def __getitem__(self, index):
if self.is_test:
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
img1 = np.array(img1).astype(np.uint8)[..., :3]
img2 = np.array(img2).astype(np.uint8)[..., :3]
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
return img1, img2, self.extra_info[index]
if not self.init_seed:
worker_info = torch.utils.data.get_worker_info()
if worker_info is not None:
torch.manual_seed(worker_info.id)
np.random.seed(worker_info.id)
random.seed(worker_info.id)
self.init_seed = True
index = index % len(self.image_list)
valid = None
if self.sparse:
flow, valid = frame_utils.readFlowKITTI(self.flow_list[index])
else:
flow = frame_utils.read_gen(self.flow_list[index])
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
flow = np.array(flow).astype(np.float32)
img1 = np.array(img1).astype(np.uint8)
img2 = np.array(img2).astype(np.uint8)
# grayscale images
if len(img1.shape) == 2:
img1 = np.tile(img1[..., None], (1, 1, 3))
img2 = np.tile(img2[..., None], (1, 1, 3))
else:
img1 = img1[..., :3]
img2 = img2[..., :3]
if self.augmentor is not None:
if self.sparse:
img1, img2, flow, valid = self.augmentor(
img1, img2, flow, valid)
else:
img1, img2, flow = self.augmentor(img1, img2, flow)
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
flow = torch.from_numpy(flow).permute(2, 0, 1).float()
if valid is not None:
valid = torch.from_numpy(valid)
else:
valid = (flow[0].abs() < 1000) & (flow[1].abs() < 1000)
return img1, img2, flow, valid.float()
def __getitem__(self, index):
np.random.seed()
index = index % len(self.image_list)
frame_id = self.image_list[index][0]
frame_id = frame_id.split('/')[-1]
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
flow, valid = frame_utils.readFlowKITTI(self.flow_list[index])
img1 = np.array(img1).astype(np.uint8)[..., :3]
img2 = np.array(img2).astype(np.uint8)[..., :3]
if self.do_augument:
img1, img2, flow, valid = self.augumentor(img1, img2, flow, valid)
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
flow = torch.from_numpy(flow).permute(2, 0, 1).float()
valid = torch.from_numpy(valid).float()
if self.do_pad:
ht, wd = img1.shape[1:]
pad_ht = (((ht // 128) + 1) * 128 - ht) % 128
pad_wd = (((wd // 128) + 1) * 128 - wd) % 128
pad_ht1 = [0, pad_ht]
pad_wd1 = [pad_wd // 2, pad_wd - pad_wd // 2]
pad = pad_wd1 + pad_ht1
img1 = img1.view(1, 3, ht, wd)
img2 = img2.view(1, 3, ht, wd)
flow = flow.view(1, 2, ht, wd)
valid = valid.view(1, 1, ht, wd)
img1 = torch.nn.functional.pad(img1, pad, mode='replicate')
img2 = torch.nn.functional.pad(img2, pad, mode='replicate')
flow = torch.nn.functional.pad(flow, pad, mode='constant', value=0)
valid = torch.nn.functional.pad(valid,
pad,
mode='replicate',
value=0)
img1 = img1.view(3, ht + pad_ht, wd + pad_wd)
img2 = img2.view(3, ht + pad_ht, wd + pad_wd)
flow = flow.view(2, ht + pad_ht, wd + pad_wd)
valid = valid.view(ht + pad_ht, wd + pad_wd)
img1 = (img1 / 255 - 0.5) / 0.5
img2 = (img2 / 255 - 0.5) / 0.5
if self.return_path:
return [img1, img2], flow, valid, frame_id
return [img1, img2], flow, valid
def __getitem__(self, index):
if self.is_test:
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
img1 = np.array(img1).astype(np.uint8)[..., :3]
img2 = np.array(img2).astype(np.uint8)[..., :3]
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
return img1, img2, self.extra_info[index]
if not self.init_seed:
worker_info = torch.utils.data.get_worker_info()
if worker_info is not None:
torch.manual_seed(worker_info.id)
np.random.seed(worker_info.id)
random.seed(worker_info.id)
self.init_seed = True
index = index % len(self.image_list)
valid = None
if self.sparse:
flow, valid = frame_utils.readFlowKITTI(self.flow_list[index])
else:
flow = frame_utils.read_gen(self.flow_list[index])
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
flow = np.array(flow).astype(np.float32)
img1 = np.array(img1).astype(np.uint8)
img2 = np.array(img2).astype(np.uint8)
# grayscale images
if len(img1.shape) == 2:
img1 = np.tile(img1[..., None], (1, 1, 3))
img2 = np.tile(img2[..., None], (1, 1, 3))
else:
img1 = img1[..., :3]
img2 = img2[..., :3]
if self.augmentor is not None:
if self.sparse:
img1, img2, flow, valid = self.augmentor(
img1, img2, flow, valid)
else:
img1, img2, flow = self.augmentor(img1, img2, flow)
# cv2.imshow(f'img1{index}', cv2.cvtColor(img1, cv2.COLOR_RGB2BGR))
# cv2.imshow(f'img2{index}', cv2.cvtColor(img2, cv2.COLOR_RGB2BGR))
# cv2.imshow(f'flow{index}', cv2.cvtColor(flow_viz.flow_to_image(flow), cv2.COLOR_RGB2BGR))
# cv2.imshow(f'flowx{index}', flow[:, :, 0] / flow.max())
# cv2.imshow(f'flowy{index}', flow[:, :, 1] / flow.max())
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
flow = torch.from_numpy(flow).permute(2, 0, 1).float()
if valid is not None:
valid = torch.from_numpy(valid)
else:
valid = (flow[0].abs() < 1000) & (flow[1].abs() < 1000)
# cv2.imshow(f'valid{index}', valid.float().numpy())
# cv2.waitKey(0)
return img1, img2, flow, valid.float()
def __getitem__(self, index):
if self.is_test:
frame_id = self.image_list[index][0]
frame_id = frame_id.split('/')[-1]
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
img1 = np.array(img1).astype(np.uint8)[..., :3]
img2 = np.array(img2).astype(np.uint8)[..., :3]
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
return img1, img2, frame_id
else:
if not self.init_seed:
worker_info = torch.utils.data.get_worker_info()
if worker_info is not None:
np.random.seed(worker_info.id)
random.seed(worker_info.id)
self.init_seed = True
index = index % len(self.image_list)
frame_id = self.image_list[index][0]
frame_id = frame_id.split('/')[-1]
img1 = frame_utils.read_gen(self.image_list[index][0])
img2 = frame_utils.read_gen(self.image_list[index][1])
flow, valid = frame_utils.readFlowKITTI(self.flow_list[index])
img1 = np.array(img1).astype(np.uint8)[..., :3]
img2 = np.array(img2).astype(np.uint8)[..., :3]
if self.do_augument:
img1, img2, flow, valid = self.augumentor(
img1, img2, flow, valid)
img1 = torch.from_numpy(img1).permute(2, 0, 1).float()
img2 = torch.from_numpy(img2).permute(2, 0, 1).float()
flow = torch.from_numpy(flow).permute(2, 0, 1).float()
valid = torch.from_numpy(valid).float()
if self.do_pad:
ht, wd = img1.shape[1:]
pad_ht = (((ht // 8) + 1) * 8 - ht) % 8
pad_wd = (((wd // 8) + 1) * 8 - wd) % 8
pad_ht1 = [0, pad_ht]
pad_wd1 = [pad_wd // 2, pad_wd - pad_wd // 2]
pad = pad_wd1 + pad_ht1
img1 = img1.view(1, 3, ht, wd)
img2 = img2.view(1, 3, ht, wd)
flow = flow.view(1, 2, ht, wd)
valid = valid.view(1, 1, ht, wd)
img1 = torch.nn.functional.pad(img1, pad, mode='replicate')
img2 = torch.nn.functional.pad(img2, pad, mode='replicate')
flow = torch.nn.functional.pad(flow,
pad,
mode='constant',
value=0)
valid = torch.nn.functional.pad(valid,
pad,
mode='replicate',
value=0)
img1 = img1.view(3, ht + pad_ht, wd + pad_wd)
img2 = img2.view(3, ht + pad_ht, wd + pad_wd)
flow = flow.view(2, ht + pad_ht, wd + pad_wd)
valid = valid.view(ht + pad_ht, wd + pad_wd)
if self.is_test:
return img1, img2, flow, valid, frame_id
return img1, img2, flow, valid