def test_calc_semantic_segmentation_iou(self):
c = np.random.randint(0, 100, size=(self.n_class, self.n_class))
expected = np.array(
[c[0, 0] / (c[0, 0] + c[0, 1] + c[1, 0]),
c[1, 1] / (c[1, 1] + c[1, 0] + c[0, 1])])
iou = calc_semantic_segmentation_iou(c)
np.testing.assert_equal(iou, expected)
def test_calc_semantic_segmentation_iou(self):
c = np.random.randint(0, 100, size=(self.n_class, self.n_class))
expected = np.array(
[c[0, 0] / (c[0, 0] + c[0, 1] + c[1, 0]),
c[1, 1] / (c[1, 1] + c[1, 0] + c[0, 1])])
iou = calc_semantic_segmentation_iou(c)
np.testing.assert_equal(iou, expected)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--dataset',
choices=('cityscapes', 'ade20k', 'camvid'))
parser.add_argument('--model', choices=('pspnet_resnet101', 'segnet'))
parser.add_argument('--pretrained-model')
parser.add_argument('--input-size', type=int, default=None)
args = parser.parse_args()
comm = chainermn.create_communicator()
device = comm.intra_rank
dataset, label_names, model = get_dataset_and_model(
args.dataset, args.model, args.pretrained_model,
(args.input_size, args.input_size))
assert len(dataset) % comm.size == 0, \
"The size of the dataset should be a multiple "\
"of the number of GPUs"
chainer.cuda.get_device_from_id(device).use()
model.to_gpu()
if comm.rank == 0:
indices = np.arange(len(dataset))
else:
indices = None
indices = chainermn.scatter_dataset(indices, comm)
dataset = dataset.slice[indices]
it = iterators.SerialIterator(dataset, 1, repeat=False, shuffle=False)
in_values, out_values, rest_values = apply_to_iterator(model.predict,
it,
hook=ProgressHook(
len(dataset)))
# Delete an iterator of images to save memory usage.
del in_values
pred_labels, = out_values
gt_labels, = rest_values
confusion = calc_semantic_segmentation_confusion(pred_labels, gt_labels)
confusion = comm.allreduce(confusion)
if comm.rank == 0:
iou = calc_semantic_segmentation_iou(confusion)
pixel_accuracy = np.diag(confusion).sum() / confusion.sum()
class_accuracy = np.diag(confusion) / np.sum(confusion, axis=1)
for iu, label_name in zip(iou, label_names):
print('{:>23} : {:.4f}'.format(label_name, iu))
print('=' * 34)
print('{:>23} : {:.4f}'.format('mean IoU', np.nanmean(iou)))
print('{:>23} : {:.4f}'.format('Class average accuracy',
np.nanmean(class_accuracy)))
print('{:>23} : {:.4f}'.format('Global average accuracy',
pixel_accuracy))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained_model', type=str, default='camvid')
parser.add_argument('--batchsize', type=int, default=24)
args = parser.parse_args()
model = SegNetBasic(n_class=len(camvid_label_names),
pretrained_model=args.pretrained_model)
if args.gpu >= 0:
model.to_gpu(args.gpu)
model = calc_bn_statistics(model, args.batchsize)
chainer.config.train = False
test = CamVidDataset(split='test')
it = chainer.iterators.SerialIterator(test,
batch_size=args.batchsize,
repeat=False,
shuffle=False)
imgs, pred_values, gt_values = apply_prediction_to_iterator(
model.predict, it)
# Delete an iterator of images to save memory usage.
del imgs
pred_labels, = pred_values
gt_labels, = gt_values
confusion = calc_semantic_segmentation_confusion(pred_labels, gt_labels)
ious = calc_semantic_segmentation_iou(confusion)
pixel_accuracy = np.diag(confusion).sum() / confusion.sum()
mean_pixel_accuracy = np.mean(
np.diag(confusion) / np.sum(confusion, axis=1))
for iou, label_name in zip(ious, camvid_label_names):
print('{:>23} : {:.4f}'.format(label_name, iou))
print('=' * 34)
print('{:>23} : {:.4f}'.format('mean IoU', np.nanmean(ious)))
print('{:>23} : {:.4f}'.format('Class average accuracy',
mean_pixel_accuracy))
print('{:>23} : {:.4f}'.format('Global average accuracy', pixel_accuracy))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model',
choices=('pspnet_resnet101', ),
default='pspnet_resnet101')
parser.add_argument('--pretrained-model')
args = parser.parse_args()
comm = chainermn.create_communicator()
device = comm.intra_rank
if args.model == 'pspnet_resnet101':
if args.pretrained_model:
model = PSPNetResNet101(
n_class=len(cityscapes_semantic_segmentation_label_names),
pretrained_model=args.pretrained_model,
input_size=(713, 713))
else:
model = PSPNetResNet101(pretrained_model='cityscapes')
chainer.cuda.get_device_from_id(device).use()
model.to_gpu()
dataset = CityscapesSemanticSegmentationDataset(split='val',
label_resolution='fine')
if comm.rank == 0:
indices = np.arange(len(dataset))
else:
indices = None
indices = chainermn.scatter_dataset(indices, comm)
dataset = dataset.slice[indices]
it = iterators.SerialIterator(dataset, 1, repeat=False, shuffle=False)
in_values, out_values, rest_values = apply_to_iterator(model.predict,
it,
hook=ProgressHook(
len(dataset)))
# Delete an iterator of images to save memory usage.
del in_values
pred_labels, = out_values
gt_labels, = rest_values
confusion = calc_semantic_segmentation_confusion(pred_labels, gt_labels)
confusion = comm.allreduce(confusion)
if comm.rank == 0:
iou = calc_semantic_segmentation_iou(confusion)
pixel_accuracy = np.diag(confusion).sum() / confusion.sum()
class_accuracy = np.diag(confusion) / np.sum(confusion, axis=1)
for iu, label_name in zip(
iou, cityscapes_semantic_segmentation_label_names):
print('{:>23} : {:.4f}'.format(label_name, iu))
print('=' * 34)
print('{:>23} : {:.4f}'.format('mean IoU', np.nanmean(iou)))
print('{:>23} : {:.4f}'.format('Class average accuracy',
np.nanmean(class_accuracy)))
print('{:>23} : {:.4f}'.format('Global average accuracy',
pixel_accuracy))