def next(self):
# just grab the next random frame
frame = self.source[random.choice(self.frame_ids)]
# frame.show_image_with_labels()
# get a random crop object
crop_objs = filter(lambda x: not self.obj_types or x.obj_type in self.obj_types,frame.get_objects())
# print 'Num crop objs in sample: {0}'.format(len(crop_objs))
crop = random.choice(crop_objs)
# print 'crop_box: ' + str(crop.box)
# frame.show_image_with_labels()
# 1) Randomly perturb crop box (scale and translation)
transformed_box = RandomPerturber.perturb_crop_box(crop.box,{})
# 2) Take crop, todo, change to using center crop to preserve aspect ratio
# check if the affine is identity within some toleranc, then don't bother applying
affine = Affine()
scalex = float(self.crop_size[0])/transformed_box.edges()[0]
scaley = float(self.crop_size[1])/transformed_box.edges()[1]
affine.append(Affine.translation(-transformed_box.xy_min()))
affine.append(Affine.scaling((scalex,scaley)))
transformed_image = affine.apply_to_image(frame.image,self.crop_size)
# transformed_image.visualize(title='transformed image')
# 3) Randomly perturb cropped image (rotation only)
chw_image = transformed_image.to_order_and_class(Ordering.CHW,ValueClass.FLOAT01)
# chw_image.visualize(title='chw_image')
sample = AutoEncoderSample([torch.Tensor(chw_image.get_data().astype(float))],
[torch.Tensor(chw_image.get_data().astype(float))])
return sample
def load_train(self):
frame1, frame2, neg_box, pos_box, anchor_box = None, None, None, None, None
# TODO, this should probably break if never find anything for a while
while neg_box is None:
indices = random.sample(self.frame_ids, 2)
frame1, frame2 = [self.source[x] for x in indices]
frame1_objs = filter(lambda x: x.obj_type in self.obj_types,
frame1.get_objects())
frame2_objs = filter(lambda x: x.obj_type in self.obj_types,
frame2.get_objects())
# get random pos boxes
pos_box = random.choice(frame1_objs).box
anchor_box = random.choice(frame2_objs).box
# find random neg crop
neg_box = self.find_negative_crop(frame1, frame1_objs)
perturbed_pos_box = RandomPerturber.perturb_crop_box(
pos_box, self.perturbations)
affine_crop0 = crop_image_resize(frame1.image, perturbed_pos_box,
self.crop_size)
pos_crop = affine_crop0.apply_to_image(frame1.image, self.crop_size)
affine_crop1 = crop_image_resize(frame2.image, anchor_box,
self.anchor_size)
anchor_crop = affine_crop1.apply_to_image(frame2.image,
self.anchor_size)
affine_crop2 = crop_image_resize(frame1.image, neg_box, self.crop_size)
neg_crop = affine_crop2.apply_to_image(frame1.image, self.crop_size)
# neg_crop.visualize(display=True,title='neg')
# now find all the boxes that intersect with the perturbed_pos_box
intersected_boxes = []
for obj in filter(lambda x: x.obj_type in self.obj_types,
frame1.get_objects()):
if Box.intersection(obj.box, perturbed_pos_box) is not None:
intersected_boxes.append(obj.box)
intersected_boxes = list(
map(lambda x: affine_crop0.apply_to_box(x), intersected_boxes))
# test display
# disp_frame = Frame.from_image_and_objects(pos_crop,[Object(box_crop)])
# disp_frame.visualize(display=True,title='pos frame')
# pos_crop.visualize(display=True,title='pos crop')
pos = torch.Tensor(
pos_crop.to_order_and_class(
Ordering.CHW, ValueClass.FLOAT01).get_data().astype(float))
neg = torch.Tensor(
neg_crop.to_order_and_class(
Ordering.CHW, ValueClass.FLOAT01).get_data().astype(float))
anchor = torch.Tensor(
anchor_crop.to_order_and_class(
Ordering.CHW, ValueClass.FLOAT01).get_data().astype(float))
# pos_map = generate_response_map_from_boxes(pos_crop.get_hw(),intersected_boxes)
# PTImage.from_2d_numpy(pos_map).visualize(display=True,title='pos frame')
pos_map = torch.Tensor(
generate_response_map_from_boxes(pos_crop.get_hw(),
intersected_boxes))
neg_map = torch.Tensor(
generate_response_map_from_boxes(pos_crop.get_hw()))
data = [pos, neg, anchor]
target = [pos_map, neg_map, anchor]
return TripletDetectionSample(data, target)