def __getitem__(self, index):
ann = self.coco[index]
# bbox transform.
bbox = np.array([ann["bbox"]]) # xmin, ymin, w, h
bbox = BoxMode.convert(bbox, BoxMode.XYWH_ABS,
BoxMode.XYXY_ABS) # x1y1x2y2
bbox = Boxes(bbox)
# mask transform.
mask = PolygonMasks([ann["segmentation"]])
mask = mask.crop_and_resize(bbox.tensor, self.size).float()
return mask
def __getitem__(self, index):
ann = self.all_annotations[index]
# bbox transform.
bbox = np.array([ann["bbox"]]) # xmin, ymin, xmax, ymax
bbox = Boxes(bbox)
# mask transform.
# print(bbox)
# print(ann["segmentation"])
mask = PolygonMasks([ann["segmentation"]])
mask = mask.crop_and_resize(bbox.tensor, self.size).float()
return mask
def valid_dct_source(coco, dct_dim, mask_size):
dct_mask_encoding = DctMaskEncoding(dct_dim, mask_size)
mIoU = []
Number = 0
for ann in coco:
Number += 1
bbox = np.array([ann["bbox"]]) # xmin, ymin, w, h
w, h = bbox[0][2], bbox[0][3]
w, h = round(w), round(h)
bbox = BoxMode.convert(bbox, BoxMode.XYWH_ABS,
BoxMode.XYXY_ABS) # x1y1x2y2
bbox = Boxes(bbox)
# mask transform.
mask = PolygonMasks([ann["segmentation"]])
mask_source = rasterize_polygons_within_box_for_arbitrary_shape(
mask.polygons[0], bbox.tensor[0].numpy(), h, w)
mask_source = mask_source.numpy() # numpy [h,w] binary
mask_k = mask.crop_and_resize(
bbox.tensor, mask_size).float() # tensor [1,28,28],all 0 or 1
mask_k = mask_k.view([mask_size, mask_size])
dct_code = dct_mask_encoding.encode(mask_k)
mask_re = dct_mask_encoding.decode(dct_code).numpy().squeeze()
res = cv2.resize(mask_re.astype('float'),
dsize=(mask_source.shape[1], mask_source.shape[0]),
interpolation=cv2.INTER_LINEAR)
res = np.where(res >= 0.5, 1, 0)
res = np.reshape(res, [1, -1])
mask_source = np.reshape(mask_source, [1, -1])
res = res.astype(int)
IoUevaluate = IOUMetric(2)
IoUevaluate.add_batch(res, mask_source)
_, _, _, mean_iu, _ = IoUevaluate.evaluate()
mIoU.append(mean_iu)
if Number % 1000 == 1:
print(np.mean(mIoU))
return np.mean(mIoU)
def __getitem__(self, index):
ann = self.coco[index]
# bbox transform.
bbox = np.array([ann["bbox"]]) # xmin, ymin, w, h
bbox = BoxMode.convert(bbox, BoxMode.XYWH_ABS,
BoxMode.XYXY_ABS) # x1y1x2y2
bbox = Boxes(bbox)
# mask transform.
mask = PolygonMasks([ann["segmentation"]])
mask = mask.crop_and_resize(bbox.tensor, self.size).float()
if self.transform:
if torch.rand(1) < 0.5:
mask = mask.flip(2)
# introduce several noise.
noise_matrix = VALUE_NOISE * torch.rand(mask.shape)
mask = torch.where(mask > noise_matrix, mask - noise_matrix,
noise_matrix)
return mask
