def __init__(self,
labels,
dataset,
ids,
rasters,
patches,
use_rasters=True):
"""
:param labels: list of labels
:param dataset: list of (latitude, longitude)
:param ids: list of identifiers
:param rasters: path to the rasters root
:param patches: path to the patches root
"""
self.labels = labels
self.dataset = dataset
self.ids = ids
self.one_hot_size = 34
self.one_hot = np.eye(self.one_hot_size)
self.rasters = rasters
self.patches = patches
global patch_extractor
if patch_extractor is None and rasters is not None and use_rasters:
# 256 is mandatory as images have been extracted in 256 and will be stacked in the __getitem__ method
patch_extractor = PatchExtractor(rasters, size=256, verbose=True)
patch_extractor.add_all()
self.extractor = patch_extractor
return len(self.labels)
def __getitem__(self, idx):
tensor = self.extractor[self.dataset[idx]]
return torch.from_numpy(tensor).float(), self.labels[idx]
if __name__ == '__main__':
patch_extractor = PatchExtractor(
'/Users/ykarmim/Documents/Cours/Master/Projet_DAC/geoLifeClef/data/rasters_GLC19',
size=64,
verbose=True)
#patch_extractor.append('proxi_eau_fast')
#patch_extractor.append('text')
patch_extractor.add_all()
# example of dataset
dataset_list = [(43.61, 3.88), (42.61, 4.88), (46.15, -1.1), (49.54, -1.7)]
labels_list = [0, 1, 0, 1]
dataset_pytorch = GeoLifeClefDataset(patch_extractor, dataset_list,
labels_list)
print(len(dataset_pytorch), 'elements in the dataset')
# dataset_pytorch can now be used in a data_loader
data_loader = torch.utils.data.DataLoader(dataset_pytorch,
shuffle=True,
batch_size=2)
from environmental_raster_glc import PatchExtractor
extractor = PatchExtractor(
'/Users/ykarmim/Documents/Cours/Master/Projet_DAC/geoLifeClef/data/rasters_GLC19',
size=64,
verbose=True)
#extractor.append('proxi_eau_fast')
# extractor.append('text')
# extractor.append('clc')
# extractor.append('bs_top')
# extractor.append('oc_top')
extractor.add_all()
extractor.plot((43.61, 3.88))