def load_dataset(*, sample_size=600, image_size=224) -> ImageDataBunch:
labels = pd.read_csv(config.PROCESSED_DATA_DIR / 'labels_full.csv')
classes = ['pneumonia', 'normal', 'COVID-19']
ds_types = ['train']
selected = []
for c in classes:
for t in ds_types:
selected.extend(
labels[(labels.label == c)
& (labels.ds_type == t)][:sample_size].values.tolist())
subset = pd.DataFrame(selected, columns=labels.columns)
subset[['name', 'label']].to_csv(config.PROCESSED_DATA_DIR / 'labels.csv',
index=False)
tfms = _get_image_transformation()
# will read from "labels.csv" in the data directory
data = ImageDataBunch.from_csv(config.PROCESSED_DATA_DIR,
ds_tfms=tfms,
csv_labels=config.PROCESSED_DATA_DIR /
'labels.csv',
valid_pct=0.1,
seed=config.SEED,
size=image_size,
bs=21)
data.normalize(imagenet_stats)
return data
import torchvision
from fastai.vision import ImageDataBunch, cnn_learner, unet_learner, SegmentationItemList, imagenet_stats
data = ImageDataBunch.from_csv('fixtures/classification').normalize(
imagenet_stats)
learner = cnn_learner(data, torchvision.models.resnet34)
learner.export()
data = (SegmentationItemList.from_folder(
'fixtures/segmentation/images').split_none().label_from_func(
lambda x: f'fixtures/segmentation/masks/{x.stem}.jpg',
classes=[0, 1, 2]).databunch().normalize(imagenet_stats))
learner = unet_learner(data, torchvision.models.resnet50)
learner.export('../export.pkl')
