import sys
sys.path.insert(0, '..')
from deephyp import autoencoder
from deephyp import data
if __name__ == '__main__':
# download dataset (if already downloaded, comment this out)
#urllib.urlretrieve( 'http://www.ehu.eus/ccwintco/uploads/e/ee/PaviaU.mat', os.path.join(os.getcwd(),'PaviaU.mat'), reporthook )
# read data into numpy array
mat = scipy.io.loadmat('PaviaU.mat')
img = mat['paviaU']
# create a hyperspectral dataset object from the numpy array
hypData = data.HypImg(img)
# pre-process data to make the model easier to train
hypData.pre_process('minmax')
# create data iterator objects for training and validation using the pre-processed data
trainSamples = 200000
valSamples = 100
dataTrain = data.Iterator(
dataSamples=hypData.spectraPrep[:trainSamples, :],
targets=hypData.spectraPrep[:trainSamples, :],
batchSize=1000)
dataVal = data.Iterator(
dataSamples=hypData.spectraPrep[trainSamples:trainSamples +
valSamples, :],
targets=hypData.spectraPrep[trainSamples:trainSamples + valSamples, :])
# download dataset and ground truth (if already downloaded, comment this out)
urlretrieve('http://www.ehu.eus/ccwintco/uploads/e/ee/PaviaU.mat',
os.path.join(os.getcwd(), 'PaviaU.mat'), reporthook)
urlretrieve('http://www.ehu.eus/ccwintco/uploads/5/50/PaviaU_gt.mat',
os.path.join(os.getcwd(), 'PaviaU_gt.mat'), reporthook)
# read data into numpy array
mat = scipy.io.loadmat('PaviaU.mat')
img = mat['paviaU']
# read labels into numpy array
mat_gt = scipy.io.loadmat('PaviaU_gt.mat')
img_gt = mat_gt['paviaU_gt']
# create a hyperspectral dataset object from the numpy array
hypData = data.HypImg(img, labels=img_gt)
# pre-process data to make the model easier to train
hypData.pre_process('minmax')
# get indices for training and validation data
trainSamples = 50 # per class
valSamples = 15 # per class
train_indices = []
for i in range(1, 10):
train_indices += np.nonzero(
hypData.labels == i)[0][:trainSamples].tolist()
val_indices = []
for i in range(1, 10):
val_indices += np.nonzero(
hypData.labels == i)[0][trainSamples:trainSamples +
