_filepaths_smoke(tmpdir):
tmpdir = Path(tmpdir)
_rand_image().save(tmpdir / "a_1.png")
_rand_image().save(tmpdir / "b_1.png")
train_images = [
str(tmpdir / "a_1.png"),
str(tmpdir / "b_1.png"),
]
spectrograms_data = AudioClassificationData.from_files(
train_files=train_images,
train_targets=[1, 2],
batch_size=2,
num_workers=0,
)
assert spectrograms_data.train_dataloader() is not None
assert spectrograms_data.val_dataloader() is None
assert spectrograms_data.test_dataloader() is None
data = next(iter(spectrograms_data.train_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, )
assert sorted(list(labels.numpy())) == [1, 2]
def run(transform: Any = None):
dm = AudioClassificationData.from_files(
train_files=train_filepaths,
train_targets=train_labels,
transform=transform,
batch_size=B,
num_workers=0,
val_split=val_split,
)
data = next(iter(dm.train_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (B, 3, H, W)
assert labels.shape == (B, )
def test_from_filepaths(tmpdir, file_generator):
train_images, channels = file_generator(tmpdir)
spectrograms_data = AudioClassificationData.from_files(
train_files=train_images,
train_targets=[1, 2],
batch_size=2,
num_workers=0,
)
assert spectrograms_data.train_dataloader() is not None
data = next(iter(spectrograms_data.train_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, channels, 128, 128)
assert labels.shape == (2, )
assert sorted(list(labels.numpy())) == [1, 2]
def test_from_filepaths_list_image_paths(tmpdir):
tmpdir = Path(tmpdir)
_rand_image().save(tmpdir / "e_1.png")
train_images = [
str(tmpdir / "e_1.png"),
str(tmpdir / "e_1.png"),
str(tmpdir / "e_1.png"),
]
spectrograms_data = AudioClassificationData.from_files(
train_files=train_images,
train_targets=[0, 3, 6],
val_files=train_images,
val_targets=[1, 4, 7],
test_files=train_images,
test_targets=[2, 5, 8],
batch_size=2,
num_workers=0,
)
# check training data
data = next(iter(spectrograms_data.train_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, )
assert labels.numpy()[0] in [0, 3, 6] # data comes shuffled here
assert labels.numpy()[1] in [0, 3, 6] # data comes shuffled here
# check validation data
data = next(iter(spectrograms_data.val_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, )
assert list(labels.numpy()) == [1, 4]
# check test data
data = next(iter(spectrograms_data.test_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, )
assert list(labels.numpy()) == [2, 5]
def test_from_filepaths_multilabel(tmpdir):
tmpdir = Path(tmpdir)
(tmpdir / "a").mkdir()
_rand_image().save(tmpdir / "a1.png")
_rand_image().save(tmpdir / "a2.png")
train_images = [str(tmpdir / "a1.png"), str(tmpdir / "a2.png")]
train_labels = [[1, 0, 1, 0], [0, 0, 1, 1]]
valid_labels = [[1, 1, 1, 0], [1, 0, 0, 1]]
test_labels = [[1, 0, 1, 0], [1, 1, 0, 1]]
dm = AudioClassificationData.from_files(
train_files=train_images,
train_targets=train_labels,
val_files=train_images,
val_targets=valid_labels,
test_files=train_images,
test_targets=test_labels,
batch_size=2,
num_workers=0,
)
data = next(iter(dm.train_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, 4)
data = next(iter(dm.val_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, 4)
torch.testing.assert_allclose(labels, torch.tensor(valid_labels))
data = next(iter(dm.test_dataloader()))
imgs, labels = data["input"], data["target"]
assert imgs.shape == (2, 3, 128, 128)
assert labels.shape == (2, 4)
torch.testing.assert_allclose(labels, torch.tensor(test_labels))
"./data")
datamodule = AudioClassificationData.from_folders(
train_folder="data/urban8k_images/train",
val_folder="data/urban8k_images/val",
transform_kwargs=dict(spectrogram_size=(64, 64)),
batch_size=4,
)
# 2. Build the model.
model = ImageClassifier(backbone="resnet18", labels=datamodule.labels)
# 3. Create the trainer and finetune the model
trainer = flash.Trainer(max_epochs=3, gpus=torch.cuda.device_count())
trainer.finetune(model, datamodule=datamodule, strategy=("freeze_unfreeze", 1))
# 4. Predict what's on few images! air_conditioner, children_playing, siren etc.
datamodule = AudioClassificationData.from_files(
predict_files=[
"data/urban8k_images/test/air_conditioner/13230-0-0-5.wav.jpg",
"data/urban8k_images/test/children_playing/9223-2-0-15.wav.jpg",
"data/urban8k_images/test/jackhammer/22883-7-10-0.wav.jpg",
],
batch_size=3,
)
predictions = trainer.predict(model, datamodule=datamodule, output="labels")
print(predictions)
# 5. Save the model!
trainer.save_checkpoint("audio_classification_model.pt")