def predict_malignancy(self,
weights_file,
out_filename,
data_subset_id,
dataset_type='Clean',
configuration=None):
input_shape = (self.model_size, self.model_size, 1)
# prepare model
model = DirectArch(miniXception_loader,
input_shape,
objective="malignancy",
pooling=self.pooling,
output_size=self.out_size,
normalize=True)
if weights_file is not None:
model.load_weights(weights_file)
print('Load from: {}'.format(weights_file))
else:
print('Model without weights')
# prepare test data
images_test, labels_test, classes_test, masks_test, meta_test = \
prepare_data_direct(
load_nodule_dataset(size=self.data_size, res=self.res, sample=self.sample, dataset_type=dataset_type, configuration=configuration)[data_subset_id],
size=self.model_size, return_meta=True, objective="malignancy", verbose=1, balanced=False)
print("Data ready: images({}), labels({})".format(
images_test[0].shape, labels_test.shape))
print("Range = [{:.2f},{:.2f}]".format(np.min(images_test[0]),
np.max(images_test[0])))
images_test = np.array([
crop_center(im, msk, size=self.model_size)[0]
for im, msk in zip(images_test, masks_test)
])
print("Image size changed to {}".format(images_test.shape))
print('Mask not updated')
# eval
print("Begin Predicting...")
pred = model.predict(images_test, round=False)
print("Predication Ready")
print("\tshape = {}\n\trange [{}, {}]".format(pred.shape, np.min(pred),
np.max(pred)))
pickle.dump((images_test, pred, meta_test, labels_test, masks_test),
open(out_filename, 'bw'))
print("Saved to: {}".format(out_filename))
return (images_test, pred, meta_test, labels_test,
masks_test), out_filename
#model = miniXception(None, (size, size,1),'avg', weights='w_002_37-0.95-0.82.h5')
#compile(model, learning_rate=0.01)
model = DirectArch(miniXception_loader, input_shape, 2)
#model.summary()
#model.compile()
model.load_weights('w_007_36-0.91-0.86.h5')
start = timer()
try:
if load:
pred, Size = pickle.load(open('pred_test.p', 'br'))
print("loaded saved dump of predications")
else:
Size = [
getAnnotation(entry['info']).estimate_diameter()
for entry in dataset
]
pred = model.predict(images_test, round=False)
pickle.dump((pred, Size), open('pred_test.p', 'bw'))
MalignancyConfusionMatrix(pred, labels_test[:])
MalignancyBySize(pred, labels_test[:], Size[:])
plt.show()
finally:
total_time = (timer() - start) / 60 / 60
print("Total runtime is {:.1f} hours".format(total_time))
class Rating:
def __init__(self, pooling='max'):
self.pred_file_format = '.\output\embed\predR_dirR{}_E{}_{}.p'
self.pooling = pooling
# Setup
self.in_size = 128
self.out_size = 128
input_shape = (self.in_size, self.in_size, 1)
# prepare model
self.model = DirectArch(miniXception_loader,
input_shape,
objective="rating",
pooling=self.pooling,
output_size=self.out_size,
normalize=True)
def load_dataset(self,
data_subset_id,
size=160,
sample='Normal',
res=0.5,
rating_scale='none',
configuration=None,
dataset_type='Clean'):
# prepare test data
self.images_test, self.labels_test, self.classes_test, self.masks_test, self.meta_test, _ = \
prepare_data_direct(
load_nodule_dataset(size=size, res=res, sample=sample, dataset_type=dataset_type, configuration=configuration)[data_subset_id],
size=size,
return_meta=True, objective="rating", rating_scale=rating_scale, verbose=1,
balanced=False)
print("Data ready: images({}), labels({})".format(
self.images_test[0].shape, self.labels_test.shape))
print("Range = [{:.2f},{:.2f}]".format(np.min(self.images_test[0]),
np.max(self.images_test[0])))
self.images_test = np.array([
crop_center(im, msk, size=self.in_size)[0]
for im, msk in zip(self.images_test, self.masks_test)
])
print("Image size changed to {}".format(self.images_test.shape))
print('Mask not updated')
def pred_filename(self, run, epoch, post):
return self.pred_file_format.format(run, epoch, post)
def load(self, run, epoch, post):
filename = self.pred_filename(run=run, epoch=epoch, post=post)
predict, epochs, images, meta_data, labels, masks = pickle.load(
open(filename, 'br'))
return predict, epochs, images, meta_data, labels, masks
def predict_rating(self, weights_file, out_filename):
if weights_file is not None:
self.model.load_weights(weights_file)
print('Load from: {}'.format(weights_file))
else:
print('Model without weights')
# eval
print("Begin Predicting...")
pred = self.model.predict(self.images_test, round=False)
print("Predication Ready")
print("\tshape = {}\n\trange [{}, {}]".format(pred.shape, np.min(pred),
np.max(pred)))
#pickle.dump((images_test, pred, meta_test, labels_test, masks_test), open(out_filename, 'bw'))
#print("Saved to: {}".format(out_filename))
return (self.images_test, pred, self.meta_test, self.classes_test,
self.labels_test, self.masks_test), out_filename