def imagenette_loader(path):
''' Load Imagenette-320 version 2 dataset to path '''
try:
from fastai.vision.all import untar_data, URLs
except ImportError:
print('FastAI do not found')
print('Please install Fast AI')
print(
'Command for installation: "conda install -c fastai -c pytorch fastai"'
)
untar_data(URLs.IMAGENETTE_320, dest=path)
def main():
# Parse command-line arguments
args = parse_args()
# Split data between training and testing
splitter = GrandparentSplitter(train_name="training", valid_name="testing")
# Prepare DataBlock which is a generic container to quickly build Datasets and DataLoaders
mnist = DataBlock(
blocks=(ImageBlock(PILImage), CategoryBlock),
get_items=get_image_files,
splitter=splitter,
get_y=parent_label,
)
# Download, untar the MNIST data set and create DataLoader from DataBlock
data = mnist.dataloaders(untar_data(URLs.MNIST), bs=256, num_workers=0)
# Enable auto logging
mlflow.fastai.autolog()
# Create Learner model
learn = cnn_learner(data, resnet18)
# Start MLflow session
with mlflow.start_run():
# Train and fit with default or supplied command line arguments
learn.fit_one_cycle(args.epochs, args.lr)
def main(epochs):
Task.init(project_name="examples", task_name="fastai v2")
path = untar_data(URLs.PETS)
files = get_image_files(path / "images")
dls = ImageDataLoaders.from_name_func(path,
files,
label_func,
item_tfms=Resize(224),
num_workers=0)
dls.show_batch()
learn = cnn_learner(dls, resnet34, metrics=error_rate)
learn.fine_tune(epochs)
learn.show_results()
def create_dataloaders() -> DataLoaders:
"""
Create the dataloaders for the cats vs. dogs dataset.
"""
path = untar_data(URLs.PETS) / "images"
dls = ImageDataLoaders.from_name_func(
path,
get_image_files(path),
valid_pct=0.2,
batch_size=8,
seed=42,
label_func=is_cat,
item_tfms=Resize(224),
)
return dls
from fastai.vision.all import Learner
from fastai.vision.all import SimpleCNN
from fastai.vision.all import untar_data
from fastai.vision.all import URLs
# TODO(crcrpar): Remove the below three lines once fastai gets compatible with torchvision v0.9.
# Register a global custom opener to avoid HTTP Error 403: Forbidden when downloading MNIST.
# This is a temporary fix until torchvision v0.9 is released.
opener = urllib.request.build_opener()
opener.addheaders = [("User-agent", "Mozilla/5.0")]
urllib.request.install_opener(opener)
BATCHSIZE = 128
EPOCHS = 10
path = untar_data(URLs.MNIST_SAMPLE)
def objective(trial):
# Data Augmentation
apply_tfms = trial.suggest_categorical("apply_tfms", [True, False])
if apply_tfms:
# MNIST is a hand-written digit dataset. Thus horizontal and vertical flipping are
# disabled. However, the two flipping will be important when the dataset is CIFAR or
# ImageNet.
tfms = aug_transforms(
do_flip=False,
flip_vert=False,
max_rotate=trial.suggest_int("max_rotate", 0, 45),
max_zoom=trial.suggest_float("max_zoom", 1, 2),
p_affine=trial.suggest_float("p_affine", 0.1, 1.0, step=0.1),
# https://www.fast.ai/
# https://course.fast.ai/
# https://github.com/fastai/fastbook
# https://github.com/fastai/fastbook/blob/master/01_intro.ipynb
import fastai.vision.all as fa
path = fa.untar_data(fa.URLs.PETS)/"images"
def is_cat(x):
return x[0].isupper()
# https://github.com/fastai/fastbook/blob/master/01_intro.ipynb
# continue from this page
# fa.ImageDataLoaders.from_name_func(
# path, fa.get_image_files?
# )
from fastai.vision.all import untar_data, URLs, ImageDataLoaders, get_image_files, Resize, error_rate, resnet34, \
cnn_learner
from labml import lab, experiment
from labml.utils.fastai import LabMLFastAICallback
path = untar_data(
URLs.PETS,
dest=lab.get_data_path(),
fname=lab.get_data_path() / URLs.path(URLs.PETS).name) / 'images'
def is_cat(x):
return x[0].isupper()
dls = ImageDataLoaders.from_name_func(path,
get_image_files(path),
valid_pct=0.2,
seed=42,
label_func=is_cat,
item_tfms=Resize(224))
# Train the model ⚡
learn = cnn_learner(dls,
resnet34,
metrics=error_rate,
cbs=LabMLFastAICallback())
with experiment.record(name='pets', exp_conf=learn.labml_configs()):
learn.fine_tune(5)
ch_in = [3, 6, 12, 24]
convs = [ConvLayer(c, c * 2, stride=2) for c in ch_in]
convs += [AdaptiveAvgPool(), Flatten(), nn.Linear(48, emb_size)]
self.convs = nn.Sequential(*convs)
self.classifier = classifier
def get_embs(self, x):
return self.convs(x)
def forward(self, x):
x = self.get_embs(x)
x = self.classifier(x)
return x
dls = ImageDataLoaders.from_folder(untar_data(URLs.MNIST),
train="training",
valid="testing",
num_workers=0)
learn = Learner(dls,
SimpleConv(ArcFaceClassifier(3, 10)),
metrics=accuracy,
loss_func=arcface_loss)
# %%
learn.fit_one_cycle(5, 5e-3)
# %%
def get_embs(model, dl):