class TestSegNetBasic(unittest.TestCase):
def setUp(self):
self.n_class = 10
self.link = SegNetBasic(n_class=self.n_class)
def check_call(self):
xp = self.link.xp
x = chainer.Variable(
xp.random.uniform(low=-1, high=1,
size=(2, 3, 128, 160)).astype(np.float32))
y = self.link(x)
self.assertIsInstance(y, chainer.Variable)
self.assertIsInstance(y.array, xp.ndarray)
self.assertEqual(y.shape, (2, self.n_class, 128, 160))
@attr.slow
def test_call_cpu(self):
self.check_call()
@attr.gpu
@attr.slow
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
@attr.slow
def test_predict_cpu(self):
assert_is_semantic_segmentation_link(self.link, self.n_class)
@attr.gpu
@attr.slow
def test_predict_gpu(self):
self.link.to_gpu()
assert_is_semantic_segmentation_link(self.link, self.n_class)
class TestSegNetBasic(unittest.TestCase):
def setUp(self):
self.n_class = 10
self.link = SegNetBasic(n_class=self.n_class)
def check_call(self):
xp = self.link.xp
x = chainer.Variable(xp.random.uniform(
low=-1, high=1, size=(2, 3, 128, 160)).astype(np.float32))
y = self.link(x)
self.assertIsInstance(y, chainer.Variable)
self.assertIsInstance(y.array, xp.ndarray)
self.assertEqual(y.shape, (2, self.n_class, 128, 160))
@attr.slow
def test_call_cpu(self):
self.check_call()
@attr.gpu
@attr.slow
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
@attr.slow
def test_predict_cpu(self):
assert_is_semantic_segmentation_link(self.link, self.n_class)
@attr.gpu
@attr.slow
def test_predict_gpu(self):
self.link.to_gpu()
assert_is_semantic_segmentation_link(self.link, self.n_class)
def main():
chainer.config.train = False
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained_model', default='camvid')
parser.add_argument('image')
args = parser.parse_args()
model = SegNetBasic(
n_class=len(camvid_label_names),
pretrained_model=args.pretrained_model)
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu()
img = utils.read_image(args.image, color=True)
labels = model.predict([img])
label = labels[0]
fig = plot.figure()
ax1 = fig.add_subplot(1, 2, 1)
vis_image(img, ax=ax1)
ax2 = fig.add_subplot(1, 2, 2)
vis_label(label, camvid_label_names, camvid_label_colors, ax=ax2)
plot.show()
def main():
chainer.config.train = False
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained_model', default='camvid')
parser.add_argument('image')
args = parser.parse_args()
model = SegNetBasic(
n_class=len(camvid_label_names),
pretrained_model=args.pretrained_model)
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu()
img = utils.read_image(args.image, color=True)
labels = model.predict([img])
label = labels[0]
fig = plot.figure()
ax1 = fig.add_subplot(1, 2, 1)
vis_image(img, ax=ax1)
ax2 = fig.add_subplot(1, 2, 2)
vis_semantic_segmentation(
label, camvid_label_names, camvid_label_colors, ax=ax2)
plot.show()
def main():
chainer.config.train = False
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--pretrained-model')
parser.add_argument('--dataset', choices=('camvid', ), default='camvid')
parser.add_argument('image')
args = parser.parse_args()
if args.dataset == 'camvid':
if args.pretrained_model is None:
args.pretrained_model = 'camvid'
label_names = camvid_label_names
colors = camvid_label_colors
model = SegNetBasic(n_class=len(label_names),
pretrained_model=args.pretrained_model)
if args.gpu >= 0:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu()
img = utils.read_image(args.image, color=True)
labels = model.predict([img])
label = labels[0]
fig = plt.figure()
ax1 = fig.add_subplot(1, 2, 1)
vis_image(img, ax=ax1)
ax2 = fig.add_subplot(1, 2, 2)
# Do not overlay the label image on the color image
vis_semantic_segmentation(None, label, label_names, colors, ax=ax2)
plt.show()
def test_pretrained(self):
kwargs = {
'n_class': self.n_class,
'pretrained_model': self.pretrained_model,
}
if self.pretrained_model == 'camvid':
valid = self.n_class in {None, 11}
if valid:
SegNetBasic(**kwargs)
else:
with self.assertRaises(ValueError):
SegNetBasic(**kwargs)
def get_dataset_and_model(dataset_name, model_name, pretrained_model,
input_size):
if dataset_name == 'cityscapes':
dataset = CityscapesSemanticSegmentationDataset(
split='val', label_resolution='fine')
label_names = cityscapes_semantic_segmentation_label_names
elif dataset_name == 'ade20k':
dataset = ADE20KSemanticSegmentationDataset(split='val')
label_names = ade20k_semantic_segmentation_label_names
elif dataset_name == 'camvid':
dataset = CamVidDataset(split='test')
label_names = camvid_label_names
n_class = len(label_names)
if pretrained_model:
pretrained_model = pretrained_model
else:
pretrained_model = dataset_name
if model_name == 'pspnet_resnet101':
model = PSPNetResNet101(n_class=n_class,
pretrained_model=pretrained_model,
input_size=input_size)
elif model_name == 'pspnet_resnet50':
model = PSPNetResNet50(n_class=n_class,
pretrained_model=pretrained_model,
input_size=input_size)
elif model_name == 'segnet':
model = SegNetBasic(n_class=n_class, pretrained_model=pretrained_model)
return dataset, label_names, model
class TestSegNetBasic(unittest.TestCase):
def setUp(self):
self.n_class = 10
self.link = SegNetBasic(n_class=self.n_class)
def check_call(self):
xp = self.link.xp
x = chainer.Variable(
xp.random.uniform(low=-1, high=1,
size=(2, 3, 128, 160)).astype(np.float32))
y = self.link(x)
self.assertIsInstance(y, chainer.Variable)
self.assertIsInstance(y.data, xp.ndarray)
self.assertEqual(y.shape, (2, self.n_class, 128, 160))
def test_call_cpu(self):
self.check_call()
@attr.gpu
def test_call_gpu(self):
self.link.to_gpu()
self.check_call()
def check_predict(self):
hs = np.random.randint(128, 160, size=(2, ))
ws = np.random.randint(128, 160, size=(2, ))
imgs = [
np.random.uniform(size=(3, hs[0], ws[0])).astype(np.float32),
np.random.uniform(size=(3, hs[1], ws[1])).astype(np.float32),
]
labels = self.link.predict(imgs)
self.assertEqual(len(labels), 2)
for i in range(2):
self.assertIsInstance(labels[i], np.ndarray)
self.assertEqual(labels[i].shape, (hs[i], ws[i]))
self.assertEqual(labels[i].dtype, np.int64)
def test_predict_cpu(self):
self.check_predict()
@attr.gpu
def test_predict_gpu(self):
self.link.to_gpu()
self.check_predict()
def get_segnet(batchsize):
model = SegNetBasic(n_class=17)
model = PixelwiseSoftmaxClassifier(model, class_weight=np.ones(17))
x = np.random.uniform(size=(batchsize, 3, 1024, 1024)).astype('f')
x = chainer.as_variable(x)
t = np.random.randint(size=(batchsize, 1024, 1024), low=0, high=10)\
.astype(np.int32)
t = chainer.as_variable(t)
return [x, t], model
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('--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:
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_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
result = eval_semantic_segmentation(pred_labels, gt_labels)
for iu, label_name in zip(result['iou'], camvid_label_names):
print('{:>23} : {:.4f}'.format(label_name, iu))
print('=' * 34)
print('{:>23} : {:.4f}'.format('mean IoU', result['miou']))
print('{:>23} : {:.4f}'.format('Class average accuracy',
result['mean_class_accuracy']))
print('{:>23} : {:.4f}'.format('Global average accuracy',
result['pixel_accuracy']))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--batchsize', type=int, default=12)
parser.add_argument('--class_weight', type=str, default='class_weight.npy')
parser.add_argument('--out', type=str, default='result')
args = parser.parse_args()
# Triggers
log_trigger = (50, 'iteration')
validation_trigger = (2000, 'iteration')
end_trigger = (16000, 'iteration')
# Dataset
train = CamVidDataset(split='train')
train = TransformDataset(train, transform)
val = CamVidDataset(split='val')
# Iterator
train_iter = iterators.MultiprocessIterator(train, args.batchsize)
val_iter = iterators.MultiprocessIterator(
val, args.batchsize, shuffle=False, repeat=False)
# Model
class_weight = np.load(args.class_weight)
model = SegNetBasic(n_class=11)
model = PixelwiseSoftmaxClassifier(
model, class_weight=class_weight)
if args.gpu >= 0:
# Make a specified GPU current
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu() # Copy the model to the GPU
# Optimizer
optimizer = optimizers.MomentumSGD(lr=0.1, momentum=0.9)
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer.WeightDecay(rate=0.0005))
# Updater
updater = training.StandardUpdater(train_iter, optimizer, device=args.gpu)
# Trainer
trainer = training.Trainer(updater, end_trigger, out=args.out)
trainer.extend(extensions.LogReport(trigger=log_trigger))
trainer.extend(extensions.observe_lr(), trigger=log_trigger)
trainer.extend(extensions.dump_graph('main/loss'))
if extensions.PlotReport.available():
trainer.extend(extensions.PlotReport(
['main/loss'], x_key='iteration',
file_name='loss.png'))
trainer.extend(extensions.PlotReport(
['validation/main/miou'], x_key='iteration',
file_name='miou.png'))
trainer.extend(extensions.snapshot_object(
model.predictor, filename='model_iteration-{.updater.iteration}'),
trigger=end_trigger)
trainer.extend(extensions.PrintReport(
['epoch', 'iteration', 'elapsed_time', 'lr',
'main/loss', 'validation/main/miou',
'validation/main/mean_class_accuracy',
'validation/main/pixel_accuracy']),
trigger=log_trigger)
trainer.extend(extensions.ProgressBar(update_interval=10))
trainer.extend(
SemanticSegmentationEvaluator(
val_iter, model.predictor,
camvid_label_names),
trigger=validation_trigger)
trainer.run()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=-1)
parser.add_argument('--batchsize', type=int, default=12)
parser.add_argument('--class_weight', type=str, default='class_weight.npy')
parser.add_argument('--out', type=str, default='result')
args = parser.parse_args()
# Triggers
log_trigger = (50, 'iteration')
validation_trigger = (2000, 'iteration')
end_trigger = (16000, 'iteration')
# Dataset
train = CamVidDataset(split='train')
train = TransformDataset(train, transform)
val = CamVidDataset(split='val')
# Iterator
train_iter = iterators.MultiprocessIterator(train, args.batchsize)
val_iter = iterators.MultiprocessIterator(val,
args.batchsize,
shuffle=False,
repeat=False)
# Model
class_weight = np.load(args.class_weight)
model = SegNetBasic(n_class=len(camvid_label_names))
model = PixelwiseSoftmaxClassifier(model, class_weight=class_weight)
if args.gpu >= 0:
# Make a specified GPU current
chainer.cuda.get_device_from_id(args.gpu).use()
model.to_gpu() # Copy the model to the GPU
# Optimizer
optimizer = optimizers.MomentumSGD(lr=0.1, momentum=0.9)
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer_hooks.WeightDecay(rate=0.0005))
# Updater
updater = training.updaters.StandardUpdater(train_iter,
optimizer,
device=args.gpu)
# Trainer
trainer = training.Trainer(updater, end_trigger, out=args.out)
trainer.extend(extensions.LogReport(trigger=log_trigger))
trainer.extend(extensions.observe_lr(), trigger=log_trigger)
trainer.extend(extensions.dump_graph('main/loss'))
if extensions.PlotReport.available():
trainer.extend(
extensions.PlotReport(['main/loss'],
x_key='iteration',
file_name='loss.png'))
trainer.extend(
extensions.PlotReport(['validation/main/miou'],
x_key='iteration',
file_name='miou.png'))
trainer.extend(extensions.snapshot_object(
model.predictor, filename='model_iteration-{.updater.iteration}'),
trigger=end_trigger)
trainer.extend(extensions.PrintReport([
'epoch', 'iteration', 'elapsed_time', 'lr', 'main/loss',
'validation/main/miou', 'validation/main/mean_class_accuracy',
'validation/main/pixel_accuracy'
]),
trigger=log_trigger)
trainer.extend(extensions.ProgressBar(update_interval=10))
trainer.extend(SemanticSegmentationEvaluator(val_iter, model.predictor,
camvid_label_names),
trigger=validation_trigger)
trainer.run()
def main():
# This follows evaluation code used in SegNet.
# https://github.com/alexgkendall/SegNet-Tutorial/blob/master/
# # Scripts/compute_test_results.m
parser = argparse.ArgumentParser()
parser.add_argument('gpu', type=int, default=-1)
parser.add_argument('snapshot', type=str)
parser.add_argument('--batchsize', type=int, default=24)
args = parser.parse_args()
n_class = 11
ignore_labels = [-1]
model = SegNetBasic(n_class=n_class)
serializers.load_npz(args.snapshot, model)
model = calc_bn_statistics(model, args.gpu)
model.train = False
if args.gpu >= 0:
model.to_gpu(args.gpu)
test = CamVidDataset(split='test')
it = chainer.iterators.SerialIterator(test,
batch_size=args.batchsize,
repeat=False,
shuffle=False)
n_positive = [0 for _ in range(n_class)]
n_true = [0 for _ in range(n_class)]
n_true_positive = [0 for _ in range(n_class)]
for batch in it:
img, gt_label = concat_examples(batch, args.gpu)
img = chainer.Variable(img, volatile=True)
pred_label = F.argmax(F.softmax(model(img)), axis=1)
pred_label = cuda.to_cpu(pred_label.data)
gt_label = cuda.to_cpu(gt_label)
for cls_i in range(n_class):
if cls_i in ignore_labels:
continue
n_positive[cls_i] += np.sum(pred_label == cls_i)
n_true[cls_i] += np.sum(gt_label == cls_i)
n_true_positive[cls_i] += np.sum(
(pred_label == cls_i) * (gt_label == cls_i))
ious = []
mean_accs = []
pixel_accs = []
for cls_i in range(n_class):
if cls_i in ignore_labels:
continue
deno = n_positive[cls_i] + n_true[cls_i] - n_true_positive[cls_i]
iou = n_true_positive[cls_i] / deno
ious.append(iou)
print('{:>23} : {:.4f}'.format(camvid_label_names[cls_i], iou))
mean_accs.append(n_true_positive[cls_i] / n_true[cls_i])
pixel_accs.append([n_true_positive[cls_i], n_true[cls_i]])
print('=' * 34)
print('{:>23} : {:.4f}'.format('mean IoU', np.mean(ious)))
print('{:>23} : {:.4f}'.format('Class average accuracy',
np.mean(mean_accs)))
pixel_accs = np.asarray(pixel_accs)
pixel_accs = pixel_accs[:, 0].sum() / pixel_accs[:, 1].sum()
print('{:>23} : {:.4f}'.format('Global average accuracy', pixel_accs))
def setUp(self):
self.n_class = 10
self.link = SegNetBasic(n_class=self.n_class)
def setUp(self):
self.n_class = 10
self.link = SegNetBasic(n_class=self.n_class)
def handler(context):
# Triggers
log_trigger = (50, 'iteration')
validation_trigger = (2000, 'iteration')
end_trigger = (nb_iterations, 'iteration')
# Dataset
dataset_alias = context.datasets
train_dataset_id = dataset_alias['train']
val_dataset_id = dataset_alias['val']
train = SegmentationDatasetFromAPI(train_dataset_id)
val = SegmentationDatasetFromAPI(val_dataset_id)
class_weight = calc_weight(train)
print(class_weight)
train = TransformDataset(train, transform)
# Iterator
train_iter = iterators.SerialIterator(train, BATCHSIZE)
val_iter = iterators.SerialIterator(val,
BATCHSIZE,
shuffle=False,
repeat=False)
# Model
model = SegNetBasic(n_class=len(camvid_label_names))
model = PixelwiseSoftmaxClassifier(model, class_weight=class_weight)
if USE_GPU >= 0:
# Make a specified GPU current
chainer.cuda.get_device_from_id(USE_GPU).use()
model.to_gpu() # Copy the model to the GPU
# Optimizer
optimizer = optimizers.MomentumSGD(lr=0.1, momentum=0.9)
optimizer.setup(model)
optimizer.add_hook(chainer.optimizer_hooks.WeightDecay(rate=0.0005))
# Updater
updater = training.updaters.StandardUpdater(train_iter,
optimizer,
device=USE_GPU)
# Trainer
trainer = training.Trainer(updater,
end_trigger,
out=ABEJA_TRAINING_RESULT_DIR)
trainer.extend(extensions.LogReport(trigger=log_trigger))
trainer.extend(extensions.observe_lr(), trigger=log_trigger)
trainer.extend(extensions.dump_graph('main/loss'))
trainer.extend(extensions.snapshot_object(
model.predictor, filename='model_iteration-{.updater.iteration}'),
trigger=end_trigger)
print_entries = [
'iteration', 'main/loss', 'validation/main/miou',
'validation/main/mean_class_accuracy', 'validation/main/pixel_accuracy'
]
report_entries = [
'epoch', 'iteration', 'lr', 'main/loss', 'validation/main/miou',
'validation/main/mean_class_accuracy', 'validation/main/pixel_accuracy'
]
trainer.extend(Statistics(report_entries,
nb_iterations,
obs_key='iteration'),
trigger=log_trigger)
trainer.extend(Tensorboard(report_entries, out_dir=log_path))
trainer.extend(extensions.PrintReport(print_entries), trigger=log_trigger)
trainer.extend(SemanticSegmentationEvaluator(val_iter, model.predictor,
camvid_label_names),
trigger=validation_trigger)
trainer.run()