def convert_batched_inputs_to_c2_format(batched_inputs, size_divisibility,
device):
"""
See get_caffe2_inputs() below.
"""
assert all(isinstance(x, dict) for x in batched_inputs)
assert all(x["image"].dim() == 3 for x in batched_inputs)
images = [x["image"] for x in batched_inputs]
images = ImageList.from_tensors(images, size_divisibility)
im_info = []
for input_per_image, image_size in zip(batched_inputs, images.image_sizes):
target_height = input_per_image.get("height", image_size[0])
target_width = input_per_image.get("width", image_size[1]) # noqa
# NOTE: The scale inside im_info is kept as convention and for providing
# post-processing information if further processing is needed. For
# current Caffe2 model definitions that don't include post-processing inside
# the model, this number is not used.
# NOTE: There can be a slight difference between width and height
# scales, using a single number can results in numerical difference
# compared with D2's post-processing.
scale = target_height / image_size[0]
im_info.append([image_size[0], image_size[1], scale])
im_info = torch.Tensor(im_info)
return images.tensor.to(device), im_info.to(device)
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)
features = self.backbone(images.tensor)
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, self.sem_seg_head.ignore_value
).tensor
else:
targets = None
results, losses = self.sem_seg_head(features, targets)
if self.training:
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})
return processed_results
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)
return images
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 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, 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