def preprocess_image(self, batched_inputs):
r"""
Normalize, pad and batch the input images.
"""
images = [x["image"].to(self.device) for x in batched_inputs]
# images = [img / 255 for img in images]
images = [self.normalizer(img / 255.0) for img in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
return images
def test_rroi_heads(self):
torch.manual_seed(121)
cfg = RCNNConfig()
cfg.MODEL.ANCHOR_GENERATOR.NAME = "RotatedAnchorGenerator"
# PROPOSAL_GENERATOR: "RRPN"
# ROI_HEADS: "RROIHeads"
# ROI_BOX_HEAD.NAME: "FastRCNNConvFCHead"
def build_box_head(cfg, input_shape):
return FastRCNNConvFCHead(cfg, input_shape)
cfg.build_box_head = build_box_head
cfg.MODEL.RESNETS.DEPTH = 50
cfg.MODEL.ROI_BOX_HEAD.NUM_FC = 2
cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1, 1)
cfg.MODEL.RPN.HEAD_NAME = "StandardRPNHead"
cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE = "ROIAlignRotated"
cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5, 1)
backbone = build_backbone(cfg)
num_images = 2
images_tensor = torch.rand(num_images, 20, 30)
image_sizes = [(10, 10), (20, 30)]
images = ImageList(images_tensor, image_sizes)
num_channels = 1024
features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
image_shape = (15, 15)
gt_boxes0 = torch.tensor([[2, 2, 2, 2, 30], [4, 4, 4, 4, 0]], dtype=torch.float32)
gt_instance0 = Instances(image_shape)
gt_instance0.gt_boxes = RotatedBoxes(gt_boxes0)
gt_instance0.gt_classes = torch.tensor([2, 1])
gt_boxes1 = torch.tensor([[1.5, 5.5, 1, 3, 0], [8.5, 4, 3, 2, -50]], dtype=torch.float32)
gt_instance1 = Instances(image_shape)
gt_instance1.gt_boxes = RotatedBoxes(gt_boxes1)
gt_instance1.gt_classes = torch.tensor([1, 2])
gt_instances = [gt_instance0, gt_instance1]
# currently using DefaultAnchorGenerator in RRPN
proposal_generator = RRPN(cfg, backbone.output_shape())
roi_heads = RROIHeads(cfg, backbone.output_shape())
with EventStorage(): # capture events in a new storage to discard them
proposals, proposal_losses = proposal_generator(images, features, gt_instances)
_, detector_losses = roi_heads(images, features, proposals, gt_instances)
expected_losses = {
"loss_cls": torch.tensor(4.381618499755859),
"loss_box_reg": torch.tensor(0.0011829272843897343),
}
for name in expected_losses.keys():
err_msg = "detector_losses[{}] = {}, expected losses = {}".format(
name, detector_losses[name], expected_losses[name]
)
self.assertTrue(torch.allclose(detector_losses[name], expected_losses[name]), err_msg)
def preprocess_image(self, batched_inputs):
"""
Normalize, pad and batch the input images.
"""
images = [x["image"].to(self.device) for x in batched_inputs]
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility,
pad_ref_long=True,
pad_value=0.0)
return images
def forward(self, images, features, gt_instances=None):
"""
See :class:`RPN.forward`.
"""
num_branch = self.num_branch if self.training or not self.trident_fast else 1
# Duplicate images and gt_instances for all branches in TridentNet.
all_images = ImageList(torch.cat([images.tensor] * num_branch),
images.image_sizes * num_branch)
all_gt_instances = gt_instances * num_branch if gt_instances is not None else None
return super(TridentRPN, self).forward(all_images, features,
all_gt_instances)
def _caffe2_preprocess_image(self, inputs):
"""
Caffe2 implementation of preprocess_image, which is called inside each MetaArch's forward.
It normalizes the input images, and the final caffe2 graph assumes the
inputs have been batched already.
"""
data, im_info = inputs
data = alias(data, "data")
im_info = alias(im_info, "im_info")
normalized_data = self._wrapped_model.normalizer(data)
normalized_data = alias(normalized_data, "normalized_data")
# Pack (data, im_info) into ImageList which is recognized by self.inference.
images = ImageList(tensor=normalized_data, image_sizes=im_info)
return images
def test_roi_heads(self):
torch.manual_seed(121)
cfg = RCNNConfig()
# PROPOSAL_GENERATOR: "RPN"
# ROI_HEADS: "StandardROIHeads"
# ROI_BOX_HEAD: "FastRCNNConvFCHead"
cfg.MODEL.RESNETS.DEPTH = 50
cfg.MODEL.ROI_BOX_HEAD.NUM_FC = 2
cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE = "ROIAlignV2"
cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5)
def build_box_head(cfg, input_shape):
return FastRCNNConvFCHead(cfg, input_shape)
cfg.build_box_head = build_box_head
backbone = build_backbone(cfg)
num_images = 2
images_tensor = torch.rand(num_images, 20, 30)
image_sizes = [(10, 10), (20, 30)]
images = ImageList(images_tensor, image_sizes)
num_channels = 1024
features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
image_shape = (15, 15)
gt_boxes0 = torch.tensor([[1, 1, 3, 3], [2, 2, 6, 6]], dtype=torch.float32)
gt_instance0 = Instances(image_shape)
gt_instance0.gt_boxes = Boxes(gt_boxes0)
gt_instance0.gt_classes = torch.tensor([2, 1])
gt_boxes1 = torch.tensor([[1, 5, 2, 8], [7, 3, 10, 5]], dtype=torch.float32)
gt_instance1 = Instances(image_shape)
gt_instance1.gt_boxes = Boxes(gt_boxes1)
gt_instance1.gt_classes = torch.tensor([1, 2])
gt_instances = [gt_instance0, gt_instance1]
proposal_generator = RPN(cfg, backbone.output_shape())
roi_heads = StandardROIHeads(cfg, backbone.output_shape())
with EventStorage(): # capture events in a new storage to discard them
proposals, proposal_losses = proposal_generator(images, features, gt_instances)
_, detector_losses = roi_heads(images, features, proposals, gt_instances)
expected_losses = {
"loss_cls": torch.tensor(4.4236516953),
"loss_box_reg": torch.tensor(0.0091214813),
}
for name in expected_losses.keys():
self.assertTrue(torch.allclose(detector_losses[name], expected_losses[name]))
def forward(self, batched_inputs):
"""
Args:
Same as in :class:`GeneralizedRCNN.forward`
Returns:
list[dict]:
Each dict is the output for one input image.
The dict contains one key "proposals" whose value is a
:class:`Instances` with keys "proposal_boxes" and "objectness_logits".
"""
images = [x["image"].to(self.device) for x in batched_inputs]
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
features = self.backbone(images.tensor)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN,
"'targets' in the model inputs is now renamed to 'instances'!",
n=10)
gt_instances = [
x["targets"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
proposals, proposal_losses = self.proposal_generator(
images, features, gt_instances)
# In training, the proposals are not useful at all but we generate them anyway.
# This makes RPN-only models about 5% slower.
if self.training:
return proposal_losses
processed_results = []
for results_per_image, input_per_image, image_size in zip(
proposals, batched_inputs, images.image_sizes):
height = input_per_image.get("height", image_size[0])
width = input_per_image.get("width", image_size[1])
r = detector_postprocess(results_per_image, height, width)
processed_results.append({"proposals": r})
return processed_results
def preprocess_image(self, batched_inputs):
"""
Normalize, pad and batch the input images.
"""
images = [x["image"].float().to(self.device) for x in batched_inputs]
images = [self.normalizer(img) for img in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
images_whwh = list()
for bi in batched_inputs:
h, w = bi["image"].shape[-2:]
images_whwh.append(
torch.tensor([w, h, w, h],
dtype=torch.float32,
device=self.device))
images_whwh = torch.stack(images_whwh)
return images, images_whwh
def test_rpn_scriptability(self):
cfg = RCNNConfig()
proposal_generator = RPN(cfg, {"res4": ShapeSpec(channels=1024, stride=16)}).eval()
num_images = 2
images_tensor = torch.rand(num_images, 30, 40)
image_sizes = [(32, 32), (30, 40)]
images = ImageList(images_tensor, image_sizes)
features = {"res4": torch.rand(num_images, 1024, 1, 2)}
fields = {"proposal_boxes": "Boxes", "objectness_logits": "Tensor"}
proposal_generator_ts = export_torchscript_with_instances(proposal_generator, fields) # noqa
proposals, _ = proposal_generator(images, features)
proposals_ts, _ = proposal_generator_ts(images, features)
for proposal, proposal_ts in zip(proposals, proposals_ts):
self.assertEqual(proposal.image_size, proposal_ts.image_size)
self.assertTrue(
torch.equal(proposal.proposal_boxes.tensor, proposal_ts.proposal_boxes.tensor)
)
self.assertTrue(torch.equal(proposal.objectness_logits, proposal_ts.objectness_logits))
def forward(self, batched_inputs):
"""
Args:
batched_inputs: a list, batched outputs of :class:`DatasetMapper` .
Each item in the list contains the inputs for one image.
For now, each item in the list is a dict that contains:
image: Tensor, image in (C, H, W) format.
sem_seg: semantic segmentation ground truth
Other information that's included in the original dicts, such as:
"height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
Returns:
list[dict]: Each dict is the output for one input image.
The dict contains one key "sem_seg" whose value is a
Tensor of the output resolution that represents the
per-pixel segmentation prediction.
"""
images = [x["image"].to(self.device) for x in batched_inputs]
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
# step_rate: a float, calculated by current_step/total_step,
# This parameter is used for Scheduled Drop Path.
step_rate = self.iter * 1.0 / self.max_iter
self.iter += 1
features, expt_flops, real_flops = self.backbone(
images.tensor, step_rate)
if "sem_seg" in batched_inputs[0]:
targets = [x["sem_seg"].to(self.device) for x in batched_inputs]
targets = ImageList.from_tensors(
targets, self.backbone.size_divisibility, False,
self.sem_seg_head.ignore_value).tensor
else:
targets = None
results, losses = self.sem_seg_head(features, targets)
# calculate flops
real_flops += self.sem_seg_head.flops
# remove grad, avoid adding flops to the loss sum
real_flops = real_flops.detach().requires_grad_(False)
expt_flops = expt_flops.detach().requires_grad_(False)
flops = {'real_flops': real_flops, 'expt_flops': expt_flops}
# use budget constraint for training
if self.training:
if self.constrain_on and step_rate >= self.unupdate_rate:
warm_up_rate = min(1.0,
(step_rate - self.unupdate_rate) / 0.02)
loss_budget = self.budget_constrint(expt_flops,
warm_up_rate=warm_up_rate)
losses.update({'loss_budget': loss_budget})
losses.update(flops)
return losses
processed_results = []
for result, input_per_image, image_size in zip(results, batched_inputs,
images.image_sizes):
height = input_per_image.get("height")
width = input_per_image.get("width")
r = sem_seg_postprocess(result, image_size, height, width)
processed_results.append({"sem_seg": r, "flops": flops})
return processed_results
def forward(self, batched_inputs):
"""
Args:
batched_inputs: a list, batched outputs of :class:`DatasetMapper`.
Each item in the list contains the inputs for one image.
For now, each item in the list is a dict that contains:
* "image": Tensor, image in (C, H, W) format.
* "instances": Instances
* "sem_seg": semantic segmentation ground truth.
* Other information that's included in the original dicts, such as:
"height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
Returns:
list[dict]:
each dict is the results for one image. The dict contains the following keys:
* "instances": see :meth:`GeneralizedRCNN.forward` for its format.
* "sem_seg": see :meth:`SemanticSegmentor.forward` for its format.
* "panoptic_seg": available when `PANOPTIC_FPN.COMBINE.ENABLED`.
See the return value of
:func:`combine_semantic_and_instance_outputs` for its format.
"""
images = [x["image"].to(self.device) for x in batched_inputs]
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
features = self.backbone(images.tensor)
if "proposals" in batched_inputs[0]:
proposals = [
x["proposals"].to(self.device) for x in batched_inputs
]
proposal_losses = {}
if "sem_seg" in batched_inputs[0]:
gt_sem_seg = [x["sem_seg"].to(self.device) for x in batched_inputs]
gt_sem_seg = ImageList.from_tensors(
gt_sem_seg,
self.backbone.size_divisibility,
pad_value=self.sem_seg_head.ignore_value).tensor
else:
gt_sem_seg = None
sem_seg_results, sem_seg_losses = self.sem_seg_head(
features, gt_sem_seg)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
if self.proposal_generator:
proposals, proposal_losses = self.proposal_generator(
images, features, gt_instances)
detector_results, detector_losses = self.roi_heads(
images, features, proposals, gt_instances)
if self.training:
losses = {}
losses.update(sem_seg_losses)
losses.update({
k: v * self.instance_loss_weight
for k, v in detector_losses.items()
})
losses.update(proposal_losses)
return losses
processed_results = []
for sem_seg_result, detector_result, input_per_image, image_size in zip(
sem_seg_results, detector_results, batched_inputs,
images.image_sizes):
height = input_per_image.get("height", image_size[0])
width = input_per_image.get("width", image_size[1])
sem_seg_r = sem_seg_postprocess(sem_seg_result, image_size, height,
width)
detector_r = detector_postprocess(detector_result, height, width)
processed_results.append({
"sem_seg": sem_seg_r,
"instances": detector_r
})
if self.combine_on:
panoptic_r = combine_semantic_and_instance_outputs(
detector_r,
sem_seg_r.argmax(dim=0),
self.combine_overlap_threshold,
self.combine_stuff_area_limit,
self.combine_instances_confidence_threshold,
)
processed_results[-1]["panoptic_seg"] = panoptic_r
return processed_results
def preprocess_image(self, batched_inputs, training):
"""
Normalize, pad and batch the input images.
"""
images = [x["image"].to(self.device) for x in batched_inputs]
bs = len(images)
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
size_divisibility=0,
pad_ref_long=True)
# sync image size for all gpus
comm.synchronize()
if training and self.iter % self.change_iter == 0:
if self.iter < self.max_iter - 20000:
meg = torch.LongTensor(1).to(self.device)
comm.synchronize()
if comm.is_main_process():
size = np.random.choice(self.multi_size)
meg.fill_(size)
if comm.get_world_size() > 1:
comm.synchronize()
dist.broadcast(meg, 0)
self.size = meg.item()
comm.synchronize()
else:
self.size = 608
if training:
# resize image inputs
modes = ['bilinear', 'nearest', 'bicubic', 'area']
mode = modes[random.randrange(4)]
if mode == 'bilinear' or mode == 'bicubic':
images.tensor = F.interpolate(images.tensor,
size=[self.size, self.size],
mode=mode,
align_corners=False)
else:
images.tensor = F.interpolate(images.tensor,
size=[self.size, self.size],
mode=mode)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN,
"'targets' in the model inputs is now renamed to 'instances'!",
n=10)
gt_instances = [
x["targets"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
targets = [
torch.cat([
instance.gt_classes.float().unsqueeze(-1),
instance.gt_boxes.tensor
],
dim=-1) for instance in gt_instances
]
labels = torch.zeros((bs, 100, 5))
for i, target in enumerate(targets):
labels[i][:target.shape[0]] = target
labels[:, :, 1:] = labels[:, :, 1:] / 512. * self.size
else:
labels = None
self.iter += 1
return images, labels
def test_rpn(self):
torch.manual_seed(121)
cfg = RCNNConfig()
# PROPOSAL_GENERATOR: "RPN"
# ANCHOR_GENERATOR: "DefaultAnchorGenerator"
cfg.MODEL.RESNETS.DEPTH = 50
cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1)
backbone = build_backbone(cfg)
proposal_generator = RPN(cfg, backbone.output_shape())
num_images = 2
images_tensor = torch.rand(num_images, 20, 30)
image_sizes = [(10, 10), (20, 30)]
images = ImageList(images_tensor, image_sizes)
image_shape = (15, 15)
num_channels = 1024
features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
gt_boxes = torch.tensor([[1, 1, 3, 3], [2, 2, 6, 6]], dtype=torch.float32)
gt_instances = Instances(image_shape)
gt_instances.gt_boxes = Boxes(gt_boxes)
with EventStorage(): # capture events in a new storage to discard them
proposals, proposal_losses = proposal_generator(
images, features, [gt_instances[0], gt_instances[1]]
)
expected_losses = {
"loss_rpn_cls": torch.tensor(0.0804563984),
"loss_rpn_loc": torch.tensor(0.0990132466),
}
for name in expected_losses.keys():
err_msg = "proposal_losses[{}] = {}, expected losses = {}".format(
name, proposal_losses[name], expected_losses[name]
)
self.assertTrue(torch.allclose(proposal_losses[name], expected_losses[name]), err_msg)
expected_proposal_boxes = [
Boxes(torch.tensor([[0, 0, 10, 10], [7.3365392685, 0, 10, 10]])),
Boxes(
torch.tensor(
[
[0, 0, 30, 20],
[0, 0, 16.7862777710, 13.1362524033],
[0, 0, 30, 13.3173446655],
[0, 0, 10.8602609634, 20],
[7.7165775299, 0, 27.3875980377, 20],
]
)
),
]
expected_objectness_logits = [
torch.tensor([0.1225359365, -0.0133192837]),
torch.tensor([0.1415634006, 0.0989848152, 0.0565387346, -0.0072308783, -0.0428492837]),
]
for proposal, expected_proposal_box, im_size, expected_objectness_logit in zip(
proposals, expected_proposal_boxes, image_sizes, expected_objectness_logits
):
self.assertEqual(len(proposal), len(expected_proposal_box))
self.assertEqual(proposal.image_size, im_size)
self.assertTrue(
torch.allclose(proposal.proposal_boxes.tensor, expected_proposal_box.tensor)
)
self.assertTrue(torch.allclose(proposal.objectness_logits, expected_objectness_logit))
def test_rrpn(self):
torch.manual_seed(121)
cfg = RCNNConfig()
# PROPOSAL_GENERATOR: "RRPN"
# ANCHOR_GENERATOR: "RotatedAnchorGenerator"
cfg.MODEL.RESNETS.DEPTH = 50
cfg.MODEL.ANCHOR_GENERATOR.SIZES = [[32, 64]]
cfg.MODEL.ANCHOR_GENERATOR.ASPECT_RATIOS = [[0.25, 1]]
cfg.MODEL.ANCHOR_GENERATOR.ANGLES = [[0, 60]]
cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1, 1)
# cfg.MODEL.RPN.HEAD_NAME = "StandardRPNHead"
backbone = build_backbone(cfg)
# currently using DefaultAnchorGenerator in RRPN
proposal_generator = RRPN(cfg, backbone.output_shape())
num_images = 2
images_tensor = torch.rand(num_images, 20, 30)
image_sizes = [(10, 10), (20, 30)]
images = ImageList(images_tensor, image_sizes)
image_shape = (15, 15)
num_channels = 1024
features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
gt_boxes = torch.tensor([[2, 2, 2, 2, 0], [4, 4, 4, 4, 0]], dtype=torch.float32)
gt_instances = Instances(image_shape)
gt_instances.gt_boxes = RotatedBoxes(gt_boxes)
with EventStorage(): # capture events in a new storage to discard them
proposals, proposal_losses = proposal_generator(
images, features, [gt_instances[0], gt_instances[1]]
)
expected_losses = {
"loss_rpn_cls": torch.tensor(0.043263837695121765),
"loss_rpn_loc": torch.tensor(0.14432406425476074),
}
for name in expected_losses.keys():
err_msg = "proposal_losses[{}] = {}, expected losses = {}".format(
name, proposal_losses[name], expected_losses[name]
)
self.assertTrue(torch.allclose(proposal_losses[name], expected_losses[name]), err_msg)
expected_proposal_boxes = [
RotatedBoxes(
torch.tensor(
[
[0.60189795, 1.24095452, 61.98131943, 18.03621292, -4.07244873],
[15.64940453, 1.69624567, 59.59749603, 16.34339333, 2.62692475],
[-3.02982378, -2.69752932, 67.90952301, 59.62455750, 59.97010040],
[16.71863365, 1.98309708, 35.61507797, 32.81484985, 62.92267227],
[0.49432933, -7.92979717, 67.77606201, 62.93098450, -1.85656738],
[8.00880814, 1.36017394, 121.81007385, 32.74150467, 50.44297409],
[16.44299889, -4.82221127, 63.39775848, 61.22503662, 54.12270737],
[5.00000000, 5.00000000, 10.00000000, 10.00000000, -0.76943970],
[17.64130402, -0.98095351, 61.40377808, 16.28918839, 55.53118134],
[0.13016054, 4.60568953, 35.80157471, 32.30180359, 62.52872086],
[-4.26460743, 0.39604485, 124.30079651, 31.84611320, -1.58203125],
[7.52815342, -0.91636634, 62.39784622, 15.45565224, 60.79549789],
]
)
),
RotatedBoxes(
torch.tensor(
[
[0.07734215, 0.81635046, 65.33510590, 17.34688377, -1.51821899],
[-3.41833067, -3.11320257, 64.17595673, 60.55617905, 58.27033234],
[20.67383385, -6.16561556, 63.60531998, 62.52315903, 54.85546494],
[15.00000000, 10.00000000, 30.00000000, 20.00000000, -0.18218994],
[9.22646523, -6.84775209, 62.09895706, 65.46472931, -2.74307251],
[15.00000000, 4.93451595, 30.00000000, 9.86903191, -0.60272217],
[8.88342094, 2.65560246, 120.95362854, 32.45022202, 55.75970078],
[16.39088631, 2.33887148, 34.78761292, 35.61492920, 60.81977463],
[9.78298569, 10.00000000, 19.56597137, 20.00000000, -0.86660767],
[1.28576660, 5.49873352, 34.93610382, 33.22600174, 60.51599884],
[17.58912468, -1.63270092, 62.96052551, 16.45713997, 52.91245270],
[5.64749718, -1.90428460, 62.37649155, 16.19474792, 61.09543991],
[0.82255805, 2.34931135, 118.83985901, 32.83671188, 56.50753784],
[-5.33874989, 1.64404404, 125.28501892, 33.35424042, -2.80731201],
]
)
),
]
expected_objectness_logits = [
torch.tensor(
[
0.10111768,
0.09112845,
0.08466332,
0.07589971,
0.06650183,
0.06350251,
0.04299347,
0.01864817,
0.00986163,
0.00078543,
-0.04573630,
-0.04799230,
]
),
torch.tensor(
[
0.11373727,
0.09377633,
0.05281663,
0.05143715,
0.04040275,
0.03250912,
0.01307789,
0.01177734,
0.00038105,
-0.00540255,
-0.01194804,
-0.01461012,
-0.03061717,
-0.03599222,
]
),
]
torch.set_printoptions(precision=8, sci_mode=False)
for proposal, expected_proposal_box, im_size, expected_objectness_logit in zip(
proposals, expected_proposal_boxes, image_sizes, expected_objectness_logits
):
self.assertEqual(len(proposal), len(expected_proposal_box))
self.assertEqual(proposal.image_size, im_size)
# It seems that there's some randomness in the result across different machines:
# This test can be run on a local machine for 100 times with exactly the same result,
# However, a different machine might produce slightly different results,
# thus the atol here.
err_msg = "computed proposal boxes = {}, expected {}".format(
proposal.proposal_boxes.tensor, expected_proposal_box.tensor
)
self.assertTrue(
torch.allclose(
proposal.proposal_boxes.tensor, expected_proposal_box.tensor, atol=1e-5
),
err_msg,
)
err_msg = "computed objectness logits = {}, expected {}".format(
proposal.objectness_logits, expected_objectness_logit
)
self.assertTrue(
torch.allclose(proposal.objectness_logits, expected_objectness_logit, atol=1e-5),
err_msg,
)
def f(image_tensor, image_shape: List[Tuple[int, int]]):
return ImageList(image_tensor, image_shape)
